Skip to content

feat(skills): add gentle-ai-collab-perfect workflow skill for external contributors#1171

Open
ardelperal wants to merge 1 commit into
Gentleman-Programming:mainfrom
ardelperal:skill/gentle-ai-collab-perfect
Open

feat(skills): add gentle-ai-collab-perfect workflow skill for external contributors#1171
ardelperal wants to merge 1 commit into
Gentleman-Programming:mainfrom
ardelperal:skill/gentle-ai-collab-perfect

Conversation

@ardelperal

@ardelperal ardelperal commented Jul 12, 2026

Copy link
Copy Markdown
Contributor

🔗 Linked Issue

Closes #1170

🏷️ PR Type

  • type:feature — New feature (non-breaking change that adds functionality)
  • type:bug — Bug fix
  • type:docs — Documentation only
  • type:refactor — Code refactoring
  • type:chore — Build, CI, or tooling
  • type:breaking-change — Breaking change

📝 Summary

Adds a new AI-collaborator workflow skill at skills/gentle-ai-collab-perfect/SKILL.md. The skill codifies, in one triggerable reference, the rules that CONTRIBUTING.md, .github/PULL_REQUEST_TEMPLATE.md, .github/ISSUE_TEMPLATE/*.yml, and .github/workflows/pr-check.yml imply but do not centralise:

  • Maintainer-vs-contributor scope split (verified empirically against this repo's gate failures).
  • PR body honesty pattern — the ## Pending maintainer actions idiom, pre-existing-failure disclosure, line-count honesty.
  • Chained-PR strategy comparison (Stacked vs Feature Branch Chain) and the cross-fork base-ref limitation that makes Feature Branch Chain require maintainer cooperation.
  • A verification protocol (gh pr view --json ... cross-checks) to run before recommending any action.

Content-only change; no executable code, no API changes, no runtime risk.

📂 Changes

File Change
skills/gentle-ai-collab-perfect/SKILL.md New skill: 301 lines, references gentle-ai-branch-pr, gentle-ai-chained-pr, gentle-ai-issue-creation, gentle-ai-cognitive-doc-design, gentle-ai-comment-writer, gentle-ai-work-unit-commits rather than duplicating them

PR diff totals (per GitHub API): +301 / -0 across 1 new file.

🧪 Test Plan

  • N/A — content-only skill file; no executable code, no API changes
  • SKILL.md frontmatter is valid YAML (verified via local YAML parse)
  • Skill does not duplicate mechanics from existing skills — it cross-references them
  • Skill content reviewed against CONTRIBUTING.md, .github/PULL_REQUEST_TEMPLATE.md, .github/ISSUE_TEMPLATE/*.yml, pr-check.yml
  • N/A — no shell scripts modified
  • N/A — no documentation needed beyond the skill itself

🤖 Automated Checks

Check Status
Check PR Cognitive Load ✅ expected pass — +301 / -0 across 1 file, within 400-line budget
Check Issue Reference ⏳ awaiting Closes #1170 — pattern + repo match accepted
Check Issue Has status:approved ⚠️ depends on maintainer: #1170 currently has no labels (auto-template labels were overwritten by my gh issue create --label enhancement flag, my mistake). When Alan applies status:approved to #1170, this check clears.
Check PR Has type:* Label ⏸ pending Alan
Unit Tests N/A
E2E Tests N/A

✅ Contributor Checklist

Pending maintainer actions (gentle-ai repo convention)

The following are maintainer-applied per pr-check.yml and CONTRIBUTING.md in this repo — not within contributor scope:

💬 Notes for Reviewers

The skill deliberately avoids assuming a fork — it applies whether the contributor pushes to a personal working repo, their fork, or anywhere else with write access. The wording is repo-neutral: "the contributor's working branch", "wherever they push from", not "your fork".

The skill cross-references the existing gentle-ai-branch-pr, gentle-ai-chained-pr, gentle-ai-issue-creation, gentle-ai-cognitive-doc-design, gentle-ai-comment-writer, and gentle-ai-work-unit-commits skills. It is meant to be a higher-level workflow reference, not a duplicate of those mechanics.

Reviewers may also want to skim the linked issue #1170 (which describes the problem this skill solves), since the issue body explains the maintainer-vs-contributor scope split and the PR-body honesty pattern from the angle of "external collaborators ask these questions repeatedly".

I take the blame for one issue on the linked issue: when I created #1170 with gh issue create --label enhancement, this overrode the feature_request.yml template's auto-applied labels (enhancement, status:needs-review). So #1170 currently has no labels. The fix is: Alan adds enhancement and status:approved, and then this PR's gates clear.

