Skip to content

feat: restructure Karma agent skills#27

Open
maheshmurthy wants to merge 8 commits into
mainfrom
feat/unified-karma-agent-skills
Open

feat: restructure Karma agent skills#27
maheshmurthy wants to merge 8 commits into
mainfrom
feat/unified-karma-agent-skills

Conversation

@maheshmurthy

@maheshmurthy maheshmurthy commented May 31, 2026

Copy link
Copy Markdown
Member

Summary

  • Replace legacy Karma skills with the unified in-product/external-agent skill set
  • Add anonymous and authenticated plugin profiles
  • Add generated tools manifest for backend integration checks

Testing

  • Not run; content-only skills repo change

Dependency

  • gap-indexer PR pins this commit: 7b11d49

Summary by CodeRabbit

  • New Features

    • v3.0.0 release: consolidated shared Karma agent skills package with authenticated and anonymous profiles
    • Added skills for knowledge‑base answering, application review, milestone review, philanthropy research, and workspace/admin views
  • Removals

    • Deprecated legacy funding-discovery, project-manager, setup-agent, and related skill docs
  • Chores

    • Plugin metadata and package version updated to 3.0.0

@coderabbitai

coderabbitai Bot commented May 31, 2026

Copy link
Copy Markdown

Review Change Stack

Warning

Review limit reached

@maheshmurthy, we couldn't start this review because you've reached your PR review rate limit.

More reviews will be available in 16 minutes and 18 seconds. Learn how PR review limits work.

Your organization has run out of usage credits. Purchase more in the billing tab.

⌛ How to resolve this issue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available.

Please see our Fair Usage Limits Policy for further information.

ℹ️ Review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 00f5aaf1-4377-4c9b-a312-ea8c65a301eb

📥 Commits

Reviewing files that changed from the base of the PR and between 6dc5bdb and d6b8da9.

📒 Files selected for processing (5)
  • skill-profiles/anonymous/skills/knowledge-base-answering/SKILL.md
  • skill-profiles/authenticated/skills/knowledge-base-answering/SKILL.md
  • skill-profiles/authenticated/skills/milestone-review/SKILL.md
  • skills/knowledge-base-answering/SKILL.md
  • skills/milestone-review/SKILL.md
📝 Walkthrough

Walkthrough

Restructure skills into a shared Karma agent skills package (v3.0.0): consolidate plugin/manifests, remove legacy skill docs and hooks, add shared SKILL.md specifications, and add anonymous and authenticated profile manifests for transport-neutral skill access.

Changes

Shared Karma Agent Skills Restructuring

Layer / File(s) Summary
Plugin manifest and marketplace configuration
.claude-plugin/plugin.json, .claude-plugin/marketplace.json
Version bumped to 3.0.0, description updated to "Shared Karma agent skills," keywords and tags revised, and hooks configuration removed. Marketplace consolidates to a single Karma Agent Skills plugin entry with updated skill paths pointing to the new shared model.
Documentation and skill operations specification
README.md
Main content reworded to describe "Shared agent skills for the Karma ecosystem"; "Quick Start," "What Are Skills?," "Available Skills," and "How It Works" sections updated to reflect the new shared skills model (transport-neutral, runtime enforcement, MCP-capable). Note added that SKILL.md frontmatter can include an operations list.
Shared skills definitions
skills/README.md, skills/*/SKILL.md
New shared skills layer introduced with documentation of knowledge-base-answering, application-review, karma-product-concepts, milestone-review, philanthropy-research, program-admin-workspace, and project-owner-workspace skills. Each skill defines usage semantics and supported operations independent of transport mechanism.
Anonymous skill profile
skill-profiles/anonymous/.claude-plugin/plugin.json, skill-profiles/anonymous/skills/knowledge-base-answering/SKILL.md
New unauthenticated in-product chat profile added with plugin metadata and knowledge-base-answering skill definition for public access.
Authenticated skill profile
skill-profiles/authenticated/.claude-plugin/plugin.json, skill-profiles/authenticated/skills/*/SKILL.md
New authenticated user profile added with plugin metadata and skill definitions for application-review, karma-product-concepts, knowledge-base-answering, milestone-review, philanthropy-research, program-admin-workspace, and project-owner-workspace for authorized access.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Possibly related PRs

