Skip to content

Change agents and skills fields in plugin.json to array format for Claude Code CLI compatibility - #407

Merged
ViktorHofer merged 12 commits into
mainfrom
copilot/fix-manifest-issues-claude-cli
Mar 20, 2026
Merged

Change agents and skills fields in plugin.json to array format for Claude Code CLI compatibility#407
ViktorHofer merged 12 commits into
mainfrom
copilot/fix-manifest-issues-claude-cli

Conversation

Copilot AI commented Mar 19, 2026

Copy link
Copy Markdown
Contributor

Claude Code CLI validates agents and skills in plugin.json as array<string> per its manifest schema. Our plugins declared these as directory path strings (e.g. "agents": "./agents/", "skills": "./skills/"), causing install failures:

Error: Failed to install: Plugin has an invalid manifest file. Validation errors: agents: Invalid input

Per the Copilot CLI plugin reference, both agents and skills field types are string | string[] with values being "Path(s) to directories". The simplified directory-path array form ["./agents/"] / ["./skills/"] satisfies both Claude Code CLI (requires array) and Copilot CLI (accepts both).

Changes

  • Convert "agents" to a directory-path array in 3 plugin.json files (dotnet-diag, dotnet-msbuild, dotnet-template-engine) — using ["./agents/"]
  • Convert "skills" to a directory-path array in all 10 plugin.json files — using ["./skills/"]
  • Consolidate PluginInfo model — replaced the dual SkillsPath (string) / SkillPaths (array) and AgentsPath (string) / AgentPaths (array) fields with single SkillPaths and AgentPaths fields (IReadOnlyList<string>). The parser normalizes legacy string values into single-element arrays, so all downstream code uses one field with no fallback branching.
  • Update ParsePluginJson to read both skills and agents as string arrays first (preferred, Claude Code schema) and normalize plain strings into single-element arrays
  • Update ValidatePlugin to validate array entries as either directories or files for both fields (safety checks + existence)
  • Update DiscoverSkillsInPlugin and DiscoverAgentsInPlugin to handle array entries as directories (discovering all files within) or individual files
  • Update AgentRunner and CheckCommand to resolve skill directories from the array fields
  • Remove accidentally committed .nuget/nuget.exe binary
-"skills": "./skills/"
+"skills": ["./skills/"]
-"agents": "./agents/"
+"agents": ["./agents/"]
Original prompt

This section details on the original issue you should resolve

<issue_title>Manifest issues with Claude Code CLI</issue_title>
<issue_description>After adding the marketplace and attempting to add the dotnet-diag plugin, Claude is reporting (on Windows):

Image

Looks like a possible known issue with CC and mismatch in their docs on agents must be array of string: anthropics/claude-code/issues/21598</issue_description>

Comments on the Issue (you are @copilot in this section)


💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

Copilot AI and others added 2 commits March 19, 2026 13:42
…n parser

Claude Code CLI validates `agents` as array-of-strings per its plugin manifest
schema. Our plugin.json files had `"agents": "./agents/"` (a string), which
caused "agents: Invalid input" validation errors on install.

Remove the field from the 3 affected plugin.json files — agents are still
discovered by convention from the `agents/` directory. Also make ParsePluginJson
resilient to both string and array formats for forward-compatibility.

Co-authored-by: ViktorHofer <7412651+ViktorHofer@users.noreply.github.com>
…patibility

Co-authored-by: ViktorHofer <7412651+ViktorHofer@users.noreply.github.com>
Copilot AI changed the title [WIP] [CC-21598] Fix manifest issues with Claude Code CLI Remove agents string field from plugin.json for Claude Code CLI compatibility Mar 19, 2026
Copilot AI requested a review from ViktorHofer March 19, 2026 13:46
@ViktorHofer

Copy link
Copy Markdown
Member

@copilot instead of removing the agents key, I would just make it an array. I would just mirror what we do for skills (glob everything). Also update skill-validator to read the string array and fallback to just a string if an array doesn't exist.

…to read array-first with string fallback

Plugin.json files now declare agents as an array of file paths:
  "agents": ["./agents/foo.agent.md", "./agents/bar.agent.md"]

ParsePluginJson reads the array first (preferred, Claude Code schema),
falls back to a string path (legacy). PluginInfo gains an AgentPaths
field. Validator and discovery use the array when present, else fall
back to directory-based convention.

Co-authored-by: ViktorHofer <7412651+ViktorHofer@users.noreply.github.com>
@ViktorHofer

Copy link
Copy Markdown
Member

@copilot do we need to list every agent in the plugin.json? We don't do that for skills. Check if Claude Code and Copilot CLI support the simplified form (just pointing to the directory).

Copilot AI commented Mar 19, 2026

Copy link
Copy Markdown
Contributor Author

@copilot instead of removing the agents key, I would just make it an array. I would just mirror what we do for skills (glob everything). Also update skill-validator to read the string ...

Done in 129c089. Changed agents to an array of file paths in all 3 plugin.json files (globbing all .agent.md files), and updated skill-validator to read the string array first with string fallback:

  • ParsePluginJson reads array → AgentPaths, falls back to string → AgentsPath
  • ValidatePlugin validates per-file paths from the array (safety checks + existence)
  • DiscoverAgentsInPlugin resolves array entries directly when present, else falls back to directory convention

All 402 tests pass, plugin check confirms 5 agents discovered across 3 plugins.

Copilot AI changed the title Remove agents string field from plugin.json for Claude Code CLI compatibility Change agents field in plugin.json to array format for Claude Code CLI compatibility Mar 19, 2026
…rectories in array entries

Per Copilot CLI spec, agents field values are "Path(s) to agent directories"
— no need to list individual files. Use ["./agents/"] to mirror how
skills uses "./skills/". Updated validator and discovery to handle both
directory and file entries in the array.

Co-authored-by: ViktorHofer <7412651+ViktorHofer@users.noreply.github.com>
Comment thread .nuget/nuget.exe Outdated

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@copilot remove this file

Copilot AI commented Mar 19, 2026

Copy link
Copy Markdown
Contributor Author

@copilot do we need to list every agent in the plugin.json? We don't do that for skills. Check if Claude Code and Copilot CLI support the simplified form (just pointing to the director...

No, we don't need to list every agent. Per the Copilot CLI plugin reference, the agents field type is string | string[] with values being "Path(s) to agent directories" — not individual files. The only reason we need the array form is that Claude Code CLI rejects the plain string.

Simplified all 3 plugin.json files to "agents": ["./agents/"] in cf96900. Also updated the validator/discovery to handle array entries as directories (not just files).

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

  • code.claude.com
    • Triggering command: /home/REDACTED/work/_temp/ghcca-node/node/bin/node /home/REDACTED/work/_temp/ghcca-node/node/bin/node --enable-source-maps /home/REDACTED/work/_temp/copilot-developer-action-main/dist/index.js (dns block)
  • code.visualstudio.com
    • Triggering command: /home/REDACTED/work/_temp/ghcca-node/node/bin/node /home/REDACTED/work/_temp/ghcca-node/node/bin/node --enable-source-maps /home/REDACTED/work/_temp/copilot-developer-action-main/dist/index.js (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

@ViktorHofer
ViktorHofer marked this pull request as ready for review March 19, 2026 14:14
Copilot AI review requested due to automatic review settings March 19, 2026 14:14
@ViktorHofer

Copy link
Copy Markdown
Member

@copilot do we treat skills the same in plugin.json?

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR updates plugin manifests and the skill-validator tooling to support Claude Code CLI’s requirement that plugin.json declare agents as an array<string>, while preserving compatibility with the legacy Copilot CLI string form.

