fix-issue

Fix a single GitHub issue end-to-end: triage, research, write the fix, review, and create a PR. Use when asked to fix an issue: "fix issue 1234", "resolve #500", "create a PR for issue 200".

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-sequenced orchestration skill with concrete commands and a clear decision tree plus review feedback loop. Minor gaps are a redundant disclosure-footer explanation and missing success verification on the outward-facing gh actions.

Suggestions

Remove the standalone disclosure-footer paragraph (lines 45-47) — the footer is already shown in each comment template — and reference it once to tighten conciseness.

Add a verification step after each gh issue close/comment action (e.g., confirm the comment posted or the issue state changed) to add explicit validation checkpoints to the outward-facing branches.

Briefly state what a "clean" review means or how to confirm the PR was opened, so the Write/Review/Create-PR steps are actionable without relying entirely on the delegated sub-skills.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned, but the agent-disclosure footer is explained both inline in each comment template and again in a standalone paragraph ("End every issue comment with an accurate agent-disclosure footer..."), a minor redundancy that could be trimmed.	4 / 5
Actionability	Concrete gh close/comment commands with clearly marked placeholders and specific sub-skill invocations ("/triage-issue $ARGUMENTS", "/research", "/write") make it mostly executable, though the Write/Review/Create-PR steps delegate detail to sub-skills and leave placeholder filling to Claude.	4 / 5
Workflow Clarity	A clearly numbered 1–8 sequence with a triage-verdict decision tree and an explicit review feedback loop ("fix them and re-review until clean"); however the close/escalate/leave-open branches each end with a bare "Done." without verifying the gh command succeeded, a minor validation gap in outward-facing state changes.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed; the orchestrator body is self-contained with well-organized numbered sections and no nested references, satisfying the simple-skill exception for clean structure.	5 / 5
	Total	17 / 20 Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states the end-to-end capability and pairs it with concrete, natural trigger phrases. The only soft spot is a minor trigger overlap with the /create-pr sub-skill it orchestrates.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "triage, research, write the fix, review, and create a PR" — giving comprehensive coverage of the end-to-end workflow rather than a single generic verb.	5 / 5
Completeness	Explicitly answers both what ("Fix a single GitHub issue end-to-end: ...") and when ("Use when asked to fix an issue: ...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Provides natural phrases users actually say — "fix issue 1234", "resolve #500", "create a PR for issue 200" — covering synonyms (fix/resolve) and the PR-creation variant.	5 / 5
Distinctiveness Conflict Risk	The "fix issue / resolve #" triggers are distinct, but "create a PR for issue 200" overlaps with the delegated /create-pr sub-skill, giving minor overlap risk with a closely related skill rather than a fully clean niche.	4 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: docker/docs
Path: .agents/skills/fix-issue/SKILL.md
Commit: ff96ad1

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.