  • show-karma/skills#16: Affects skills/project-manager/SKILL.md which is removed in this PR as part of the restructuring.
  • show-karma/skills#20: Updates README and references funding-program-manager skill that is being removed and consolidated here.
  • show-karma/skills#9: Updates .claude-plugin/marketplace.json and plugin structure that this PR directly supersedes.

Suggested reviewers

  • brunodmsi

Poem

🐰 I hopped through manifests, tidy and spry,
Shared skills gathered under v3.0’s sky,
Anonymous whispers, authenticated nods,
Old docs tucked in burrows, new specs applaud,
A rabbit applauds the tidy supply.

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title 'feat: restructure Karma agent skills' accurately describes the main change: a comprehensive restructuring of the Karma agent skills package, replacing legacy skills with a unified in-product/external-agent skill set and adding new plugin profiles.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch feat/unified-karma-agent-skills

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Actionable comments posted: 7

🧹 Nitpick comments (1)
skill-profiles/authenticated/skills/program-admin-workspace/SKILL.md (1)

3-9: ⚡ Quick win

Clarify delegated reviewer/milestone/payout tooling (no missing operations gap).

program-admin-workspace’s operations list is intentionally a narrow “broad workspace” set; reviewer and milestone review/queue operations live in other skills—e.g., skill-profiles/authenticated/skills/application-review/SKILL.md (list_assigned_applications, etc.) and skill-profiles/authenticated/skills/milestone-review/SKILL.md (list_pending_milestones, get_milestone_completion, etc.)—while payouts can be obtained via get_program_financials and the portfolio report tools already listed.

Consider explicitly pointing to those narrower skills in the “call narrower tools… for reviewers/milestones/payouts” guidance.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@skill-profiles/authenticated/skills/program-admin-workspace/SKILL.md` around
lines 3 - 9, Update the SKILL.md for program-admin-workspace to explicitly note
that reviewer, milestone and payout actions are handled by narrower skills
rather than this workspace; add a short guidance line after the operations list
saying to call the application-review skill (e.g., list_assigned_applications
and other reviewer ops) for reviewer queues, the milestone-review skill (e.g.,
list_pending_milestones, get_milestone_completion) for milestone inspections,
and to use get_program_financials and the portfolio report operations already
listed for payouts/financials so there’s no ambiguity about missing operations.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@README.md`:
- Around line 47-57: The fenced diagram block containing the lines "User
request", "AI agent selects a Karma skill", "Skill names the workflow and
expected operations", "Runtime adapter exposes operations through MCP or another
interface", and "Karma services enforce auth, RBAC, budgets, and tool policy"
needs a language tag to satisfy markdownlint MD040; update that triple-backtick
fence to include a neutral tag such as ```text so the diagram remains readable
and linter-compliant.
- Around line 35-36: Remove the duplicated table header row by deleting the
second occurrence of the header lines (the repeated "| Skill | Description |"
and its separator "|-------|-------------|") so only the single header remains
before the table data; ensure the remaining header and separator are the first
two table lines to avoid the extra empty data row.
- Around line 13-23: The example quoted lines are separated by blank lines,
which creates multiple blockquotes and triggers markdownlint MD028; fix by
making those lines a single continuous blockquote (remove the blank lines
between the lines starting with ">" so all of: "How do I submit a milestone
update for this program?", "What applications do I need to review?", "Which
projects have milestones ready for my review?", "What is happening across the
programs I manage?", and "What is the status of my project milestones?" appear
as one >-prefixed block) or convert them into a normal bullet list so the
examples are a single block and the lint rule is satisfied.

