CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

92%

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

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.

An highly actionable, well-sequenced CI debugging playbook with executable commands and genuine error-recovery loops. Minor improvements possible by deduplicating the quick-reference table and moving repo-specific log-structure details to a reference file.

DimensionReasoningScore

Conciseness

The body is command-dense and assumes competence (no explanations of git/CI basics), but the Quick Reference table duplicates commands already shown in the steps and Step 5's grep patterns overlap Step 4's, adding trimmable tokens.

4 / 5

Actionability

Every step gives copy-paste-ready commands (`gh pr checks --jq ...`, `gh api repos/.../jobs/<JOB_ID>/logs`, `grep -n '##[error]'`) with concrete placeholders, real artifact names ("logs-linux-x64-electron-extension-host-1"), and coverage of test, build, infrastructure, and in-progress-run cases.

5 / 5

Workflow Clarity

A clearly sequenced 7-step workflow with explicit validation before pushing ("Verify compilation", "Run relevant unit tests locally"), a pre-fix decision checkpoint (Step 6), and feedback loops (watch checks, rerun failed jobs, check main, fall back to Option C when the run is in progress).

5 / 5

Progressive Disclosure

No bundle files exist, and the single-file structure is well-sectioned with headers and a navigation table; however, the VS Code-specific material (artifact naming conventions, log directory structure, infrastructure error catalog) is inlined where a references file would keep the core workflow leaner.

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 that clearly states capability, explicit trigger conditions, and a concrete action inventory in third person. The only gap is modest synonym coverage for trigger terms (e.g., build/pipeline failures).

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" — giving comprehensive coverage of the CI-failure workflow; no meaningful capability gaps remain.

5 / 5

Completeness

Explicitly answers both what ("Investigate and fix CI failures on a pull request" plus enumerated sub-actions) and when ("Use when CI checks fail on a PR branch") with concrete trigger phrasing, matching the top anchor.

5 / 5

Trigger Term Quality

"CI failures", "CI checks fail on a PR branch", and "pull request" are natural phrases users would say, but common synonyms such as "build failures", "pipeline", or "GitHub Actions" are missing, placing it just below comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — CI failure triage on PRs via the `gh` CLI ("Requires the `gh` CLI") — with trigger terms unlikely to fire for adjacent git, review, or commit 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

microsoft/vscode

Path

.github/skills/fix-ci-failures/SKILL.md

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.