Changes:

  • Convert agents in 3 plugin.json files from a string to an array of directory paths (e.g., ["./agents/"]).
  • Extend PluginInfo with AgentPaths and update ParsePluginJson/ValidatePlugin to prefer the array form with legacy fallback.
  • Update agent discovery to honor AgentPaths and add tests for parsing/validation behavior.

Reviewed changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated 2 comments.

Show a summary per file
File Description
plugins/dotnet-template-engine/plugin.json Switch agents to array form for Claude Code CLI compatibility.
plugins/dotnet-msbuild/plugin.json Switch agents to array form for Claude Code CLI compatibility.
plugins/dotnet-diag/plugin.json Switch agents to array form for Claude Code CLI compatibility.
eng/skill-validator/src/Models/Models.cs Add PluginInfo.AgentPaths to carry array-based agent paths.
eng/skill-validator/src/Services/PluginValidator.cs Prefer parsing/validating agents as an array with legacy string fallback.
eng/skill-validator/src/Services/SkillDiscovery.cs Discover agents using AgentPaths (dirs or files), else fall back to legacy behavior.
eng/skill-validator/tests/AgentPluginTests.cs Add tests covering parsing agents array and validating array-based agent paths.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

Comment thread eng/skill-validator/src/Services/PluginValidator.cs Outdated
Comment thread eng/skill-validator/src/Services/SkillDiscovery.cs Outdated
ViktorHofer and others added 2 commits March 19, 2026 15:23
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
… to handle both forms

Co-authored-by: ViktorHofer <7412651+ViktorHofer@users.noreply.github.com>
Copilot AI requested review from Redth and jfversluis as code owners March 19, 2026 14:23
…tency

Co-authored-by: ViktorHofer <7412651+ViktorHofer@users.noreply.github.com>

Copilot AI commented Mar 19, 2026

Copy link
Copy Markdown
Contributor Author

@copilot do we treat skills the same in plugin.json?

No, we weren't — skills was still a plain string "./skills/" in all plugin.json files. Converted all 10 to "skills": ["./skills/"] and updated the validator, discovery, and runner to handle both array and string forms (same pattern as agents). 404 tests pass in 6a7e721.

…r Claude Code CLI compatibility

Co-authored-by: ViktorHofer <7412651+ViktorHofer@users.noreply.github.com>
Copilot AI changed the title Change agents field in plugin.json to array format for Claude Code CLI compatibility Change agents and skills fields in plugin.json to array format for Claude Code CLI compatibility Mar 19, 2026
Comment thread eng/skill-validator/src/Models/Models.cs
…le array fields

Remove dual string/array fields from PluginInfo. The parser now
normalizes legacy string values into single-element arrays, so all
downstream code uses only SkillPaths and AgentPaths (IReadOnlyList<string>).
This eliminates all array-vs-string fallback branching.

Co-authored-by: ViktorHofer <7412651+ViktorHofer@users.noreply.github.com>
@srs-adamr

Copy link
Copy Markdown

Thanks for the quick turnaround! We hit this installing dotnet-diag, dotnet-msbuild, and dotnet-template-engine on Claude Code 2.1.79 (macOS ARM64). The other 7 plugins installed fine. We also filed anthropics/claude-code#36268 for the validator bug on their side.

@timheuer

Copy link
Copy Markdown
Contributor

@ViktorHofer is the array for skills needed or just agents. I don't think that was an issue and there is just a diff on the agents definition? Want to make sure we don't break what's already working ;-).

@ViktorHofer

Copy link
Copy Markdown
Member

The skill-validator changes are required so that we are able to validate all forms of plugins. The actual plugin.json changes around skills aren't needed, this is just for consistency. But I tested it and it work with cc and GH cp CLI.

@ViktorHofer

Copy link
Copy Markdown
Member

/evaluate

@JanKrivanek JanKrivanek left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@github-actions