In `@skill-profiles/authenticated/skills/project-owner-workspace/SKILL.md`:
- Around line 3-9: The frontmatter operations list in SKILL.md is missing the
completion/payout/invoice/update/indicator operations referenced in the
description; either add concrete operation identifiers (e.g., add
list_project_completions, list_project_payouts, list_project_invoices,
list_project_updates, list_project_indicators) to the operations: array or
change the description/body to explicitly state that get_project_details and
get_project_status cover those items; update the operations: section so it
matches the narrative (modify or append operation names like
get_project_details, get_project_status, list_project_milestones,
list_my_grants, list_project_completions, list_project_payouts,
list_project_invoices, list_project_updates, list_project_indicators) and ensure
any references in the body mention which operation to call for each resource
type.

In `@skills/application-review/SKILL.md`:
- Line 15: The frontmatter operations list for this skill doesn't include a
workspace operation but the text references "the available workspace tool";
either add the workspace operation (e.g., get_my_workspace) to the operations
frontmatter so the skill can call it alongside list_assigned_applications, or
change the wording on line 15 to remove/replace "the available workspace tool"
to avoid implying an unlisted operation; update references to
list_assigned_applications and any examples to reflect the chosen approach
(adding get_my_workspace or rephrasing).

In `@skills/program-admin-workspace/SKILL.md`:
- Line 16: The description on line 16 references tools for "applications,
reviewers, financials, payouts, milestones, or reports" but the SKILL
frontmatter operations only declare workspace, program applications, financials,
and portfolio report generation; either add explicit operations for reviewers,
payouts, and milestones to the frontmatter (so symbols like operations:
reviewers, operations: payouts, operations: milestones exist) or change the
sentence on line 16 to only mention the existing operations (workspace, program
applications, financials, portfolio report generation); update whichever symbols
you choose (frontmatter operations or the sentence) so the listed operations and
the prose stay consistent.

In `@skills/project-owner-workspace/SKILL.md`:
- Line 14: The frontmatter "operations" list currently (operations) does not
include entities referenced in the prose (milestone completions, updates,
indicators, invoices, payouts, completion tools, payout tools, invoice tools)
mentioned in the description lines (line 14 and 18); either add corresponding
operation names to the frontmatter so the skill can directly handle those
entities (e.g., add operations for "milestoneCompletions", "updates",
"indicators", "invoices", "payouts", "completionTools", "payoutTools",
"invoiceTools") or edit the description text in SKILL.md to only mention the
entities that are actually implemented (workspace, projectDetails, milestones,
status, grants) so the documentation matches the operations list — update the
"operations" frontmatter or the prose accordingly to keep them consistent.

---

Nitpick comments:
In `@skill-profiles/authenticated/skills/program-admin-workspace/SKILL.md`:
- Around line 3-9: Update the SKILL.md for program-admin-workspace to explicitly
note that reviewer, milestone and payout actions are handled by narrower skills
rather than this workspace; add a short guidance line after the operations list
saying to call the application-review skill (e.g., list_assigned_applications
and other reviewer ops) for reviewer queues, the milestone-review skill (e.g.,
list_pending_milestones, get_milestone_completion) for milestone inspections,
and to use get_program_financials and the portfolio report operations already
listed for payouts/financials so there’s no ambiguity about missing operations.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: ad9bf823-7821-4af1-89f4-0751cf871ea6

📥 Commits

Reviewing files that changed from the base of the PR and between ad291ad and 7b11d49.

