agentleFS
surasakchosurasakcho/claude-skills/check-feedback/SKILL.md

check-feedback

Skill0 starsChanged 5 months agoMITView on GitHub

Check the CURRENT repo's GitHub issues for feedback the owner left, then act on it by following that repo's own feedback pipeline. Use when the user tells the repo's CEO/manager to "check the issues", "check for feedback", or see whether the owner replied on any issue — or when a CEO/manager session should look for owner feedback and process it per the repo's pipeline.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 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.

  • 2

    Very specific

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

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

    If this fails (not a repo, no GitHub remote, or gh not authed), say so and stop — there are no issues to check.

    line 18
  2. Distinctive:

    Read this repo's CLAUDE.md first — the pipeline (or a pointer to it) is usually there.

    line 24
  3. Very specific:

    If it points to a dedicated doc (e.g.

    line 25
  4. Distinctive:

    If you cannot find any documented feedback pipeline, stop and ask the owner where it's defined rather than inventing one.

    line 27
  5. Distinctive:

    Don't pre-filter with assumptions about labels or markers — surface what the owner actually wrote and let the repo's pipeline decide what …

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Go see whether the owner left feedback on this repo's GitHub issues, then handle it by following this repo's own feedback pipeline. This skill only points you at the issues and at the pipeline — it deliberately does not define the pipeline. The repo does.

Operate on the current repo only. One invocation = one repo.

1. Confirm context

Confirm the current directory is a git repo with a GitHub remote and gh is authenticated:

gh repo view --json nameWithOwner -q .nameWithOwner

If this fails (not a repo, no GitHub remote, or gh not authed), say so and stop — there are no issues to check.

2. Find this repo's feedback pipeline — it is authoritative

The process for interpreting and acting on feedback lives in the repo, not here. Locate it before touching any issue:

  • Read this repo's CLAUDE.md first — the pipeline (or a pointer to it) is usually there.
  • If it points to a dedicated doc (e.g. a pipeline.md, feedback.md, or a file under docs/), read that too.

If you cannot find any documented feedback pipeline, stop and ask the owner where it's defined rather than inventing one. Everything below follows that doc, not this skill.

3. Check the issues

List the open issues and read the ones that may carry owner feedback, including their comment threads:

gh issue list --state open
gh issue view <number> --comments

Don't pre-filter with assumptions about labels or markers — surface what the owner actually wrote and let the repo's pipeline decide what counts as actionable feedback.

4. Act per the repo's pipeline

For each issue where the owner left feedback, do exactly what this repo's pipeline prescribes — respond, relabel, move a stage, open the next piece of work, close it, whatever the pipeline defines. This skill intentionally does not spell out those steps; the repo's doc from step 2 does.

5. Report back

One short summary: which issues had owner feedback, what you did with each per the pipeline, and anything now waiting back on the owner.

Download now (ZIP)

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.