Copy link
Copy Markdown
Contributor

Skill Validation Results

Skill Scenario Quality (Isolated) Quality (Plugin) Skills Loaded Overfit Verdict
csharp-scripts Test a C# language feature with a script 3.0/5 → 4.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ csharp-scripts; tools: skill, create / ✅ csharp-scripts; tools: skill, create, edit 🟡 0.31
nuget-trusted-publishing Set up trusted publishing for a new NuGet library 3.0/5 → 4.0/5 🟢 3.0/5 → 4.0/5 🟢 ✅ nuget-trusted-publishing; tools: skill / ✅ nuget-trusted-publishing; tools: skill ✅ 0.18
nuget-trusted-publishing Set up NuGet publishing without mentioning trusted publishing 2.0/5 → 4.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ nuget-trusted-publishing; tools: report_intent, skill, view, glob, bash, create / ✅ nuget-trusted-publishing; tools: skill, report_intent, view, glob ✅ 0.18
nuget-trusted-publishing Migrate existing workflow from API key to trusted publishing 2.0/5 → 4.0/5 🟢 2.0/5 → 4.0/5 🟢 ✅ nuget-trusted-publishing; tools: skill / ✅ nuget-trusted-publishing; tools: skill, task, bash ✅ 0.18
dotnet-pinvoke Generate LibraryImport declaration from C header (.NET 8+) 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ dotnet-pinvoke; tools: skill / ✅ dotnet-pinvoke; tools: skill ✅ 0.07
dotnet-pinvoke Generate LibraryImport declaration from C header (.NET Framework) 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ dotnet-pinvoke; tools: skill / ✅ dotnet-pinvoke; tools: skill ✅ 0.07
dotnet-trace-collect High CPU in Kubernetes on Linux (.NET 8) 3.0/5 → 3.0/5 3.0/5 → 4.0/5 🟢 ✅ dotnet-trace-collect; tools: report_intent, skill, view / ✅ dotnet-trace-collect; tools: skill, report_intent, view ✅ 0.17
dotnet-trace-collect .NET Framework on Windows without admin privileges 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: skill / ✅ dotnet-trace-collect; tools: skill ✅ 0.17
dotnet-trace-collect .NET 10 on Linux with root access and native call stacks 1.0/5 → 4.0/5 🟢 1.0/5 → 3.0/5 🟢 ✅ dotnet-trace-collect; tools: skill / ✅ dotnet-trace-collect; tools: skill ✅ 0.17
dotnet-trace-collect Memory leak on Linux (.NET 8) 3.0/5 → 3.0/5 3.0/5 → 3.0/5 ✅ dotnet-trace-collect; tools: skill, report_intent, view / ✅ dotnet-trace-collect; tools: report_intent, skill ✅ 0.17 [1]
dotnet-trace-collect Slow requests on Windows with PerfView 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: skill, report_intent, view / ✅ dotnet-trace-collect; tools: skill ✅ 0.17
dotnet-trace-collect Excessive GC on Linux (.NET 8) 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: skill / ✅ dotnet-trace-collect; tools: skill ✅ 0.17
dotnet-trace-collect Hang or deadlock diagnosis on Linux 3.0/5 → 4.0/5 🟢 3.0/5 → 3.0/5 ✅ dotnet-trace-collect; tools: skill, report_intent, view / ✅ dotnet-trace-collect; tools: report_intent, skill, view ✅ 0.17
dotnet-trace-collect Windows container high CPU with PerfView 1.0/5 → 4.0/5 🟢 1.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: report_intent, skill, view / ✅ dotnet-trace-collect; tools: report_intent, skill, view ✅ 0.17
dotnet-trace-collect Long-running intermittent issue with PerfView triggers 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: skill, report_intent, view / ✅ dotnet-trace-collect; tools: skill, report_intent, view ✅ 0.17
dotnet-trace-collect Linux pre-.NET 10 needing native call stacks 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: skill, report_intent, view / ✅ dotnet-trace-collect; tools: skill, report_intent, view ✅ 0.17
dotnet-trace-collect Windows modern .NET with admin high CPU 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: skill, report_intent, view / ✅ dotnet-trace-collect; tools: skill, report_intent, view ✅ 0.17
dotnet-trace-collect Memory leak on .NET Framework Windows 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: skill, report_intent, view / ✅ dotnet-trace-collect; tools: skill, report_intent, view ✅ 0.17
dotnet-trace-collect Kubernetes with console access prefers console tools 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: skill, report_intent, view / ✅ dotnet-trace-collect; tools: report_intent, skill, view ✅ 0.17
dotnet-trace-collect Container installation without .NET SDK 4.0/5 → 4.0/5 4.0/5 → 4.0/5 ✅ dotnet-trace-collect; tools: skill / ✅ dotnet-trace-collect; tools: skill ✅ 0.17
dotnet-trace-collect HTTP 500s from downstream service on Linux (.NET 8) 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: skill, report_intent, view / ✅ dotnet-trace-collect; tools: skill, report_intent, view ✅ 0.17
dotnet-trace-collect Networking timeouts on Windows with admin (.NET 8) 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: report_intent, skill, view / ✅ dotnet-trace-collect; tools: skill, report_intent, view ✅ 0.17
dotnet-trace-collect Assembly loading failure on Linux (.NET 8) 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ dotnet-trace-collect; tools: report_intent, skill, view / ✅ dotnet-trace-collect; tools: skill, report_intent, view ✅ 0.17
microbenchmarking Investigate runtime upgrade performance impact 4.0/5 → 5.0/5 🟢 4.0/5 → 4.0/5 ✅ microbenchmarking; tools: skill / ✅ microbenchmarking; tools: skill ✅ 0.11
clr-activation-debugging Diagnose unexpected FOD dialog from native build tool 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ clr-activation-debugging; tools: skill / ✅ clr-activation-debugging; tools: skill ✅ 0.08 [2]
clr-activation-debugging Diagnose FOD suppressed but activation still failing 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ clr-activation-debugging; tools: skill, bash / ✅ clr-activation-debugging; tools: skill ✅ 0.08
clr-activation-debugging Explain why same binary behaves differently under different launch methods 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ clr-activation-debugging; tools: skill / ✅ clr-activation-debugging; tools: skill ✅ 0.08
clr-activation-debugging Analyze healthy managed EXE activation 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ clr-activation-debugging; tools: skill / ✅ clr-activation-debugging; tools: skill ✅ 0.08 [3]
clr-activation-debugging Identify multiple activation sequences in a single log 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ clr-activation-debugging; tools: skill / ✅ clr-activation-debugging; tools: skill ✅ 0.08 [4]
clr-activation-debugging Explain useLegacyV2RuntimeActivationPolicy in activation log 4.0/5 → 4.0/5 4.0/5 → 4.0/5 ✅ clr-activation-debugging; tools: skill / ✅ clr-activation-debugging; tools: skill ✅ 0.08
clr-activation-debugging Decline non-CLR-activation issue 1.0/5 → 5.0/5 🟢 1.0/5 → 5.0/5 🟢 ✅ clr-activation-debugging; tools: skill, glob / ℹ️ not activated (expected) ✅ 0.08
analyzing-dotnet-performance Detects compiled regex startup budget and regex chain allocations 1.0/5 ⏰ → 5.0/5 ⏰ 🟢 1.0/5 ⏰ → 5.0/5 ⏰ 🟢 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, bash
analyzing-dotnet-performance Detects CurrentCulture comparer and compiled regex budget in inflection rules 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ⏰ ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, grep [5]
analyzing-dotnet-performance Finds per-call Dictionary allocation not hoisted to static 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, bash
analyzing-dotnet-performance Catches compound allocations in recursive number converter with ToLower 3.0/5 → 5.0/5 🟢 3.0/5 → 4.0/5 🟢 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, bash, write_bash, stop_bash
analyzing-dotnet-performance Finds StringComparison.Ordinal missing and FrozenDictionary opportunities 5.0/5 → 5.0/5 5.0/5 → 1.0/5 ⏰ 🔴 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, bash, read_bash, stop_bash
analyzing-dotnet-performance Detects Aggregate+Replace chain and struct missing IEquatable 4.0/5 → 4.0/5 ⏰ 4.0/5 → 4.0/5 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, bash [6]
analyzing-dotnet-performance Finds branched Replace chain in format string manipulation 4.0/5 → 3.0/5 🔴 4.0/5 → 4.0/5 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, bash, write_bash
analyzing-dotnet-performance Catches LINQ on hot-path string processing and All(char.IsUpper) 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, bash