⛔ Files ignored due to path filters (1)
  • generated/tools-manifest.json is excluded by !**/generated/**
📒 Files selected for processing (32)
  • .claude-plugin/marketplace.json
  • .claude-plugin/plugin.json
  • README.md
  • hooks/hooks.json
  • hooks/load-credentials.sh
  • skill-profiles/anonymous/.claude-plugin/plugin.json
  • skill-profiles/anonymous/skills/knowledge-base-answering/SKILL.md
  • skill-profiles/authenticated/.claude-plugin/plugin.json
  • skill-profiles/authenticated/skills/application-review/SKILL.md
  • skill-profiles/authenticated/skills/karma-product-concepts/SKILL.md
  • skill-profiles/authenticated/skills/knowledge-base-answering/SKILL.md
  • skill-profiles/authenticated/skills/milestone-review/SKILL.md
  • skill-profiles/authenticated/skills/philanthropy-research/SKILL.md
  • skill-profiles/authenticated/skills/program-admin-workspace/SKILL.md
  • skill-profiles/authenticated/skills/project-owner-workspace/SKILL.md
  • skills/README.md
  • skills/application-review/SKILL.md
  • skills/find-funding-opportunities/SKILL.md
  • skills/find-funding-opportunities/references/api-reference.md
  • skills/funding-program-manager/SKILL.md
  • skills/karma-product-concepts/SKILL.md
  • skills/knowledge-base-answering/SKILL.md
  • skills/milestone-review/SKILL.md
  • skills/philanthropy-research/SKILL.md
  • skills/program-admin-workspace/SKILL.md
  • skills/project-manager/SKILL.md
  • skills/project-owner-workspace/SKILL.md
  • skills/references/agent-api.md
  • skills/setup-agent/SKILL.md
  • skills/skill-creator/SKILL.md
  • skills/skill-creator/references/output-patterns.md
  • skills/skill-creator/references/workflows.md
💤 Files with no reviewable changes (11)
  • skills/references/agent-api.md
  • hooks/hooks.json
  • hooks/load-credentials.sh
  • skills/find-funding-opportunities/references/api-reference.md
  • skills/skill-creator/references/workflows.md
  • skills/skill-creator/SKILL.md
  • skills/setup-agent/SKILL.md
  • skills/skill-creator/references/output-patterns.md
  • skills/funding-program-manager/SKILL.md
  • skills/project-manager/SKILL.md
  • skills/find-funding-opportunities/SKILL.md

Comment thread README.md
Comment on lines +13 to +23
Then ask your agent questions such as:

> Find active grant programs on Ethereum
> How do I submit a milestone update for this program?

> Post an update on my project — we shipped the MVP
> What applications do I need to review?

> List reviewers for Optimism Audit Grants Season 8
> Which projects have milestones ready for my review?

> Show pending applications for my grant program
> What is happening across the programs I manage?

> Add a reviewer to my program
> What is the status of my project milestones?

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Make the quoted examples a single block.

The blank lines between these > lines split the examples into separate blockquotes and trip markdownlint (MD028). Converting this to one continuous blockquote or a normal bullet list will keep the docs lint-clean.

🧰 Tools
🪛 markdownlint-cli2 (0.22.1)

[warning] 16-16: Blank line inside blockquote

(MD028, no-blanks-blockquote)


[warning] 18-18: Blank line inside blockquote

(MD028, no-blanks-blockquote)


[warning] 20-20: Blank line inside blockquote

(MD028, no-blanks-blockquote)


[warning] 22-22: Blank line inside blockquote

(MD028, no-blanks-blockquote)

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@README.md` around lines 13 - 23, The example quoted lines are separated by
blank lines, which creates multiple blockquotes and triggers markdownlint MD028;
fix by making those lines a single continuous blockquote (remove the blank lines
between the lines starting with ">" so all of: "How do I submit a milestone
update for this program?", "What applications do I need to review?", "Which
projects have milestones ready for my review?", "What is happening across the
programs I manage?", and "What is the status of my project milestones?" appear
as one >-prefixed block) or convert them into a normal bullet list so the
examples are a single block and the lint rule is satisfied.

Comment thread README.md
Comment on lines +35 to +36
| Skill | Description |
|-------|-------------|

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Remove the duplicated table header.

