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

96%

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

92%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 orchestration skill: the decision tree over triage verdicts is fully specified, commands are concrete, and a re-review loop provides validation. The only weakness is placeholder text in the issue-comment templates, which keeps it from being fully copy-paste ready.

Suggestions

Provide one filled-in example of the close/escalate comment (e.g. a sample one-sentence reason and footer) so the templates are copy-paste ready rather than placeholder text.

State briefly what to do if a required sub-skill (e.g. /triage-issue or /create-pr) is unavailable, to close the last actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence throughout — numbered steps, bare commands, and one short framing sentence ("it owns the decision tree, not the individual steps") that earns its place. Nothing explains concepts Claude already knows.	5 / 5
Actionability	Mostly executable: concrete `gh issue close`/`gh issue comment` commands and named sub-skill invocations (/triage-issue, /research, /write, /review-changes, /create-pr). However, templates like "<one sentence explaining why>", "<upstream-repo>", and "<active coding agent name>" are placeholders rather than copy-paste-ready content, so it stops short of the 5 anchor.	4 / 5
Workflow Clarity	Eight numbered steps with a complete decision tree over triage verdicts (close/escalate/leave-open/fix) and an explicit feedback loop: "If issues are found, fix them and re-review until clean." This matches the top anchor — clear sequence, explicit validation, error-recovery loop.	5 / 5
Progressive Disclosure	No bundle files exist, and none are needed: the body is well-sectioned under numbered headings, sized appropriately, and delegates each stage's detail to a sub-skill (one level deep) instead of inlining it. Structure and navigation are clear.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An exemplary description: concrete five-action capability list, explicit 'Use when' clause with realistic example utterances, third-person imperative voice, and no padding. It hits every judging guideline without any over-claiming.

Dimension	Reasoning	Score
Specificity	The description names five concrete actions — "triage, research, write the fix, review, and create a PR" — giving comprehensive coverage of the end-to-end workflow, matching the top anchor. It is not a 4 because no stage of the workflow is missing.	5 / 5
Completeness	Both questions are answered explicitly: what ("Fix a single GitHub issue end-to-end: triage, research, write the fix, review, and create a PR") and when ("Use when asked to fix an issue" with concrete trigger phrases). This matches the top anchor exactly.	5 / 5
Trigger Term Quality	Natural user utterances are quoted directly: "fix issue 1234", "resolve #500", "create a PR for issue 200", plus "asked to fix an issue". These cover how users actually phrase the request, including the '#number' synonym form.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche — fixing a single GitHub issue through to a PR — with triggers (issue numbers, '#500', 'create a PR for issue') that are distinct from generic PR-review or repo-maintenance skills.	5 / 5
	Total	20 / 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: 4d3cbcd

Reviewed: 1 day 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.