CtrlK
BlogDocsLog inGet started
Tessl Logo

gha-diagnosis

Use when GitHub Actions checks fail, workflow runs are red, or user asks to fix CI. Triggers on "fix CI", "actions failing", "checks are red", "pipeline broke", "workflow failed". User may provide a run URL, job ID, or just ask to fix.

61

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./registry/skills/gha-diagnosis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 tightly organized, highly actionable fix loop with strong validation and feedback structure — the main strength. The only gaps are a minor Rules/Pitfalls redundancy and a verify step that could show one concrete local command example.

DimensionReasoningScore

Conciseness

The body is lean with no concept over-explanation and dense tables that earn their tokens; the only redundancy is minor overlap between the "Rules" list and the "Common Pitfalls" table.

4 / 5

Actionability

It provides copy-paste-ready gh commands (gh run view --log-failed, gh run list --json ...) and a signal→fix triage table, but the verify step defers to "the same command from the workflow YAML" rather than giving a concrete example.

4 / 5

Workflow Clarity

A clear three-phase sequence with explicit validation checkpoints — local verify before commit, revert-and-retry on failure (max 3 attempts), and re-check CI with a loop back to Phase 1 — exactly the feedback-loop pattern the rubric rewards.

5 / 5

Progressive Disclosure

Well-sectioned and self-contained with no nested references and no need for external files, but at ~68 lines with inline triage/pitfalls tables it slightly exceeds the under-50-line simple-skill threshold that would auto-qualify for a 5.

4 / 5

Total

17

/

20

Passed

Description

63%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 excels at trigger-term coverage and explicit "when" guidance but is weak on stating concrete capabilities — it never says the skill fetches logs, diagnoses, fixes, verifies, and commits. Lead with a one-line action statement before the "Use when" clause.

Suggestions

Open with a concrete "what" clause listing the skill's actions, e.g. "Fetches failed GitHub Actions logs via gh, diagnoses root causes, applies fixes, verifies locally, and commits."

Keep the strong trigger list but move it after the capability statement so the description answers both what and when.

Tighten "pipeline broke"/"workflow failed" with GitHub Actions framing to reduce overlap with generic CI skills.

DimensionReasoningScore

Specificity

The description names the GitHub Actions/CI domain and input modes ("run URL, job ID, or just ask to fix") but lists no concrete actions the skill performs; the only action is the generic "fix CI".

2 / 5

Completeness

The "when" is explicit and strong ("Use when GitHub Actions checks fail, workflow runs are red, or user asks to fix CI"), but the "what" is only weakly implied via "fix CI" with no enumeration of what the skill does.

3 / 5

Trigger Term Quality

It enumerates comprehensive natural trigger phrases users would actually say — "fix CI", "actions failing", "checks are red", "pipeline broke", "workflow failed" — covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

It carves a clear GitHub Actions niche with distinct CI-specific triggers, though "pipeline broke"/"workflow failed" could plausibly match non-GHA CI systems, giving minor overlap risk.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
provectus/awos-recruitment
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.