analyzing-dotnet-performance Detects LINQ pipeline in TimeSpan formatting and collection processing 4.0/5 → 3.0/5 🔴 4.0/5 → 5.0/5 🟢 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, bash
analyzing-dotnet-performance Flags Span inconsistencies and compound method chains in truncation library 5.0/5 → 5.0/5 5.0/5 → 4.0/5 🔴 ✅ analyzing-dotnet-performance; tools: skill, bash, read_bash, write_bash, stop_bash / ✅ analyzing-dotnet-performance; tools: skill, bash [7]
analyzing-dotnet-performance Identifies unsealed leaf classes and locale hierarchy patterns 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill, grep
android-tombstone-symbolication Symbolicate .NET frames in an Android tombstone 4.0/5 → 2.0/5 🔴 4.0/5 → 3.0/5 🔴 ✅ android-tombstone-symbolication; tools: skill, read_bash / ✅ android-tombstone-symbolication; tools: skill, read_bash, stop_bash ✅ 0.18
android-tombstone-symbolication Recognize tombstone with no .NET frames 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ android-tombstone-symbolication; tools: skill, bash / ✅ android-tombstone-symbolication; tools: skill, bash ✅ 0.18 [8]
android-tombstone-symbolication Symbolicate CoreCLR frames in an Android tombstone 1.0/5 ⏰ → 3.0/5 🟢 1.0/5 ⏰ → 4.0/5 🟢 ✅ android-tombstone-symbolication; tools: skill, read_bash / ✅ android-tombstone-symbolication; tools: skill, stop_bash ✅ 0.18
android-tombstone-symbolication Recognize NativeAOT tombstone with app binary and libSystem.Native.so 3.0/5 → 4.0/5 🟢 3.0/5 → 4.0/5 🟢 ✅ android-tombstone-symbolication; tools: skill / ✅ android-tombstone-symbolication; tools: skill, read_bash, stop_bash ✅ 0.18
android-tombstone-symbolication Symbolicate multi-thread tombstone 2.0/5 ⏰ → 4.0/5 🟢 2.0/5 ⏰ → 4.0/5 🟢 ✅ android-tombstone-symbolication; tools: skill / ✅ android-tombstone-symbolication; tools: skill ✅ 0.18
android-tombstone-symbolication Handle .NET frames with no BuildId metadata 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ android-tombstone-symbolication; tools: skill, bash / ✅ android-tombstone-symbolication; tools: skill, bash ✅ 0.18
android-tombstone-symbolication Symbolicate tombstone with multiple .NET libraries and different BuildIds 4.0/5 → 1.0/5 ⏰ 🔴 4.0/5 → 1.0/5 ⏰ 🔴 ✅ android-tombstone-symbolication; tools: skill, read_bash / ✅ android-tombstone-symbolication; tools: skill, read_bash ✅ 0.18
android-tombstone-symbolication Reject iOS crash log as wrong format 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ℹ️ not activated (expected) / ℹ️ not activated (expected) ✅ 0.18 [9]
dump-collect Configure automatic crash dumps for CoreCLR app on Linux 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ dump-collect; tools: report_intent, skill, view / ✅ dump-collect; tools: skill, report_intent, view ✅ 0.14 [10]
dump-collect Set up NativeAOT crash dumps with createdump in Kubernetes 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill / ✅ dump-collect; tools: skill ✅ 0.14
dump-collect Recover crash dump from macOS NativeAOT without createdump 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: report_intent, skill, view / ✅ dump-collect; tools: skill, report_intent, view ✅ 0.14
dump-collect Configure CoreCLR dump collection in Alpine Docker as non-root 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill, report_intent, view / ✅ dump-collect; tools: skill, report_intent, view ✅ 0.14
dump-collect Advisory: macOS NativeAOT crash dump recovery steps 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill / ✅ dump-collect; tools: skill ✅ 0.14
dump-collect Advisory: CoreCLR Alpine Docker non-root configuration 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ dump-collect; tools: skill, report_intent, view / ✅ dump-collect; tools: report_intent, skill, view ✅ 0.14 [11]
dump-collect Advisory: NativeAOT Kubernetes dump collection setup 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: report_intent, skill, view / ✅ dump-collect; tools: skill, report_intent, view ✅ 0.14
dump-collect Detect runtime and configure crash dumps for unknown .NET app on Linux 4.0/5 → 3.0/5 🔴 4.0/5 → 4.0/5 ✅ dump-collect; tools: skill / ✅ dump-collect; tools: skill ✅ 0.14
dump-collect Decline dump analysis request 2.0/5 → 4.0/5 🟢 2.0/5 → 5.0/5 🟢 ℹ️ not activated (expected) / ℹ️ not activated (expected) ✅ 0.14
optimizing-ef-core-queries Optimize bulk operations with EF Core 7+ ExecuteUpdate and ExecuteDelete 4.0/5 → 4.0/5 4.0/5 → 4.0/5 ✅ optimizing-ef-core-queries; tools: skill / ✅ optimizing-ef-core-queries; tools: skill ✅ 0.20 [12]
build-parallelism Analyze build parallelism bottlenecks 4.0/5 → 4.0/5 4.0/5 → 5.0/5 🟢 ✅ build-parallelism; tools: skill, task / ✅ build-parallelism; tools: skill, task ✅ 0.16 [13]
including-generated-files Diagnose generated file inclusion failure 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ including-generated-files; tools: skill / ✅ including-generated-files; tools: skill 🟡 0.24
msbuild-antipatterns Review MSBuild files for anti-patterns and style issues 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ msbuild-antipatterns; tools: skill, glob / ✅ msbuild-antipatterns; tools: skill, glob ✅ 0.05 [14]
build-perf-baseline Establish build performance baseline and recommend optimizations 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ build-perf-baseline; tools: skill, glob / ✅ build-perf-baseline; build-perf-diagnostics; tools: skill, glob 🟡 0.27
msbuild-modernization Modernize legacy project to SDK-style 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ msbuild-modernization; tools: skill / ✅ msbuild-modernization; tools: skill ✅ 0.06 [15]
directory-build-organization Organize build infrastructure for a multi-project repo 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ directory-build-organization; tools: skill, task / ✅ directory-build-organization; msbuild-antipatterns; tools: skill ✅ 0.15
check-bin-obj-clash Diagnose bin/obj output path clashes 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ check-bin-obj-clash; tools: skill, edit / ✅ check-bin-obj-clash; tools: glob, skill ✅ 0.15 [16]
incremental-build Analyze incremental build issues 3.0/5 → 5.0/5 🟢 3.0/5 → 4.0/5 🟢 ✅ incremental-build; tools: skill, bash / ✅ incremental-build; tools: skill, bash ✅ 0.12
eval-performance Analyze MSBuild evaluation performance issues 3.0/5 → 4.0/5 🟢 3.0/5 → 4.0/5 🟢 ✅ eval-performance; tools: skill, bash / ✅ eval-performance; tools: skill ✅ 0.18
resolve-project-references Explain misleading ResolveProjectReferences time 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ resolve-project-references; tools: skill / ✅ resolve-project-references; tools: skill ✅ 0.16
msbuild-server Recommend MSBuild Server for slow CLI incremental builds 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ msbuild-server; tools: skill / ✅ msbuild-server; tools: skill 🟡 0.48
build-perf-diagnostics Analyze analyzer performance impact on builds 5.0/5 → 5.0/5 5.0/5 → 4.0/5 🔴 ✅ build-perf-diagnostics; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.23 [17]
binlog-generation Build project with /bl flag 1.0/5 → 5.0/5 🟢 1.0/5 → 5.0/5 🟢 ✅ binlog-generation; tools: skill / ✅ binlog-generation; tools: skill 🟡 0.48
binlog-generation Build with /bl in PowerShell 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ binlog-generation; tools: skill / ✅ binlog-generation; tools: skill 🟡 0.48
binlog-generation Build multiple configurations with unique binlogs 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ binlog-generation; tools: skill / ✅ binlog-generation; tools: skill 🟡 0.48 [18]
binlog-failure-analysis Diagnose build failures from binlog only (no source files) 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ binlog-failure-analysis; tools: skill / ✅ binlog-failure-analysis; tools: skill ✅ 0.04 [19]
dotnet-maui-doctor Plan macOS MAUI setup with Xcode 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill / ✅ dotnet-maui-doctor; tools: skill 🟡 0.22
dotnet-maui-doctor Plan Linux MAUI environment for Android 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill, view / ✅ dotnet-maui-doctor; tools: skill, view 🟡 0.22
dotnet-maui-doctor Guardrail against workload update and repair 1.0/5 → 3.0/5 🟢 1.0/5 → 3.0/5 🟢 ✅ dotnet-maui-doctor; tools: report_intent, skill / ✅ dotnet-maui-doctor; tools: report_intent, skill 🟡 0.22
