gh-fix-ci

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions. Use the GitHub app from this plugin for PR metadata and patch context, and use `gh` for Actions check and log inspection before implementing any approved fix.

Quality

100%

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

100%Weight 40%Scale 1-3

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

The body is a tight, actionable workflow that respects Claude's competence, leads with executable commands and a bundled script, and sequences an 8-step process with real validation checkpoints. Progressive disclosure is handled well via the bundled script and assets.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — no explanations of concepts Claude already knows (e.g. what GitHub Actions is), and every section earns its tokens with concrete commands rather than padding.	3 / 3
Actionability	Provides copy-paste-ready, executable commands — the bundled script invocation with real flags, `gh pr checks ... --json`, `gh run view <run_id> --log`, and `gh api .../jobs/<job_id>/logs` — plus a manual fallback path.	3 / 3
Workflow Clarity	An 8-step numbered workflow with explicit validation checkpoints (verify gh auth, propose-and-wait-for-approval, recheck status) and feedback loops (re-run tests, recheck `gh pr checks`, report residual/flaky/external checks).	3 / 3
Progressive Disclosure	SKILL.md stays an overview with a well-signaled, one-level-deep bundled script (verified present at scripts/inspect_pr_checks.py) summarized with usage examples, plus asset files kept out of the main flow.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

The description is specific, trigger-rich, and complete, clearly stating both what the skill does and when to use it. Its focused GitHub-Actions-only niche also keeps conflict risk low.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'debug or fix failing GitHub PR checks', 'PR metadata and patch context', 'Actions check and log inspection', and 'implementing any approved fix' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (inspect checks/logs, use the app and gh, implement an approved fix) and when via an explicit 'Use when a user asks to debug or fix failing GitHub PR checks' trigger clause.	3 / 3
Trigger Term Quality	Uses natural phrasings a user would actually say ('debug or fix failing GitHub PR checks', 'GitHub Actions') with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	A clear niche — failing GitHub Actions PR checks — with a hybrid app-vs-gh distinction that makes it unlikely to trigger for the wrong skill.	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/plugins
Path: plugins/github/skills/gh-fix-ci/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.