gh-fix-ci

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

1.00x

Quality

92%

Does it follow best practices?

Impact

33%

1.00x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

A well-structured, highly actionable skill body with a clear sequenced workflow and proper use of a bundled script for detail. The main weakness is duplicated script-usage examples across three sections that add tokens without adding information.

Suggestions

Show the bundled script invocation once (e.g. in Quick start) and reference it from Workflow step 3 and Bundled Resources instead of repeating the command and --json note verbatim.

Consolidate the three near-identical usage blocks in Bundled Resources into a single example, or link back to Quick start to avoid triplication.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the bundled script invocation is repeated near-verbatim in Quick start, Workflow step 3, and Bundled Resources, which could be tightened.	2 / 3
Actionability	Provides copy-paste-ready, fully executable commands with explicit fields — 'gh pr checks <pr> --json name,state,bucket,link,...', 'gh run view <run_id> --log', and 'gh api "/repos/<owner>/<repo>/actions/jobs/<job_id>/logs"' — plus the bundled script.	3 / 3
Workflow Clarity	An 8-step sequence with explicit checkpoints: auth verification (step 1), field-drift/in-progress fallbacks (step 3), an approval gate (steps 6–7), and a recheck feedback loop (step 8).	3 / 3
Progressive Disclosure	SKILL.md is a well-sectioned overview pointing to one-level-deep detail in the real bundled scripts/inspect_pr_checks.py, with logic appropriately split out rather than inlined.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, specific description with an explicit trigger, concrete actions, and clear scoping that distinguishes it from neighbouring skills. It uses third-person voice consistent with the good examples and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'inspect checks and logs', 'summarize failure context', 'draft a fix plan', 'implement only after explicit approval', and 'report only the details URL' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Opens with an explicit 'Use when a user asks to debug or fix failing GitHub PR checks' trigger and clearly states what the skill does, answering both what and when.	3 / 3
Trigger Term Quality	Uses natural terms a user would say — 'debug or fix failing GitHub PR checks', 'GitHub Actions', 'gh' — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (failing GitHub Actions PR checks) and explicitly scopes external providers like Buildkite out, making accidental triggering of other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/skills
Commit: 49f948f

Reviewed: 18 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.