dotnet-maui-doctor Diagnose non-Microsoft JDK causing build failure 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ dotnet-maui-doctor; tools: skill / ✅ dotnet-maui-doctor; tools: skill 🟡 0.22 [20]
dotnet-maui-doctor Plan complete MAUI setup on Windows 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill / ✅ dotnet-maui-doctor; tools: skill 🟡 0.22 [21]
dotnet-maui-doctor Prevent incorrect JAVA_HOME configuration 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: report_intent, skill, view / ✅ dotnet-maui-doctor; tools: report_intent, skill, view 🟡 0.22
dotnet-maui-doctor Determine required Android SDK packages for specific .NET version 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: report_intent, skill, view, bash / ✅ dotnet-maui-doctor; tools: report_intent, skill, view, bash 🟡 0.22
dotnet-maui-doctor Fix stale MAUI workloads after SDK update 2.0/5 ⏰ → 4.0/5 🟢 2.0/5 ⏰ → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill / ✅ dotnet-maui-doctor; tools: skill 🟡 0.22
technology-selection ML.NET classification on tabular data 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ technology-selection; tools: skill / ✅ technology-selection; tools: skill 🟡 0.31
technology-selection LLM integration with MEAI abstraction 1.0/5 → 3.0/5 🟢 1.0/5 → 1.0/5 ✅ technology-selection; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.31 [22]
technology-selection Reject LLM for tabular classification 3.0/5 → 4.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ technology-selection; tools: skill / ✅ technology-selection; tools: skill, read_bash, stop_bash 🟡 0.31
technology-selection Agentic workflow with guardrails 1.0/5 ⏰ → 1.0/5 ⏰ 1.0/5 ⏰ → 1.0/5 ⏰ ✅ technology-selection; tools: skill / ✅ technology-selection; tools: skill 🟡 0.31
technology-selection Natural-language scenario decomposition — RAG chatbot 4.0/5 → 4.0/5 4.0/5 → 4.0/5 ✅ technology-selection; tools: skill / ✅ technology-selection; tools: skill 🟡 0.31 [23]
technology-selection RAG pipeline with vector search 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ technology-selection; tools: skill / ✅ technology-selection; tools: skill 🟡 0.31
convert-to-cpm Decline CPM conversion for packages.config project 1.0/5 → 2.0/5 🟢 1.0/5 → 2.0/5 🟢 ℹ️ not activated (expected) / ℹ️ not activated (expected) 🟡 0.29
convert-to-cpm Recommend CPM when updating packages with version conflicts 2.0/5 → 2.0/5 2.0/5 → 2.0/5 ✅ convert-to-cpm; tools: skill, glob, bash, create / ✅ convert-to-cpm; tools: skill, glob, bash 🟡 0.29
convert-to-cpm Recommend CPM when updating packages in a complex repository 2.0/5 → 3.0/5 🟢 2.0/5 → 3.0/5 🟢 ✅ convert-to-cpm; tools: skill, read_agent, glob / ✅ convert-to-cpm; tools: skill, glob 🟡 0.29
convert-to-cpm Convert single project to CPM 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ convert-to-cpm; tools: skill, bash / ✅ convert-to-cpm; tools: skill, task, bash 🟡 0.29
convert-to-cpm Convert multi-project solution to CPM 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ convert-to-cpm; tools: skill, task, bash / ✅ convert-to-cpm; tools: skill, task, bash 🟡 0.29
convert-to-cpm Convert solution with MSBuild property versions to CPM 2.0/5 → 4.0/5 🟢 2.0/5 → 4.0/5 🟢 ✅ convert-to-cpm; tools: skill, glob, bash, grep / ✅ convert-to-cpm; tools: skill, task, bash 🟡 0.29
convert-to-cpm Convert solution with version conflicts to CPM 3.0/5 → 5.0/5 🟢 3.0/5 → 4.0/5 🟢 ✅ convert-to-cpm; tools: skill, bash / ✅ convert-to-cpm; tools: skill, bash 🟡 0.29
convert-to-cpm Convert complex repository with multiple CPM challenges 2.0/5 → 4.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ convert-to-cpm; tools: skill / ✅ convert-to-cpm; tools: skill, grep 🟡 0.29
migrate-dotnet9-to-dotnet10 Console app with System.Linq.Async, SIGTERM, and BufferedStream 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, view [24]
migrate-dotnet9-to-dotnet10 Expression tree code broken by C# 14 span overload resolution 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, grep, view / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view [25]
migrate-dotnet9-to-dotnet10 ASP.NET Core app with WebHostBuilder, OpenAPI, and forwarded headers 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill / ✅ migrate-dotnet9-to-dotnet10; tools: skill
migrate-dotnet9-to-dotnet10 ASP.NET Core app with OpenAPI transformers using Microsoft.OpenApi v1 APIs 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view [26]
migrate-dotnet9-to-dotnet10 EF Core app with Azure SQL JSON columns and parameterized collections 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, view [27]
migrate-dotnet9-to-dotnet10 EF Core app with dynamic ExecuteUpdate and complex types 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, view [28]
migrate-dotnet9-to-dotnet10 SQLite app with DateTimeOffset timezone handling 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, grep, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, view
migrate-dotnet9-to-dotnet10 Worker service with config null array binding and ProviderAlias assembly change 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill / ✅ migrate-dotnet9-to-dotnet10; tools: skill
migrate-dotnet9-to-dotnet10 Cryptography app with OpenSSL, X.509, and Rfc2898DeriveBytes 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, view [29]
migrate-dotnet9-to-dotnet10 SDK and NuGet obscure tooling changes 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill / ✅ migrate-dotnet9-to-dotnet10; tools: skill
migrate-dotnet9-to-dotnet10 JSON polymorphism with conflicting property names and XmlSerializer 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill / ✅ migrate-dotnet9-to-dotnet10; tools: skill
migrate-dotnet9-to-dotnet10 WinForms and WPF desktop app with System.Drawing and DynamicResource 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill / ✅ migrate-dotnet9-to-dotnet10; tools: skill
migrate-dotnet9-to-dotnet10 Containerized single-file app with P/Invoke and IDispatchEx 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view
migrate-dotnet9-to-dotnet10 App using SslStream properties and SystemEvents 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill [30]
migrate-dotnet9-to-dotnet10 Library with NuGet auditing, transitive deps, and InlineArray 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view
migrate-dotnet9-to-dotnet10 C# 14 compiler breaking changes — field keyword, extension keyword, disposal 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view
migrate-dotnet9-to-dotnet10 Blazor WASM app with generic math shift masking and tar operations 5.0/5 → 4.0/5 🔴 5.0/5 → 4.0/5 🔴 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, view
migrate-dotnet8-to-dotnet9 App with empty environment variables, ZIP encoding, and keyed DI services 2.0/5 → 4.0/5 🟢 2.0/5 → 4.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash / ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash ✅ 0.06
migrate-dotnet8-to-dotnet9 C# 13 compiler breaking changes — InlineArray on record, iterator safe context, collection expressions 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet8-to-dotnet9; tools: report_intent, skill, view / ✅ migrate-dotnet8-to-dotnet9; tools: skill, report_intent, view ✅ 0.06 [31]
migrate-dotnet8-to-dotnet9 ASP.NET Core app with DI validation, forwarded headers, and HttpClientFactory casting 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.06
migrate-dotnet8-to-dotnet9 EF Core app with migration patterns and Cosmos DB discriminator 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash / ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash ✅ 0.06
migrate-dotnet8-to-dotnet9 EF Core Cosmos DB app with existing documents and composite id format 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.06
migrate-dotnet8-to-dotnet9 App with JsonDocument null deserialization and BinaryFormatter fallback 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet8-to-dotnet9; tools: skill / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.06 [32]
migrate-dotnet8-to-dotnet9 CI pipeline with Terminal Logger parsing and version constraints 2.0/5 → 3.0/5 🟢 2.0/5 → 3.0/5 🟢 ℹ️ not activated (expected) / ℹ️ not activated (expected) ✅ 0.06