This PR completes

Summary by CodeRabbit

  • Documentation
    • Added comprehensive collaboration guidance for AI-assisted contributions.
    • Documented issue and pull request workflows, formatting requirements, labeling rules, review limits, branching practices, and verification steps.
    • Added checklists and examples covering contributor responsibilities, maintainer boundaries, chained pull requests, and accurate testing claims.

Captures the issue-first, contributor-vs-maintainer split, chained-PR
strategy and PR-body honesty rules that the rest of the repo's
documentation implies but does not centralise. Verified empirically
against pr-check.yml gates and the maintainer-applied vs contributor-
applicable permissions list (labels, fork approval, merge, etc.).

Use the skill whenever an external collaborator needs help opening
issues, drafting PR bodies, splitting chained/stacked PRs, or
auditing a PR before requesting review. The skill deliberately avoids
assuming a fork — contributors may push to a personal working repo,
their fork, or anywhere else with write access. References the
existing branch-pr, chained-pr, issue-creation, cognitive-doc-design,
comment-writer and work-unit-commits skills rather than duplicating
their mechanics.
@coderabbitai

coderabbitai Bot commented Jul 12, 2026

Copy link
Copy Markdown

Review Change Stack

📝 Walkthrough

Walkthrough

Changes

Adds the gentle-ai-collab-perfect skill documentation for external contributor workflows, covering repository authorities, issue and PR rules, maintainer permissions, chained PRs, verification procedures, honesty requirements, audits, and references.

External contributor workflow

Layer / File(s) Summary
Skill scope and source authority
skills/gentle-ai-collab-perfect/SKILL.md
Defines when the skill applies, distinguishes contributor and maintainer actions, and identifies repository files as authoritative workflow sources.
Issue and PR workflow rules
skills/gentle-ai-collab-perfect/SKILL.md
Documents issue approval gates, PR formatting and labeling rules, review budgets, branch and commit constraints, honest status claims, and chained PR strategies.
Verification protocol and self-audits
skills/gentle-ai-collab-perfect/SKILL.md
Adds GitHub API cross-checks, pre-PR validation checklists, anti-pattern corrections, assistant usage guidance, and supporting references.

Estimated code review effort: 2 (Simple) | ~10 minutes

Suggested labels: type:feature, size:exception

🚥 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 clearly matches the change: a new workflow skill for external contributors under skills/.
Linked Issues check ✅ Passed The skill content aligns with #1170 by documenting scope split, honest PR bodies, chained PR strategy, and verification steps.
Out of Scope Changes check ✅ Passed The change is content-only in a single SKILL.md file and stays within the contributor workflow guidance requested.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

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.

@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

🤖 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 `@skills/gentle-ai-collab-perfect/SKILL.md`:
- Around line 178-184: Update the “Stacked to main” guidance to state that the
size:exception threshold uses the pull request’s total additions plus deletions,
matching the enforced cognitive-load check, rather than only slice-specific
additions.
- Around line 107-110: Update the fenced code examples in SKILL.md, including
the blocks around the git commands and the referenced ranges, to have blank
lines before and after each fence and an explicit language tag such as bash or
markdown. Preserve the example contents while satisfying MD031 and MD040.
- Around line 149-151: Update the checklist entry referencing “pending Alan” to
use the role-based wording “pending maintainer” or an explicitly marked generic
placeholder, without hard-coding a specific maintainer identity.
- Around line 40-42: Correct the issue-template reference in the documentation
table by changing the path from `.github/ISSED_TEMPLATE/config.yml` to
`.github/ISSUE_TEMPLATE/config.yml`, while leaving the routing-rule description
unchanged.
- Around line 202-209: Update the permission and commit-history protocol around
the dry-verification guidance to replace mutation attempts with read-only
permission/state checks using gh. When the check shows maintainer-only access is
required, route the requested mutation directly to the maintainer instead of
attempting it; apply the same correction to the guidance referenced around lines
267–279.
- Around line 40-48: Remove the directive in the skills reference table that
instructs the assistant to re-read peer skills’ SKILL.md files, including the
corresponding repeated section around the second referenced location. Keep the
listed skill references and their descriptions intact, but replace or remove the
instruction so peer prompt contents remain opaque and are accessed only through
approved interfaces.
- Around line 120-125: Update the PR creation instructions for the “## 📂
Changes” table to require a per-file source such as `gh pr diff --stat` or the
PR files API, rather than `gh pr view --json additions,deletions,changedFiles`,
while preserving the requirement to include line counts for each changed file.
🪄 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: Repository UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: eccb26b6-796b-46de-886c-2ec1e2f4c432

📥 Commits

Reviewing files that changed from the base of the PR and between e7d23b1 and cd8a65a.

