agentleFS
RayZYunYanRayZYunYan/ClarityStack/.claude/skills/pipeline-review/SKILL.md

pipeline-review

Skill0 starsChanged 23 days agoMITView on GitHub

When a new file appears at outbox/review/pending.md:

13 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

10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    When a new file appears at outbox/review/pending.md:

    line 3
  2. Very specific:

    Read outbox/review/pending.md and present the LinkedIn, Blog, and X previews to the user.

    line 5
  3. Distinctive:

    Wait for the user's response through Claude Dispatch / Cowork.

    line 6
  4. Very specific:

    If the user replies OK or approve:

    line 7
  5. Distinctive:

    If the user replies with edit instructions:

    line 10
  6. Very specific:

    update the relevant files inside outbox/review/pending/

    line 11
  7. Distinctive:

    ask again for approval

    line 13
  8. Very specific:

    If the user replies reject, skip, or cancel (or 拒绝, 跳过, 取消):

    line 14
  9. Distinctive:

    Keep all original source URLs intact.

    line 21
  10. Distinctive:

    Do not publish anything until the user clearly approves.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “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

Pipeline Review Skill

When a new file appears at outbox/review/pending.md:

  1. Read outbox/review/pending.md and present the LinkedIn, Blog, and X previews to the user.
  2. Wait for the user's response through Claude Dispatch / Cowork.
  3. If the user replies OK or approve:
    • copy the files from outbox/review/pending/ into outbox/review/approved/
    • run python automation/pipeline.py --publish-approved
  4. If the user replies with edit instructions:
    • update the relevant files inside outbox/review/pending/
    • regenerate outbox/review/pending.md so the user can review the latest version
    • ask again for approval
  5. If the user replies reject, skip, or cancel (or 拒绝, 跳过, 取消):
    • delete outbox/review/pending.md
    • clear files inside outbox/review/pending/
    • log that the publish was skipped

Notes:

  • Keep all original source URLs intact.
  • Preserve Markdown formatting for outbox/review/pending/blog.md.
  • Do not publish anything until the user clearly approves.

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.