migrate-dotnet8-to-dotnet9 WinForms app with custom UserControls and PictureBox URL loading 4.0/5 → 5.0/5 🟢 4.0/5 → 4.0/5 ✅ migrate-dotnet8-to-dotnet9; tools: skill / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.06
migrate-dotnet8-to-dotnet9 Containerized app with zlib dependency and runtime configuration 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.06 [33]
migrate-dotnet8-to-dotnet9 EF Core Cosmos DB app with discriminator and sync I/O 4.0/5 → 4.0/5 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash / ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash ✅ 0.06
migrate-dotnet8-to-dotnet9 Library with String.Trim span overload, keyed services, and InlineArray 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash / ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash ✅ 0.06 [34]
migrate-dotnet8-to-dotnet9 Containerized app with env var precedence reversal and zlib removal 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-dotnet8-to-dotnet9; tools: skill / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.06
thread-abort-migration Worker thread with abort-based cancellation 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ thread-abort-migration; tools: report_intent, skill / ✅ thread-abort-migration; tools: skill ✅ 0.09 [35]
thread-abort-migration Timeout enforcement via Thread.Abort 5.0/5 → 4.0/5 🔴 5.0/5 → 4.0/5 🔴 ✅ thread-abort-migration; tools: report_intent, skill / ✅ thread-abort-migration; tools: skill ✅ 0.09
thread-abort-migration Blocking WaitHandle with Thread.Interrupt 4.0/5 → 5.0/5 🟢 4.0/5 → 4.0/5 ✅ thread-abort-migration; tools: skill / ✅ thread-abort-migration; tools: skill ✅ 0.09 [36]
thread-abort-migration ASP.NET Response.End and Response.Redirect with Thread.Abort 4.0/5 → 4.0/5 4.0/5 → 5.0/5 🟢 ✅ thread-abort-migration; tools: skill, report_intent / ✅ thread-abort-migration; tools: report_intent, skill ✅ 0.09
thread-abort-migration Thread.Join and Thread.Sleep only — should not migrate 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ⚠️ NOT ACTIVATED / ✅ thread-abort-migration; tools: report_intent, skill ✅ 0.09
migrate-nullable-references Enable NRT in a small library with mixed nullability 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-nullable-references; tools: skill / ✅ migrate-nullable-references; tools: skill ✅ 0.05 [37]
migrate-nullable-references File-by-file migration: only modify the targeted file 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED / ⚠️ NOT ACTIVATED ✅ 0.05
migrate-nullable-references Enable NRT in ASP.NET Core Web API with EF Core 4.0/5 → 4.0/5 4.0/5 → 4.0/5 ✅ migrate-nullable-references; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.05
dotnet-aot-compat Make Azure.ResourceManager AOT-compatible 3.0/5 ⏰ → 1.0/5 ⏰ 🔴 3.0/5 ⏰ → 2.0/5 ⏰ 🔴 ✅ dotnet-aot-compat; tools: skill / ✅ dotnet-aot-compat; tools: skill, read_agent ✅ 0.12
migrate-dotnet10-to-dotnet11 Console app with compression and TAR operations 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill / ✅ migrate-dotnet10-to-dotnet11; tools: skill ✅ 0.04
migrate-dotnet10-to-dotnet11 C# 15 compiler breaking changes — Span safe-context, nameof, with() 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view / ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.04
migrate-dotnet10-to-dotnet11 EF Core app with Cosmos DB provider using sync APIs 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view / ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.04 [38]
migrate-dotnet10-to-dotnet11 Deployment to older hardware with minimum requirement changes 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view / ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view ✅ 0.04
migrate-dotnet10-to-dotnet11 Cryptography app using DSA on macOS 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view / ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.04 [39]
migrate-dotnet10-to-dotnet11 Basic TFM update with Docker and global.json 3.0/5 → 4.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill / ✅ migrate-dotnet10-to-dotnet11; tools: skill ✅ 0.04
migrate-dotnet10-to-dotnet11 C# 15 dynamic operator and ref readonly delegate issues 2.0/5 → 2.0/5 2.0/5 → 5.0/5 🟢 ⚠️ NOT ACTIVATED / ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.04 [40]
migrate-mstest-v1v2-to-v3 Migrate MSTest v1 project with assembly reference 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill, bash / ✅ migrate-mstest-v1v2-to-v3; tools: skill, bash ✅ 0.05
migrate-mstest-v1v2-to-v3 Migrate MSTest v2 NuGet project to v3 3.0/5 → 3.0/5 3.0/5 → 3.0/5 ✅ migrate-mstest-v1v2-to-v3; tools: skill / ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.05 [41]
migrate-mstest-v1v2-to-v3 Fix Assert.AreEqual object overload errors after v3 upgrade 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill / ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.05
migrate-mstest-v1v2-to-v3 Migrate from .testsettings to .runsettings 4.0/5 → 4.0/5 4.0/5 → 4.0/5 ✅ migrate-mstest-v1v2-to-v3; tools: skill, bash / ✅ migrate-mstest-v1v2-to-v3; tools: skill, bash ✅ 0.05 [42]
migrate-mstest-v1v2-to-v3 Fix DataRow type mismatch errors after v3 upgrade 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill / ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.05
migrate-mstest-v1v2-to-v3 Migrate to MSTest.Sdk project style 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill, bash / ✅ migrate-mstest-v1v2-to-v3; tools: skill, bash ✅ 0.05
migrate-mstest-v1v2-to-v3 Handle dropped target framework during v3 migration 4.0/5 → 4.0/5 4.0/5 → 4.0/5 ⚠️ NOT ACTIVATED / ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.05 [43]
migrate-mstest-v1v2-to-v3 Migrate complex MSTest v2 project with testsettings, DataRow issues, and dropped TFM 4.0/5 → 5.0/5 🟢 4.0/5 → 4.0/5 ✅ migrate-mstest-v1v2-to-v3; tools: skill / ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.05
migrate-mstest-v1v2-to-v3 Correctly identify MSTest v1 vs v2 and recommend different migration paths 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill / ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.05
writing-mstest-tests Write unit tests for a service class 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ writing-mstest-tests; tools: skill, task, glob, grep / ✅ writing-mstest-tests; tools: skill, task, glob, grep 🟡 0.27 [44]
writing-mstest-tests Write data-driven tests for a calculator 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ writing-mstest-tests; tools: skill, edit / ✅ writing-mstest-tests; tools: skill 🟡 0.27
writing-mstest-tests Write async tests with cancellation 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: report_intent, skill / ✅ writing-mstest-tests; tools: skill 🟡 0.27
writing-mstest-tests Fix swapped Assert.AreEqual arguments 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ writing-mstest-tests; tools: report_intent, skill / ⚠️ NOT ACTIVATED 🟡 0.27
writing-mstest-tests Modernize legacy test patterns 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: skill 🟡 0.27
writing-mstest-tests Replace ExpectedException with Assert.Throws 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: skill 🟡 0.27
writing-mstest-tests Use proper collection assertions 4.0/5 → 2.0/5 🔴 4.0/5 → 3.0/5 🔴 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: skill 🟡 0.27
writing-mstest-tests Use proper type assertions instead of casts 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: skill 🟡 0.27
writing-mstest-tests Set up test lifecycle correctly 2.0/5 → 4.0/5 🟢 2.0/5 → 4.0/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: skill 🟡 0.27
writing-mstest-tests Use DynamicData with ValueTuples over object arrays 3.0/5 → 3.0/5 3.0/5 → 3.0/5 ✅ writing-mstest-tests; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.27
migrate-vstest-to-mtp Migrate MSTest project from VSTest to Microsoft.Testing.Platform 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-vstest-to-mtp; tools: skill, report_intent, view / ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10 [45]
migrate-vstest-to-mtp Migrate NUnit project from VSTest to Microsoft.Testing.Platform 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill / ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10