📒 Files selected for processing (1)
  • skills/gentle-ai-collab-perfect/SKILL.md

Comment on lines +40 to +42
| `.github/workflows/pr-check.yml` | Automated gates: `Check Issue Reference`, `Check Issue Has status:approved`, `Check PR Has type:* Label`, `Check PR Cognitive Load` |
| `.github/ISSED_TEMPLATE/config.yml` | Issue-template routing rules; do not bypass |
| `skills/branch-pr/SKILL.md` | Branch + PR creation mechanics |

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

🎯 Functional Correctness | 🟠 Major | ⚡ Quick win

Fix the issue-template path typo.

Line 41 uses .github/ISSED_TEMPLATE/config.yml, but the repository path is .github/ISSUE_TEMPLATE/config.yml. Following the current instruction makes the assistant consult a nonexistent source of truth.

🧰 Tools
🪛 LanguageTool

[uncategorized] ~40-~40: The official name of this software platform is spelled with a capital “H”.
Context: ...ture request structure + same gates | | .github/workflows/pr-check.yml | Automated gat...

(GITHUB)


[uncategorized] ~41-~41: The official name of this software platform is spelled with a capital “H”.
Context: ...* Label, Check PR Cognitive Load| |.github/ISSED_TEMPLATE/config.yml` | Issue-temp...

(GITHUB)

🪛 SkillSpector (2.3.7)

[warning] 42: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 43: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 44: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 45: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 46: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 294: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 295: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 296: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 297: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 298: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 299: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))

🤖 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/gentle-ai-collab-perfect/SKILL.md` around lines 40 - 42, Correct the
issue-template reference in the documentation table by changing the path from
`.github/ISSED_TEMPLATE/config.yml` to `.github/ISSUE_TEMPLATE/config.yml`,
while leaving the routing-rule description unchanged.

Comment on lines +40 to +48
| `.github/workflows/pr-check.yml` | Automated gates: `Check Issue Reference`, `Check Issue Has status:approved`, `Check PR Has type:* Label`, `Check PR Cognitive Load` |
| `.github/ISSED_TEMPLATE/config.yml` | Issue-template routing rules; do not bypass |
| `skills/branch-pr/SKILL.md` | Branch + PR creation mechanics |
| `skills/chained-pr/SKILL.md` | Chained vs Stacked PR strategy mechanics |
| `skills/issue-creation/SKILL.md` | Issue creation mechanics |
| `skills/cognitive-doc-design/SKILL.md` | Doc-writing principles |
| `skills/comment-writer/SKILL.md` | Tone for comment replies |

These files evolve. Re-read them at the start of every contribution.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

🔒 Security & Privacy | 🟠 Major | 🏗️ Heavy lift

Do not instruct the assistant to read peer skills’ SKILL.md files.

These lines direct the assistant to enumerate and read other skills, exposing peer prompt instructions and capabilities to the current skill. Keep cross-skill references opaque or invoke approved interfaces instead of reading the skills directory directly.

Also applies to: 294-299

🧰 Tools
🪛 LanguageTool

[uncategorized] ~40-~40: The official name of this software platform is spelled with a capital “H”.
Context: ...ture request structure + same gates | | .github/workflows/pr-check.yml | Automated gat...

(GITHUB)


[uncategorized] ~41-~41: The official name of this software platform is spelled with a capital “H”.
Context: ...* Label, Check PR Cognitive Load| |.github/ISSED_TEMPLATE/config.yml` | Issue-temp...

(GITHUB)

🪛 SkillSpector (2.3.7)

[warning] 42: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 43: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 44: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 45: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 46: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 294: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 295: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 296: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 297: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 298: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 299: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))

🤖 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/gentle-ai-collab-perfect/SKILL.md` around lines 40 - 48, Remove the
directive in the skills reference table that instructs the assistant to re-read
peer skills’ SKILL.md files, including the corresponding repeated section around
the second referenced location. Keep the listed skill references and their
descriptions intact, but replace or remove the instruction so peer prompt
contents remain opaque and are accessed only through approved interfaces.

