gha

Analyze GitHub Actions failures and identify root causes

Quality

62%

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

71%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.

The body is a well-sequenced, actionable investigation workflow with concrete gh CLI commands and explicit verification steps. Its main weakness is over-emphatic, repetitive capitalization that slightly hurts token efficiency without adding clarity.

Suggestions

Reduce repeated emphasis capitalization (CRITICAL/IMPORTANT/ACTUALLY/SPECIFICALLY); state the key instruction once and trust Claude to follow it.

Add a quick example of the exact gh log command for step 1 (e.g. 'gh run view <run-id> --log') to make log retrieval copy-paste ready.

Optionally collapse the duplicated 'focus on what ACTUALLY caused the failure' reminders across steps 1, 4, and the report into a single clear statement.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but the repeated emphatic capitalization ('CRITICAL', 'IMPORTANT', 'ACTUALLY', 'SPECIFICALLY', 'THE EXACT SAME failing job') and restated directives could be tightened, matching the mostly-efficient-but-could-trim anchor.	3 / 5
Actionability	It provides concrete, executable gh commands (e.g. 'gh run list --workflow=<workflow-name>', 'gh run view <run-id> --json jobs', 'gh pr list --state open --search "<keywords>"') with only minor gaps in the log-reading and root-cause steps, fitting the mostly-executable anchor.	4 / 5
Workflow Clarity	The five-step sequence is clear with explicit verification checkpoints (verifying the breaking commit against all runs before/after, verifying the root-cause hypothesis against logs), but it lacks a full validate-fix-retry feedback loop, so it sits just below the 5 anchor.	4 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, well-organized into numbered steps plus a final report structure, and has no bundle files or external references, so the simple-skill exception yields a 5 for clear, well-organized content.	5 / 5
	Total	16 / 20 Passed

Description

53%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.

The description is concise, specific, and third-person, clearly stating what the skill does for a well-defined niche. Its main weakness is the absence of an explicit 'Use when' trigger clause, which limits completeness and trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when investigating a failed GitHub Actions run, workflow, or CI job to find the root cause.'

Include natural synonyms users say such as 'CI', 'workflow run', 'build', or 'job' to broaden trigger-term coverage.

Optionally list the key output (root cause + breaking commit + flakiness assessment) to raise specificity toward a 4.

Dimension	Reasoning	Score
Specificity	The description names the domain ('GitHub Actions failures') and two concrete actions ('Analyze ... failures and identify root causes'), matching the anchor for naming domain plus 1-2 actions without comprehensive coverage.	3 / 5
Completeness	The 'what' is clear (analyze failures, identify root causes) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	'GitHub Actions' and 'failures' are natural user terms, but common variations like 'workflow run', 'CI', 'build', or 'job' are missing, so coverage is partial rather than good.	3 / 5
Distinctiveness Conflict Risk	'GitHub Actions failures' is a clear, fairly narrow niche unlikely to trigger unrelated skills, with only minor overlap risk against generic CI/git skills; it is not quite at the fully-distinct 5 anchor.	4 / 5
	Total	13 / 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: ykdojo/claude-code-tips
Path: skills/gha/SKILL.md
Commit: 2da5305

Reviewed: 7 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.