migrate-vstest-to-mtp Migrate xUnit.net v2 project from VSTest to Microsoft.Testing.Platform 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill, report_intent, view, bash / ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10
migrate-vstest-to-mtp Update Azure DevOps pipeline from VSTest task to MTP 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-vstest-to-mtp; tools: skill / ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10
migrate-vstest-to-mtp Migrate MSTest.Sdk project that explicitly uses VSTest 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill / ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10
migrate-vstest-to-mtp Translate dotnet test VSTest arguments to MTP equivalents 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-vstest-to-mtp; tools: report_intent, skill / ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10 [46]
migrate-vstest-to-mtp Handle exit code 8 when migrating from VSTest to MTP 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill / ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10
migrate-vstest-to-mtp Configure dotnet test MTP mode on .NET 10 SDK 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill / ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10
migrate-vstest-to-mtp Migrate xUnit.net VSTest filter syntax to MTP 1.0/5 → 4.0/5 🟢 1.0/5 → 3.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill / ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10
migrate-vstest-to-mtp Full VSTest to MTP migration plan for MSTest solution 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill / ✅ migrate-vstest-to-mtp; tools: skill, create ✅ 0.10
run-tests Run tests in a VSTest MSTest project 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill / ✅ run-tests; tools: skill 🟡 0.24
run-tests Run tests with trx reporting on MTP project (SDK 9) 2.0/5 ⏰ → 3.0/5 ⏰ 🟢 2.0/5 ⏰ → 3.0/5 ⏰ 🟢 ✅ run-tests; tools: skill / ✅ run-tests; tools: skill 🟡 0.24
run-tests Run tests with blame-hang on MTP project (SDK 10) 2.0/5 → 2.0/5 ⏰ 2.0/5 → 1.0/5 ⏰ 🔴 ✅ run-tests; tools: skill, bash, edit / ⚠️ NOT ACTIVATED 🟡 0.24 [47]
run-tests Run tests in a multi-TFM project targeting a specific framework 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, bash, glob / ✅ run-tests; tools: skill, bash, glob 🟡 0.24
run-tests Filter MSTest tests by category on VSTest 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED / ⚠️ NOT ACTIVATED 🟡 0.24 [48]
run-tests Filter NUnit tests by class name on VSTest 4.0/5 → 2.0/5 🔴 4.0/5 → 4.0/5 ✅ run-tests; tools: skill, bash / ⚠️ NOT ACTIVATED 🟡 0.24
run-tests Filter xUnit v3 tests by class on MTP 1.0/5 → 5.0/5 🟢 1.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, bash / ✅ run-tests; tools: skill 🟡 0.24
run-tests Filter xUnit v3 tests by trait on MTP 1.0/5 → 5.0/5 🟢 1.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view / ✅ run-tests; tools: view, skill 🟡 0.24
run-tests Filter TUnit tests by class using treenode-filter 2.0/5 → 5.0/5 🟢 2.0/5 → 2.0/5 ✅ run-tests; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.24 [49]
run-tests Combine multiple filter criteria on VSTest MSTest 5.0/5 → 3.0/5 🔴 5.0/5 → 4.0/5 🔴 ✅ run-tests; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.24
run-tests MTP project on SDK 9 must use -- separator for args 1.0/5 → 5.0/5 🟢 1.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, glob / ✅ run-tests; tools: skill 🟡 0.24
run-tests MTP project on SDK 10 passes args directly 2.0/5 ⏰ → 3.0/5 ⏰ 🟢 2.0/5 ⏰ → 3.0/5 ⏰ 🟢 ✅ run-tests; tools: skill, glob / ✅ run-tests; tools: skill 🟡 0.24
run-tests Detect test platform from Directory.Build.props 2.0/5 → 5.0/5 🟢 2.0/5 → 2.0/5 ✅ run-tests; tools: skill / ✅ run-tests; tools: skill 🟡 0.24
run-tests Negative test: do not use MTP syntax for a VSTest project 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view / ✅ run-tests; tools: skill, view 🟡 0.24
mtp-hot-reload Suggest hot reload for failing test in MTP project (SDK 9) 1.0/5 → 5.0/5 🟢 1.0/5 → 2.0/5 ⏰ 🟢 ✅ mtp-hot-reload; tools: skill / ✅ mtp-hot-reload; tools: skill ✅ 0.11
mtp-hot-reload Suggest hot reload for failing test in MTP project (SDK 10) 1.0/5 → 3.0/5 🟢 1.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill, bash, create / ✅ mtp-hot-reload; tools: skill, bash, create ✅ 0.11
mtp-hot-reload Enable hot reload when package already installed 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill / ✅ mtp-hot-reload; tools: skill ✅ 0.11
mtp-hot-reload Suggest launchSettings.json configuration for hot reload 1.0/5 → 5.0/5 🟢 1.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill, bash, create / ✅ mtp-hot-reload; tools: skill, bash, create ✅ 0.11
mtp-hot-reload Use dotnet run not dotnet test for hot reload 1.0/5 → 4.0/5 🟢 1.0/5 → 4.0/5 🟢 ✅ mtp-hot-reload; tools: skill / ✅ mtp-hot-reload; tools: report_intent, skill ✅ 0.11
mtp-hot-reload Negative: VSTest project cannot use MTP hot reload 2.0/5 → 3.0/5 🟢 2.0/5 → 2.0/5 ✅ mtp-hot-reload; tools: skill, glob, edit, create / ✅ mtp-hot-reload; tools: skill, glob, edit, create ✅ 0.11
mtp-hot-reload Run specific failing test with hot reload filter 1.0/5 → 5.0/5 🟢 1.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: report_intent, skill, view / ✅ mtp-hot-reload; tools: report_intent, skill, view ✅ 0.11
migrate-mstest-v3-to-v4 Migrate custom TestMethodAttribute from Execute to ExecuteAsync 2.0/5 → 5.0/5 🟢 2.0/5 → 3.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill / ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.07
migrate-mstest-v3-to-v4 Replace ExpectedExceptionAttribute with Assert.ThrowsExactly 3.0/5 → 3.0/5 3.0/5 → 4.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill / ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.07
migrate-mstest-v3-to-v4 Fix multiple v4 breaking changes: Assert, ClassCleanup, TestContext, Timeout 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill / ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.07
migrate-mstest-v3-to-v4 Handle net6.0 target framework dropped in MSTest v4 5.0/5 → 5.0/5 5.0/5 → 4.0/5 🔴 ⚠️ NOT ACTIVATED / ⚠️ NOT ACTIVATED ✅ 0.07 [50]
migrate-mstest-v3-to-v4 Fix TestMethodAttribute CallerInfo constructor breaking change 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ migrate-mstest-v3-to-v4; tools: skill / ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.07
migrate-mstest-v3-to-v4 Understand behavioral changes after MSTest v4 upgrade 1.0/5 ⏰ → 5.0/5 🟢 1.0/5 ⏰ → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill / ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.07
migrate-mstest-v3-to-v4 Handle MSTest.Sdk and MTP changes in v4 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill / ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.07
migrate-mstest-v3-to-v4 Full MSTest v3 to v4 migration with multiple breaking changes 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill / ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.07
migrate-mstest-v3-to-v4 Migrate MSTest.Sdk v3 project using ManagedType and TestTimeout 1.0/5 ⏰ → 4.0/5 🟢 1.0/5 ⏰ → 3.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill / ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.07
migrate-mstest-v3-to-v4 Correctly identify MSTest v3 project and recommend v4 migration 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill / ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.07
template-authoring Validate a template.json file 3.0/5 → 5.0/5 🟢 3.0/5 → 5.0/5 🟢 ✅ template-authoring; tools: skill / ✅ template-authoring; tools: skill ✅ 0.06
template-discovery Find template for web API project 2.0/5 → 5.0/5 🟢 2.0/5 → 5.0/5 🟢 ✅ template-discovery; tools: report_intent, skill, bash / ✅ template-discovery; tools: report_intent, skill, bash 🟡 0.32
template-discovery Inspect template parameters 5.0/5 → 4.0/5 🔴 5.0/5 → 4.0/5 🔴 ✅ template-discovery; tools: skill / ✅ template-discovery; tools: skill 🟡 0.32
template-instantiation Create a console application 4.0/5 → 5.0/5 🟢 4.0/5 → 5.0/5 🟢 ✅ template-instantiation; tools: skill / ✅ template-instantiation; tools: skill 🟡 0.34
template-instantiation Create project with specific framework 5.0/5 → 5.0/5 5.0/5 → 5.0/5 ✅ template-instantiation; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.34 [51]