Lines 35-36 repeat the table header that already exists at Lines 33-34, so the rendered table gets an extra first data row.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@README.md` around lines 35 - 36, Remove the duplicated table header row by
deleting the second occurrence of the header lines (the repeated "| Skill |
Description |" and its separator "|-------|-------------|") so only the single
header remains before the table data; ensure the remaining header and separator
are the first two table lines to avoid the extra empty data row.

Comment thread README.md
Comment on lines 47 to 57
```
You
AI Agent (picks the right skill)
User request
Karma API (encodes attestation)
AI agent selects a Karma skill
Server Wallet (signs + submits tx, gasless)
Skill names the workflow and expected operations
Blockchain (EAS attestation created)
Runtime adapter exposes operations through MCP or another interface
karmahq.xyz (visible on the web)
Karma services enforce auth, RBAC, budgets, and tool policy
```

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Add a language tag to the fenced diagram block.

This block currently violates markdownlint MD040. Using something like text keeps the diagram readable without introducing renderer-specific syntax.

🧰 Tools
🪛 markdownlint-cli2 (0.22.1)

[warning] 47-47: Fenced code blocks should have a language specified

(MD040, fenced-code-language)

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@README.md` around lines 47 - 57, The fenced diagram block containing the
lines "User request", "AI agent selects a Karma skill", "Skill names the
workflow and expected operations", "Runtime adapter exposes operations through
MCP or another interface", and "Karma services enforce auth, RBAC, budgets, and
tool policy" needs a language tag to satisfy markdownlint MD040; update that
triple-backtick fence to include a neutral tag such as ```text so the diagram
remains readable and linter-compliant.

Comment on lines +3 to +9
description: Help project owners inspect their projects, grants, milestones, completions, updates, indicators, invoices, and payouts.
operations:
- get_my_workspace
- get_project_details
- list_project_milestones
- get_project_status
- list_my_grants

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🔴 Critical | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Description: Check if shared skills or backend define operations for completions, updates, indicators, invoices, payouts

# Search shared skills definition for project-owner-workspace
fd -t f 'SKILL.md' skills/project-owner-workspace -x cat

# Search for these operation patterns across the repository
rg -n --type=md -C2 'list_project_(completions|updates|indicators|invoices|payouts)'

Repository: show-karma/skills

Length of output: 1189


Fix operations list/documentation mismatch in project-owner-workspace

The skill frontmatter promises “completions, updates, indicators, invoices, and payouts”, and the body instructs to “call the relevant project, grant, milestone, completion, payout, or invoice tool”. But the operations: list only includes get_my_workspace, get_project_details, list_project_milestones, get_project_status, and list_my_grants—there are no completion/payout/invoice (or updates/indicators/invoices/payouts) operations declared. Either document that these are covered by one of the existing operations (e.g., get_project_status / get_project_details) or add the missing operations.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@skill-profiles/authenticated/skills/project-owner-workspace/SKILL.md` around
lines 3 - 9, The frontmatter operations list in SKILL.md is missing the
completion/payout/invoice/update/indicator operations referenced in the
description; either add concrete operation identifiers (e.g., add
list_project_completions, list_project_payouts, list_project_invoices,
list_project_updates, list_project_indicators) to the operations: array or
change the description/body to explicitly state that get_project_details and
get_project_status cover those items; update the operations: section so it
matches the narrative (modify or append operation names like
get_project_details, get_project_status, list_project_milestones,
list_my_grants, list_project_completions, list_project_payouts,
list_project_invoices, list_project_updates, list_project_indicators) and ensure
any references in the body mention which operation to call for each resource
type.


Use this skill when a reviewer asks about applications assigned to them, pending review work, review comments, application status, applicants, or links to applications.

For "what applications do I need to review" or similar queue questions, call `list_assigned_applications` or the available workspace tool before answering. Return application identifiers, project or applicant names, statuses, and links when the tool provides them.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Verify workspace tool availability.