Source: Linters/SAST tools

Comment on lines +107 to +110
```
git checkout main && git pull
git checkout -b <type>/<short-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.

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Fix the Markdown fence warnings.

Static analysis reports MD031 and MD040 for these examples. Add blank lines around fenced blocks and specify languages such as bash and markdown.

Also applies to: 140-152, 157-159, 205-208, 212-217, 220-222, 225-228

🧰 Tools
🪛 markdownlint-cli2 (0.22.1)

[warning] 107-107: Fenced code blocks should be surrounded by blank lines

(MD031, blanks-around-fences)


[warning] 107-107: Fenced code blocks should have a language specified

(MD040, fenced-code-language)


[warning] 110-110: Fenced code blocks should be surrounded by blank lines

(MD031, blanks-around-fences)

🪛 SkillSpector (2.3.7)

[warning] 42: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 43: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 44: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 45: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 46: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 294: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 295: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 296: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 297: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 298: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 299: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))

🤖 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/gentle-ai-collab-perfect/SKILL.md` around lines 107 - 110, Update the
fenced code examples in SKILL.md, including the blocks around the git commands
and the referenced ranges, to have blank lines before and after each fence and
an explicit language tag such as bash or markdown. Preserve the example contents
while satisfying MD031 and MD040.

Source: Linters/SAST tools

Comment on lines +120 to +125
4. **Open the PR with `gh pr create`.** Body matches `.github/PULL_REQUEST_TEMPLATE.md`:
- `## 🔗 Linked Issue` → `Closes #N` (or `Fixes`/`Resolves`). Never `Refs`.
- `## 🏷️ PR Type` → exactly one `[x] type:*` matching the actual type
- `## 📝 Summary` → one paragraph: what + why
- `## 📂 Changes` → file table with line counts from `gh pr view --json additions,deletions,changedFiles`
- `## 🧪 Test Plan` → every `go test` command actually run + result, **including pre-existing failures with verification method**

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

# Locate the referenced skill file and inspect the surrounding lines.
if [ -f "skills/gentle-ai-collab-perfect/SKILL.md" ]; then
  nl -ba skills/gentle-ai-collab-perfect/SKILL.md | sed -n '110,135p'
else
  echo "Missing: skills/gentle-ai-collab-perfect/SKILL.md"
fi

# Check for any other guidance that mentions PR change tables or line counts.
rg -n --glob 'AGENTS.md' --glob 'skills/**/*.md' 'gh pr view --json additions,deletions,changedFiles|gh pr diff --stat|PR Type|Changes|line counts|per-file' .

Repository: Gentleman-Programming/gentle-ai

Length of output: 209


🏁 Script executed:

#!/bin/bash
set -euo pipefail

python3 - <<'PY'
from pathlib import Path

p = Path("skills/gentle-ai-collab-perfect/SKILL.md")
if p.exists():
    for i, line in enumerate(p.read_text().splitlines(), 1):
        if 110 <= i <= 135:
            print(f"{i:4d}: {line}")
else:
    print("Missing: skills/gentle-ai-collab-perfect/SKILL.md")
PY

printf '\n--- SEARCH ---\n'
rg -n --glob 'AGENTS.md' --glob 'skills/**/*.md' 'gh pr view --json additions,deletions,changedFiles|gh pr diff --stat|PR Type|Changes|line counts|per-file' .

Repository: Gentleman-Programming/gentle-ai

Length of output: 2973


🏁 Script executed:

#!/bin/bash
set -euo pipefail

python3 - <<'PY'
from pathlib import Path

for path, start, end in [
    ("skills/gentle-ai-collab-perfect/SKILL.md", 235, 250),
    (".github/PULL_REQUEST_TEMPLATE.md", 1, 220),
    ("skills/branch-pr/SKILL.md", 96, 110),
]:
    p = Path(path)
    print(f"\n=== {path} ===")
    if not p.exists():
        print("Missing")
        continue
    lines = p.read_text().splitlines()
    for i in range(start, min(end, len(lines)) + 1):
        print(f"{i:4d}: {lines[i-1]}")
PY

Repository: Gentleman-Programming/gentle-ai

Length of output: 4892


Use a per-file source for the ## 📂 Changes table gh pr view --json additions,deletions,changedFiles only gives aggregate totals plus a changed-file count, so it can’t populate line counts per file. Use gh pr diff --stat or the PR files API here.

🧰 Tools
🪛 LanguageTool

[uncategorized] ~120-~120: The official name of this software platform is spelled with a capital “H”.
Context: ... PR with gh pr create.** Body matches .github/PULL_REQUEST_TEMPLATE.md: - `## 🔗 ...

(GITHUB)

🪛 SkillSpector (2.3.7)

[warning] 42: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 43: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 44: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 45: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 46: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 294: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 295: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 296: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 297: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 298: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 299: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))

🤖 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/gentle-ai-collab-perfect/SKILL.md` around lines 120 - 125, Update the
PR creation instructions for the “## 📂 Changes” table to require a per-file
source such as `gh pr diff --stat` or the PR files API, rather than `gh pr view
--json additions,deletions,changedFiles`, while preserving the requirement to
include line counts for each changed file.

Comment on lines +149 to +151
- [ ] `type:feature` label applied to this PR — pending Alan