[1] (Plugin) Quality unchanged but weighted score is -5.9% due to: tokens (11894 → 32939), tool calls (0 → 2), time (14.2s → 23.4s)
[2] (Plugin) Quality unchanged but weighted score is -5.3% due to: tokens (40909 → 95683), tool calls (5 → 9), time (41.1s → 56.8s)
[3] (Plugin) Quality unchanged but weighted score is -5.8% due to: tokens (36111 → 94037), tool calls (3 → 8), time (20.5s → 39.6s)
[4] (Plugin) Quality unchanged but weighted score is -5.5% due to: tokens (38545 → 67325), tool calls (3 → 6), time (31.6s → 100.6s)
[5] (Plugin) Quality unchanged but weighted score is -15.0% due to: tokens (28859 → 82020), errors (0 → 1), tool calls (2 → 16), time (53.1s → 120.0s)
[6] (Isolated) Quality unchanged but weighted score is -3.8% due to: tokens (28471 → 110098), errors (0 → 1), tool calls (2 → 9), time (46.1s → 120.0s)
[7] (Isolated) Quality unchanged but weighted score is -10.0% due to: tokens (42315 → 245279), tool calls (3 → 13), time (33.0s → 165.5s)
[8] (Isolated) Quality unchanged but weighted score is -7.5% due to: tokens (24482 → 43728), tool calls (2 → 5), time (14.1s → 20.2s)
[9] (Plugin) Quality unchanged but weighted score is -0.5% due to: tokens (24977 → 27646)
[10] (Plugin) Quality unchanged but weighted score is -8.4% due to: tokens (11804 → 43172), tool calls (0 → 3), time (10.8s → 14.4s)
[11] (Plugin) Quality unchanged but weighted score is -8.1% due to: tokens (12127 → 48441), tool calls (0 → 4), time (16.3s → 20.2s)
[12] (Isolated) Quality unchanged but weighted score is -22.9% due to: judgment, tokens (11938 → 26428), quality, tool calls (0 → 1), time (11.1s → 14.3s)
[13] (Isolated) Quality unchanged but weighted score is -2.0% due to: tool calls (23 → 34), tokens (396505 → 464325)
[14] (Plugin) Quality unchanged but weighted score is -7.6% due to: tokens (40792 → 108496), tool calls (11 → 17), time (45.9s → 67.8s)
[15] (Plugin) Quality unchanged but weighted score is -6.6% due to: tokens (70445 → 162833), time (41.4s → 60.6s)
[16] (Isolated) Quality improved but weighted score is -15.0% due to: quality, tokens (103171 → 302006), tool calls (11 → 23), time (90.8s → 129.8s)
[17] (Isolated) Quality unchanged but weighted score is -10.7% due to: tokens (111703 → 267285), quality, tool calls (12 → 21), time (79.5s → 100.5s)
[18] (Plugin) Quality unchanged but weighted score is -5.4% due to: tokens (35417 → 64587), tool calls (3 → 4)
[19] (Plugin) Quality unchanged but weighted score is -10.0% due to: tokens (192021 → 1040850), tool calls (12 → 34), time (89.5s → 182.9s)
[20] (Isolated) Quality unchanged but weighted score is -26.7% due to: completion (✓ → ✗), judgment, quality
[21] (Plugin) Quality improved but weighted score is -0.7% due to: completion (✓ → ✗), tool calls (3 → 8), tokens (36678 → 54541), time (41.3s → 54.2s)
[22] (Plugin) Quality unchanged but weighted score is -3.0% due to: tokens (143424 → 186530), time (80.9s → 115.0s)
[23] (Isolated) Quality unchanged but weighted score is -0.6% due to: tokens (140818 → 377538), time (102.2s → 220.7s), tool calls (14 → 20)
[24] (Isolated) Quality unchanged but weighted score is -3.3% due to: quality
[25] (Plugin) Quality unchanged but weighted score is -5.6% due to: tokens (17510 → 55657), tool calls (0 → 4)
[26] (Isolated) Quality improved but weighted score is -1.2% due to: tokens (14724 → 53603), tool calls (0 → 4)
[27] (Isolated) Quality unchanged but weighted score is -12.5% due to: quality, tokens (29037 → 52817), tool calls (2 → 4), time (19.7s → 24.2s)
[28] (Plugin) Quality unchanged but weighted score is -9.7% due to: tokens (30133 → 56668), quality, tool calls (2 → 3)
[29] (Isolated) Quality unchanged but weighted score is -5.4% due to: quality
[30] (Isolated) Quality unchanged but weighted score is -24.2% due to: quality, judgment, tokens (46701 → 51831)
[31] (Isolated) Quality unchanged but weighted score is -5.9% due to: tokens (14181 → 49607), tool calls (0 → 4)
[32] (Isolated) Quality unchanged but weighted score is -7.6% due to: tokens (123325 → 265020), time (98.8s → 173.3s), tool calls (18 → 23)
[33] (Isolated) Quality unchanged but weighted score is -5.1% due to: tokens (62872 → 186219), tool calls (16 → 21)
[34] (Plugin) Quality unchanged but weighted score is -10.0% due to: tokens (40978 → 508527), tool calls (11 → 33), time (42.9s → 163.9s)
[35] (Plugin) Quality unchanged but weighted score is -8.5% due to: tokens (12696 → 31888), tool calls (0 → 1), time (20.2s → 28.1s)
[36] (Plugin) Quality unchanged but weighted score is -8.0% due to: tokens (13040 → 32056), tool calls (0 → 1), time (27.0s → 32.7s)
[37] (Isolated) Quality unchanged but weighted score is -7.9% due to: tokens (88338 → 256104), time (63.9s → 110.9s), tool calls (22 → 31)
[38] (Isolated) Quality improved but weighted score is -7.5% due to: tokens (12506 → 46035), tool calls (0 → 4)
[39] (Isolated) Quality improved but weighted score is -0.6% due to: tokens (13613 → 45343), tool calls (0 → 4)
[40] (Isolated) Quality unchanged but weighted score is -4.1% due to: tokens (16735 → 65021), tool calls (0 → 17)
[41] (Isolated) Quality unchanged but weighted score is -6.0% due to: completion (✓ → ✗)
[42] (Isolated) Quality unchanged but weighted score is -21.2% due to: judgment, quality, tokens (36702 → 61139), tool calls (5 → 8)
[43] (Plugin) Quality unchanged but weighted score is -1.4% due to: tokens (23459 → 30016)
[44] (Plugin) Quality unchanged but weighted score is -5.9% due to: tool calls (16 → 32), tokens (164205 → 244288), time (77.4s → 107.5s)
[45] (Plugin) Quality unchanged but weighted score is -6.7% due to: tokens (12653 → 32209), tool calls (0 → 1)
[46] (Isolated) Quality unchanged but weighted score is -7.0% due to: tokens (12580 → 30092), tool calls (0 → 2)
[47] (Isolated) Quality unchanged but weighted score is -15.0% due to: tokens (24171 → 221916), errors (0 → 1), tool calls (4 → 15), time (21.1s → 120.2s)
[48] (Isolated) Quality unchanged but weighted score is -3.6% due to: tokens (23910 → 37237), tool calls (3 → 4)
[49] (Plugin) Quality unchanged but weighted score is -24.5% due to: judgment, quality, time (9.5s → 18.3s), tool calls (2 → 3), tokens (23405 → 27964)
[50] (Isolated) Quality unchanged but weighted score is -0.4% due to: efficiency metrics
[51] (Plugin) Quality unchanged but weighted score is -0.6% due to: efficiency metrics

timeout — run hit the scenario timeout limit; scoring may be impacted by aborting model execution before it could produce its full output

Model: claude-opus-4.6 | Judge: claude-opus-4.6

Full results

@ViktorHofer
ViktorHofer merged commit 6face98 into main Mar 20, 2026
27 checks passed
@ViktorHofer
ViktorHofer deleted the copilot/fix-manifest-issues-claude-cli branch March 20, 2026 09:27
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Manifest issues with Claude Code CLI

6 participants