Line 15 mentions "the available workspace tool" as an alternative to list_assigned_applications, but the operations frontmatter (lines 4-8) does not include a workspace operation like get_my_workspace. If workspace access is expected for this skill, consider adding it to the operations list; otherwise, clarify the phrasing to avoid implying a tool that isn't listed.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@skills/application-review/SKILL.md` at line 15, The frontmatter operations
list for this skill doesn't include a workspace operation but the text
references "the available workspace tool"; either add the workspace operation
(e.g., get_my_workspace) to the operations frontmatter so the skill can call it
alongside list_assigned_applications, or change the wording on line 15 to
remove/replace "the available workspace tool" to avoid implying an unlisted
operation; update references to list_assigned_applications and any examples to
reflect the chosen approach (adding get_my_workspace or rephrasing).


Use this skill when a program or community admin asks about the programs they manage, application volume, reviewers, milestones, payouts, financials, reports, or overall program state.

Start with the broadest available workspace, program overview, or program list tool to identify the relevant managed programs. Then call narrower tools for applications, reviewers, financials, payouts, milestones, or reports as needed.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Verify operations coverage for mentioned entities.

Line 16 mentions calling "narrower tools for applications, reviewers, financials, payouts, milestones, or reports," but the operations frontmatter (lines 4-9) only lists workspace, program applications, financials, and portfolio report generation. If this skill is expected to handle reviewers, payouts, and milestones directly, consider adding corresponding operations; otherwise, clarify the instruction to reference only the tools actually available.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@skills/program-admin-workspace/SKILL.md` at line 16, The description on line
16 references tools for "applications, reviewers, financials, payouts,
milestones, or reports" but the SKILL frontmatter operations only declare
workspace, program applications, financials, and portfolio report generation;
either add explicit operations for reviewers, payouts, and milestones to the
frontmatter (so symbols like operations: reviewers, operations: payouts,
operations: milestones exist) or change the sentence on line 16 to only mention
the existing operations (workspace, program applications, financials, portfolio
report generation); update whichever symbols you choose (frontmatter operations
or the sentence) so the listed operations and the prose stay consistent.


# Project Owner Workspace

Use this skill when a project owner asks about their projects, grants, milestones, milestone completions, project status, updates, indicators, invoices, or payouts.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Verify operations coverage for mentioned entities.

Lines 14 and 18 reference multiple entity types (milestone completions, updates, indicators, invoices, payouts, completion tools, payout tools, invoice tools), but the operations frontmatter (lines 4-10) only lists workspace, project details, milestones, status, and grants. If this skill is expected to handle these additional entities directly, consider adding corresponding operations; otherwise, adjust the description and instructions to reference only the available tools.

Also applies to: 18-18

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@skills/project-owner-workspace/SKILL.md` at line 14, The frontmatter
"operations" list currently (operations) does not include entities referenced in
the prose (milestone completions, updates, indicators, invoices, payouts,
completion tools, payout tools, invoice tools) mentioned in the description
lines (line 14 and 18); either add corresponding operation names to the
frontmatter so the skill can directly handle those entities (e.g., add
operations for "milestoneCompletions", "updates", "indicators", "invoices",
"payouts", "completionTools", "payoutTools", "invoiceTools") or edit the
description text in SKILL.md to only mention the entities that are actually
implemented (workspace, projectDetails, milestones, status, grants) so the
documentation matches the operations list — update the "operations" frontmatter
or the prose accordingly to keep them consistent.

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (2)
skill-profiles/authenticated/skills/milestone-review/SKILL.md (1)

1-14: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

Frontmatter schema is incomplete for authenticated profile skill.

version and tags are required SKILL frontmatter fields but are missing here, so this profile artifact may fail shared validation expectations.

