agentleFS
Sign inStart free
rpraharajrpraharaj/ai-sdlc/skills/review-pipeline/SKILL.md

review-pipeline

Skill0 starsChanged 19 days agoMITView on GitHub

Review CI pipeline config for missing gates, secrets, and flakes — from files you can read. Use when the user asks to review CI, review the pipeline, or /review-pipeline. Do not invent jobs. Do not add YAML unless asked to implement.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the pipeline that exists.

    line 17
  2. Distinctive:

    Do not invent jobs. Do not “add more YAML” as the whole answer.

    line 19
  3. Distinctive:

    If there is no CI file and no log, stop.

    line 34
  4. Very specific:

    Read AGENTS.md if present.

    line 42
  5. Distinctive:

    Look for: secrets in the file, unbounded matrix, no test job, skip-on-failure of the required check.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review pipeline

Read the pipeline that exists. This is not fix-ci (that fixes a red run) and not cut-release.

Do not invent jobs. Do not “add more YAML” as the whole answer.

Is this the right skill?

SignalDo this instead
A specific red runfix-ci
Env driftdiff-environments
Release go/no-goplan-rollback / cut-release

Required inputs

  • CI config in the repo (paths you find) or a log the user named
  • AGENTS.md (what checks the repo claims)

If there is no CI file and no log, stop.

Human decisions (do not invent)

  • Which missing gate is required vs nice

Procedure

  1. Read AGENTS.md if present. Find CI configs (common names: .github/workflows/, .gitlab-ci.yml, Jenkinsfile, azure-pipelines.yml). Read what exists.
  2. Compare claimed checks in AGENTS.md to jobs you saw. Gaps are findings.
  3. Look for: secrets in the file, unbounded matrix, no test job, skip-on-failure of the required check.
  4. Find the home: docs/ops/pipeline-review-YYYY-MM-DD.md.
  5. Open references/pipeline-review-template.md. Copy every heading. Write n/a when unused.

Output

  • Path: docs/ops/pipeline-review-YYYY-MM-DD.md
  • Template: references/pipeline-review-template.md

Quality bar

  • Every finding cites a path or log line
  • No invented job name
  • Secrets called out if present in the config you read
  • Unused headings are n/a

Done

  1. Path
  2. Finding count
  3. Next skill: fix-ci or implement-change if the user wants a fix

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free