CtrlK
BlogDocsLog inGet started
Tessl Logo

fix-ci-failures

Investigate and fix CI failures on a pull request. Use when CI checks fail on a PR branch — covers finding the PR, identifying failed checks, downloading logs and artifacts, extracting the failure cause, and iterating on a fix. Requires the `gh` CLI.

73

Quality

90%

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

The canonical home for this skill is fix-ci-failures in microsoft/vscode

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A highly actionable, well-sequenced guide whose value comes from non-obvious, experience-derived knowledge (run-vs-job log timing, error-annotation grepping, flake triage). Its main costs are length-driven: a redundant quick-reference section and long repo-specific catalogs inlined in a single file rather than split into references.

Suggestions

Trim the Quick Reference table (or reduce it to commands not already shown verbatim in the steps) to cut repeated tokens.

Move the VS Code-specific material — log artifact directory structure and the infrastructure/flaky-failure pattern catalog — into a references/ file (e.g., LOG-STRUCTURE.md, FLAKY-FAILURES.md) and link to it one level deep.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence, surfacing genuinely non-obvious knowledge (##[error] annotations, artifact naming conventions, --log-failed's run-completion requirement). However, the closing Quick Reference table repeats commands already shown, and Option B's '--dir /dev/null' probing hack is noise, so not every token earns its place.

4 / 5

Actionability

Fully executable copy-paste-ready gh/git commands throughout with clear placeholder conventions (<RUN_ID>, <JOB_ID>), plus concrete grep patterns, specific file paths, and worked examples covering the common failure cases.

5 / 5

Workflow Clarity

A clear 7-step sequence with explicit validation checkpoints and a feedback loop: wait for pending checks, triage PR-caused vs. infrastructure failures before changing code, verify locally (npm run typecheck-client, ./scripts/test.sh), then push and re-watch CI with gh pr checks --watch.

5 / 5

Progressive Disclosure

Well-organized single file with clear section headers, labeled options A/B/C, and a Quick Reference table for navigation. But at ~270 lines with no bundle files, repo-specific detail like the VS Code log artifact structure and the infrastructure/flake failure catalog is inlined where a one-level reference file would fit, keeping it short of a lean overview.

4 / 5

Total

18

/

20

Passed

Description

92%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.

A strong description: it states concrete capabilities, an explicit 'Use when' trigger, a clear niche, and a dependency ('Requires the gh CLI'). The only weakness is modest synonym coverage in trigger terms.

DimensionReasoningScore

Specificity

Lists five concrete actions ('finding the PR, identifying failed checks, downloading logs and artifacts, extracting the failure cause, and iterating on a fix') — comprehensive coverage of the workflow with no gaps.

5 / 5

Completeness

Explicitly answers both what ('Investigate and fix CI failures on a pull request') and when ('Use when CI checks fail on a PR branch') with a concrete trigger phrase. The 'when' clause is already explicit and specific, so the level-4 anchor's caveat does not apply.

5 / 5

Trigger Term Quality

Natural phrases users would say ('CI failures', 'CI checks fail', 'PR branch') are present, but common synonyms like 'build failure', 'pipeline', or 'GitHub Actions' are missing. Good keyword coverage, just short of the comprehensive synonym level.

4 / 5

Distinctiveness Conflict Risk

Clear niche — CI failure diagnosis on PR branches via the gh CLI — with distinct triggers, minimal overlap risk with generic git or debugging skills.

5 / 5

Total

19

/

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
posit-dev/positron
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.