agentleFS
dart-langdart-lang/ai/.agents/skills/closing-obsolete-issues/SKILL.md

closing-obsolete-issues

Skill292 starsChanged 26 days agoBSD-3-ClauseView on GitHub

Find and close obsolete, stale, or not reproducible issues in the dart-lang/ai repository.

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to find old, outdated issues in the dart-lang/ai repository that can be closed because they have been fixed, are stale, …

    line 9
  2. Very specific:

    Use the GitHub CLI (gh) to search for the oldest open issues.

    line 14
  3. Distinctive:

    Use any label that the user gives you, or none if the user does not specify any issue labels.

    line 15
  4. Very specific:

    Use gh issue view <number> --repo dart-lang/ai to get details.

    line 23
  5. Distinctive:

    Style Constraint: DO NOT use em dashes (—) in the comments.

    line 30
  6. Very specific:

    If you discover a new, distinct category of closing rationale that is not covered in references/rationale_templates.md, update the …

    line 36
  7. Very specific:

    Use available file and content search tools (such as grep, ripgrep) to check the current codebase for references to the issue or relevant …

    line 44
  8. Distinctive:

    Look for related PRs that might have fixed the issue but didn't close it automatically.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Closing Obsolete Issues

Use this skill to find old, outdated issues in the dart-lang/ai repository that can be closed because they have been fixed, are stale, obsolete, or not reproducible.

Instructions

  1. Identify Target Issues:
    • Use the GitHub CLI (gh) to search for the oldest open issues.
    • Use any label that the user gives you, or none if the user does not specify any issue labels.
    • Sort by creation date (created-asc) or last update (updated-asc) to find the most likely candidates for being outdated.
    • Fetch at least 10-20 candidates.
    • Example command (with label): gh issue list --repo dart-lang/ai --search "label:bug is:open sort:created-asc" --limit 20 | cat
    • Example command (without label): gh issue list --repo dart-lang/ai --search "is:open sort:created-asc" --limit 20 | cat
  2. Investigate Status:
    • For each candidate, analyze its description and comments.
    • Use gh issue view <number> --repo dart-lang/ai to get details.
    • Compare the issue's request or reported bug with the current state of the codebase.
    • Refer to references/rationale_templates.md for a library of common reasons issues become outdated.
    • Safety Rule: Do not assume a bug is fixed or obsolete just because the code has been updated. Verify if the specific bug behavior is still possible. Valid bugs or feature requests should not be closed as stale just because they are old or have no activity. Inactivity alone does not invalidate a feature request or bug report.
  3. Draft and Review Closing Comments (CRITICAL MANDATE):
    • For issues identified as candidates for closing, draft a detailed comment for each explaining why it can be closed.
    • Style Constraint: DO NOT use em dashes (—) in the comments. Use hyphens (-) or colons (:) instead.
    • Template: Consult references/rationale_templates.md for wording inspiration.
    • Each comment MUST end with: "If there is more work to do here, please let us know by commenting on this issue or filing a new one with up to date information. Thanks!"
    • User Approval Required: You MUST present the identified issues (including URLs to the issues for easy navigation) and their drafted comments to the user and obtain explicit approval BEFORE running any command that closes an issue.
  4. Iterate on Skill Knowledge (Learning Loop):
    • If you discover a new, distinct category of closing rationale that is not covered in references/rationale_templates.md, update the reference file to include it.
  5. Execute and Summarize:
    • Once approved, use gh issue close with the -c flag to post the comment and close the issue.
    • Provide the user with a clean bulleted list of links to each closing comment.

Tips

  • Use available file and content search tools (such as grep, ripgrep) to check the current codebase for references to the issue or relevant code.
  • Look for related PRs that might have fixed the issue but didn't close it automatically.

Download now (ZIP)

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. flutter/devtools★ 1.7k70% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.