Detects subtle CI failures and performance issues that aren't obvious in job logs.

Install

mkdir -p .claude/skills/audit-ci && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12203" && unzip -o skill.zip -d .claude/skills/audit-ci && rm skill.zip

Installs to .claude/skills/audit-ci

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Audit recent CI runs for anomalies (warnings, uncached docker builds, flaky/slow tests, regressions).
101 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Identify warnings in CI run annotations
  • Detect uncached Docker image rebuilds
  • Flag flaky tests that recovered on retry
  • Pinpoint egregiously slow jobs or tests
  • Surface failures recurring across multiple PRs

How it works

The skill analyzes recent CI runs by examining annotations, checking for uncached Docker builds, identifying flaky tests, and detecting slow steps or recurring failures.

Inputs & outputs

You give it
A CI run ID
You get back
A report detailing CI anomalies grouped by category

When to use audit-ci

  • Identify flaky tests
  • Find warnings in CI logs
  • Detect slow build steps
  • Audit CI pipeline efficiency

About audit-ci

Analyzes recent CI runs to surface hidden warnings, flaky tests masked by retries, and inefficient build steps. It identifies patterns of failure to improve pipeline reliability.

Audit recent CI runs for anomalies (warnings, uncached docker builds, flaky/slow tests, regressions).

When not to use it

  • When the goal is to fix CI issues, as this skill only identifies and reports
  • When looking for test results directly in workflow jobs, as they are posted as separate check-runs

Limitations

  • The skill identifies and reports anomalies; it does not fix them.
  • Test results are not in the workflow jobs; they are in separate check-runs.
  • It does not have a rule for every anomaly, requiring judgment for 'anything else that looks off'.

How it compares

This skill systematically audits CI runs for subtle degradations that a human might miss, providing a structured report of anomalies rather than requiring manual log inspection.

Compared to similar skills

audit-ci side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
audit-ci (this skill)02moNo flagsIntermediate
gh-fix-ci126moReviewIntermediate
fix-ci16moReviewIntermediate
analyze-failures16moCautionIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

gh-fix-ci

openai

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

1234

fix-ci

llama-farm

Fetch GitHub CI failure information, analyze root causes, reproduce locally, and propose a fix plan. Use `/fix-ci` for current branch or `/fix-ci <run-id>` for a specific run.

111

analyze-failures

saleor

Analyze Playwright E2E test failure reports from CI. Parses merged blob reports, groups similar errors, and delegates to specialized subagents for investigation and fixes. Use when CI tests fail or when asked to fix E2E test failures.

19

gradle-expert

vitorpamplona

Build optimization, dependency resolution, and multi-module KMP troubleshooting for AmethystMultiplatform. Use when working with: (1) Gradle build files (build.gradle.kts, settings.gradle), (2) Version catalog (libs.versions.toml), (3) Build errors and dependency conflicts, (4) Module dependencies and source sets, (5) Desktop packaging (DMG/MSI/DEB), (6) Build performance optimization, (7) Proguard/R8 configuration, (8) Common KMP + Android Gradle issues (Compose conflicts, secp256k1 JNI variants, source set problems).

19

debugging-workflows

githubnext

Guide for debugging GitHub Agentic Workflows - analyzing logs, auditing runs, and troubleshooting issues

16

fix-sync

ClickHouse

Fix the "CH Inc sync" job in a pull request by resolving conflicts in the corresponding clickhouse-private sync PR.

16

Search skills

Search the agent skills registry