CtrlK
BlogDocsLog inGet started
Tessl Logo

diagnose-ci-failures

Diagnose CI failures for a PR using the GitHub CLI, extract error logs, and generate a plan to fix them. Use when the user asks to check CI status, pull CI issues, triage test failures, or investigate PR build failures.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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-structured, actionable guide with executable gh CLI commands and a clear five-step workflow that respects Claude's intelligence. It is solidly above the midpoint on all dimensions, with only minor tightening and consolidation opportunities.

Suggestions

Tighten the 'Common CI Check Names' and 'Example Commands' sections or fold them into the workflow steps to reduce token overhead and lift conciseness toward 5.

Add one explicit feedback loop for log extraction (e.g., if `--log-failed` returns truncated output, retry with `gh run view --log` or download the full log archive) to push workflow clarity higher.

Show a brief jq/grep snippet for parsing `statusCheckRollup` into failed-check names and run IDs, closing the main actionability gap.

DimensionReasoningScore

Conciseness

The body is efficient, using code blocks for commands and assuming Claude's competence rather than explaining CI/gh concepts; minor padding appears in the 'Common CI Check Names' list and some 'Important Notes' that restate earlier points, placing it above the 3-anchor but not fully lean.

4 / 5

Actionability

Provides mostly executable guidance — concrete `GH_PAGER=cat gh pr view ... --json statusCheckRollup` and `gh run view <run-id> --log-failed` commands with appropriate placeholders and a copy-paste-ready 'Example Commands' section — with minor gaps such as how to parse the statusCheckRollup JSON.

4 / 5

Workflow Clarity

A clear five-step sequence (verify PR → check status → extract logs → categorize → generate plan) with explicit handling of in-progress CI and validation steps embedded in the plan output; the skill is deliberately non-destructive (plan-only), so the destructive-cap does not apply, but explicit error-recovery feedback loops are only implied rather than spelled out.

4 / 5

Progressive Disclosure

Well-organized into clearly labeled sections (Overview, Workflow, Important Notes, Common CI Check Names, Example Commands) with appropriately signaled cross-references to the `create-pr` and `fix-errors` skills; no bundle files exist or are needed, but it sits just below the top anchor because a couple of sections (Common CI Check Names, Example Commands) could be consolidated.

4 / 5

Total

16

/

20

Passed

Description

87%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 specific, third-person, and explicitly pairs concrete capabilities with a strong 'Use when...' trigger clause. It is well above the midpoint on every dimension with no vague fluff or over-claims.

DimensionReasoningScore

Specificity

Names the domain (CI failures for a PR via GitHub CLI) and three concrete actions — "Diagnose CI failures", "extract error logs", and "generate a plan to fix them" — with only minor coverage gaps, fitting the 'several specific actions' anchor above the 3-anchor.

4 / 5

Completeness

Explicitly answers both 'what' (diagnose, extract logs, generate plan) and 'when' with a concrete 'Use when the user asks to check CI status, pull CI issues, triage test failures, or investigate PR build failures' clause, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users would say — "check CI status", "pull CI issues", "triage test failures", "investigate PR build failures" — giving good keyword coverage, though a few common variants (e.g. 'CI is failing', 'build is broken') are missing.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche — diagnosing PR CI failures via the GitHub CLI — with distinct triggers and minimal overlap risk with other skills, matching the 'clear niche with distinct triggers' anchor.

5 / 5

Total

18

/

20

Passed

Validation

100%

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
warpdotdev/common-skills
Reviewed

Table of Contents

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.