Suggested fix
 ---
 name: milestone-review
 description: Help milestone reviewers find projects and milestones ready for review.
+version: 0.1.0
+tags: [milestones, review, grants]
 operations:
   - get_my_workspace
   - resolveReviewer
   - getMilestoneReport
   - getProgramMilestoneSummary
   - getPendingVerificationMilestones
   - list_milestone_completions
   - get_milestone_completion
   - get_project_details
   - list_project_milestones
 ---
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@skill-profiles/authenticated/skills/milestone-review/SKILL.md` around lines 1
- 14, The SKILL frontmatter for the milestone-review skill is missing required
fields; update the top YAML block in SKILL.md for the "milestone-review" skill
to include a version field (e.g., version: "1.0.0") and a tags array (e.g.,
tags: ["authenticated","milestone","review"]) while keeping the existing name,
description, and operations entries (get_my_workspace, resolveReviewer,
getMilestoneReport, etc.) intact so the artifact meets the authenticated profile
frontmatter schema.
skills/milestone-review/SKILL.md (1)

1-14: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

Add required version and tags fields to SKILL frontmatter.

This SKILL frontmatter omits required metadata fields (version, tags) defined by the repository contract, which can break skill validation/ingestion workflows.

Suggested fix
 ---
 name: milestone-review
 description: Help milestone reviewers find projects and milestones ready for review.
+version: 0.1.0
+tags: [milestones, review, grants]
 operations:
   - get_my_workspace
   - resolveReviewer
   - getMilestoneReport
   - getProgramMilestoneSummary
   - getPendingVerificationMilestones
   - list_milestone_completions
   - get_milestone_completion
   - get_project_details
   - list_project_milestones
 ---
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@skills/milestone-review/SKILL.md` around lines 1 - 14, The SKILL frontmatter
is missing required metadata fields "version" and "tags"; update the frontmatter
at the top of the SKILL (the YAML block containing name/description/operations)
to include a "version" (use a semantic version string like "0.1.0") and a "tags"
array (e.g., ["milestone", "review"] or other relevant tag keywords) so
validation/ingestion will succeed; keep the existing name, description and
operations entries (no code changes beyond adding these two fields).
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Outside diff comments:
In `@skill-profiles/authenticated/skills/milestone-review/SKILL.md`:
- Around line 1-14: The SKILL frontmatter for the milestone-review skill is
missing required fields; update the top YAML block in SKILL.md for the
"milestone-review" skill to include a version field (e.g., version: "1.0.0") and
a tags array (e.g., tags: ["authenticated","milestone","review"]) while keeping
the existing name, description, and operations entries (get_my_workspace,
resolveReviewer, getMilestoneReport, etc.) intact so the artifact meets the
authenticated profile frontmatter schema.

In `@skills/milestone-review/SKILL.md`:
- Around line 1-14: The SKILL frontmatter is missing required metadata fields
"version" and "tags"; update the frontmatter at the top of the SKILL (the YAML
block containing name/description/operations) to include a "version" (use a
semantic version string like "0.1.0") and a "tags" array (e.g., ["milestone",
"review"] or other relevant tag keywords) so validation/ingestion will succeed;
keep the existing name, description and operations entries (no code changes
beyond adding these two fields).

ℹ️ Review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 79e82de1-4925-43f2-becc-8b3d7fa3c9a1

📥 Commits

Reviewing files that changed from the base of the PR and between 4d060f4 and 6dc5bdb.

📒 Files selected for processing (5)
  • skill-profiles/anonymous/skills/knowledge-base-answering/SKILL.md
  • skill-profiles/authenticated/skills/knowledge-base-answering/SKILL.md
  • skill-profiles/authenticated/skills/milestone-review/SKILL.md
  • skills/knowledge-base-answering/SKILL.md
  • skills/milestone-review/SKILL.md
🚧 Files skipped from review as they are similar to previous changes (3)
  • skill-profiles/anonymous/skills/knowledge-base-answering/SKILL.md
  • skills/knowledge-base-answering/SKILL.md
  • skill-profiles/authenticated/skills/knowledge-base-answering/SKILL.md

@maheshmurthy
maheshmurthy force-pushed the feat/unified-karma-agent-skills branch from 2f24f7a to b4421b3 Compare June 1, 2026 05:18
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.

1 participant