- [ ] `size:exception` consideration — see rationale below
- [ ] Fork workflow approval — 4 runs in `action_required` awaiting Alan

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Avoid hard-coding a maintainer identity.

pending Alan becomes misleading when another maintainer handles the PR or another contributor uses this skill. Use pending maintainer or a clearly marked placeholder.

🧰 Tools
🪛 SkillSpector (2.3.7)

[warning] 42: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 43: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 44: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 45: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 46: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 294: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 295: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 296: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 297: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 298: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 299: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))

🤖 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/gentle-ai-collab-perfect/SKILL.md` around lines 149 - 151, Update the
checklist entry referencing “pending Alan” to use the role-based wording
“pending maintainer” or an explicitly marked generic placeholder, without
hard-coding a specific maintainer identity.

Comment on lines +178 to +184
### Stacked to main

Use when **each slice can land independently**. Branches are independent stacks that each target `main`. The diff "pollutes" with previous-slice commits because GitHub does not allow cross-fork base refs (slice branches live only in the contributor's working repo).

- Pros: simple, each PR is its own atomic change.
- Cons: large chained diffs; reviewers must mentally isolate slice-specific changes; needs `size:exception` for anything past 400 lines of slice-specific additions.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

🎯 Functional Correctness | 🟠 Major | ⚡ Quick win

Count the same units as the enforced cognitive-load check.

The repository rule counts additions + deletions for the PR, but this section says “slice-specific additions.” That can undercount the enforced total and cause contributors to miss the required size:exception request.

🧰 Tools
🪛 SkillSpector (2.3.7)

[warning] 42: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 43: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 44: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 45: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 46: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 294: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 295: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 296: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 297: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 298: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 299: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))

🤖 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/gentle-ai-collab-perfect/SKILL.md` around lines 178 - 184, Update the
“Stacked to main” guidance to state that the size:exception threshold uses the
pull request’s total additions plus deletions, matching the enforced
cognitive-load check, rather than only slice-specific additions.

Comment on lines +202 to +209
Before recommending any action that touches permissions, label state, or commit history:

1. **Dry-verify with `gh` first.** Attempt the action and surface the error if it fails. Example:
```
$ gh pr edit 1132 --add-label type:feature
→ GraphQL: ardelperal does not have the correct permissions to execute `AddLabelsToLabelable`
```
That output IS your answer. Don't try to work around it.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

🔒 Security & Privacy | 🟠 Major | ⚡ Quick win

Resolve the contradictory permission guidance.

This protocol says to attempt a permissioned action first, while the surrounding guidance says contributors must not attempt maintainer-only actions. Replace “Attempt the action” with a read-only permission/state check and route the mutation directly to the maintainer.

Also applies to: 267-279

🧰 Tools
🪛 markdownlint-cli2 (0.22.1)

[warning] 205-205: Fenced code blocks should be surrounded by blank lines

(MD031, blanks-around-fences)


[warning] 205-205: Fenced code blocks should have a language specified

(MD040, fenced-code-language)


[warning] 208-208: Fenced code blocks should be surrounded by blank lines

(MD031, blanks-around-fences)

🪛 SkillSpector (2.3.7)

[warning] 42: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 43: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 44: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 45: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 46: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 294: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 295: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 296: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 297: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 298: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))


[warning] 299: [AS3] Skill Enumeration: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Remediation: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

(Agent Snooping (AS3))

🤖 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/gentle-ai-collab-perfect/SKILL.md` around lines 202 - 209, Update the
permission and commit-history protocol around the dry-verification guidance to
replace mutation attempts with read-only permission/state checks using gh. When
the check shows maintainer-only access is required, route the requested mutation
directly to the maintainer instead of attempting it; apply the same correction
to the guidance referenced around lines 267–279.

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.

feat(skills): add gentle-ai-collab-perfect workflow skill for external contributors

1 participant