gha

Analyze GitHub Actions failures and identify root causes

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/gha/SKILL.md

Quality

Content

70%

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

The content is a well-structured, actionable investigation workflow with clear sequencing and verification steps. Its main weaknesses are emphatic repetition and a missing command for the most important step (reading the failed logs).

Suggestions

Add the concrete log-retrieval command for step 1, e.g. 'gh run view <run-id> --log-failed' to read the failing job's output.

Trim redundant emphasis capitalization (CRITICAL/IMPORTANT/ACTUALLY) since the numbered structure already conveys priority.

Optionally show the exact command shape for viewing a single job's logs (e.g. 'gh run view --job=<job-id> --log') to make step 2 fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's familiarity with the gh CLI, but it is padded with repeated emphatic capitalization ('CRITICAL', 'THIS SPECIFIC JOB', 'ACTUALLY') that could be tightened without losing meaning.	2 / 3
Actionability	It gives concrete commands for listing runs, inspecting jobs, and searching PRs, but the pivotal log-reading step lacks an executable command (e.g. 'gh run view --log-failed'), leaving key details incomplete.	2 / 3
Workflow Clarity	A clear five-step numbered sequence with explicit verification checkpoints ('Verify by checking...', 'Verify your hypothesis against the logs'); the task is read-only so destructive feedback loops are not required.	3 / 3
Progressive Disclosure	This is a single-purpose skill under 50 lines with well-organized numbered sections and no need for external references, which the simple-skills note allows to score 3.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 clear and domain-specific but terse: it conveys what the skill does without any 'when to use it' guidance or natural trigger variations. It sits at a competent-but-incomplete level across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a GitHub Actions / CI workflow run fails and the user wants the root cause.'

Include natural keyword variations users actually say, such as 'CI failure', 'failing build', 'workflow run', or 'red check'.

List a couple more concrete actions (e.g. 'check flakiness, find the breaking commit, search for fix PRs') to raise specificity.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ('GitHub Actions failures') and two actions ('Analyze' and 'identify root causes'), matching the anchor that names a domain with some but not comprehensive actions; it is not a multi-action list like the level-3 example.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance for when to invoke it, which the guidelines cap at 2.	2 / 3
Trigger Term Quality	'GitHub Actions failures' is a term users naturally say, but common variations like 'CI', 'build', 'workflow run', or 'failing checks' are missing, so coverage is partial rather than complete.	2 / 3
Distinctiveness Conflict Risk	'GitHub Actions failures' is a reasonably distinct niche, but without explicit trigger terms it could still overlap with general git/CI debugging skills, matching the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	8 / 12 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: ykdojo/claude-code-tips
Path: skills/gha/SKILL.md
Commit: 31038b8

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.