agentleFS
Sign inStart free
ShadysmetoolsShadysmetools/claude-super-workflow/skills/feature-pipeline/SKILL.md

feature-pipeline

Skill0 starsChanged 5 months agoMITView on GitHub

Use when the work is a feature — anything that adds, removes, or significantly changes user-visible behavior. Builds on a staging branch first, then promotes to production by cherry-pick (never a naive 3-way merge of a long-lived branch).

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. notedit/happy-skills★ 340same name
    2. notedit/happy-coding-agent★ 339same name
    3. gaia-research/gaia-skill-tree★ 22same name
    4. vikisingh23/neuraforge-ai★ 4same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Spec + acceptance criteria: Write what "done" means as testable acceptance criteria before any code.

    line 12
  2. Distinctive:

    Full prod gate on the promotion PR: Run all three: code-review bot + diff-analysis + security-review on the accumulated diff.

    line 19
  3. Very specific:

    Close out: Update TEAM-BOARD.md, link both PRs (staging + promotion), record findings, hand off if heavy.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 3 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

Feature pipeline → staging first, promote by cherry-pick

A feature adds, removes, or significantly changes user-visible behavior. Features land on a staging branch first to be validated in a real environment, then promote to main as a separate PR. Promotion is cherry-pick only — a naive 3-way merge of a long-lived branch silently drops work that landed on main after staging last synced.

Work the 10 steps in order.

  1. Deep research. Find the top GitHub repos by stars solving this problem and read how they do it. If a YouTube URL covers the approach, transcribe it. Browse live competitors in a real/headless browser to see the shipped UX. Cite sources.
  2. Spec + acceptance criteria. Write what "done" means as testable acceptance criteria before any code.
  3. PLAN — ASK THE USER. Enter plan mode, present the spec and approach. Do not implement until the user approves.
  4. Branch + build. Branch <your-staging-branch>-<slug> off origin/main. Build the feature. Functions < 50 lines, try/catch on async, typecheck + build clean.
  5. Lightweight staging gate → merge → deploy. On the feature → staging PR, run your diff-analysis tool only (plus self-review). Do not run the full security battery at this stage. On green, squash-merge to the staging branch; it auto-deploys to the staging environment.
  6. QA in a real browser. Exercise the feature against the staging deploy. Capture evidence (screenshots / recording) for each acceptance criterion.
  7. Promote to main by CHERRY-PICK ONLY. First rebase the staging branch on origin/main. Then cherry-pick the feature commits onto a fresh branch off origin/main. Never open a naive 3-way merge PR from the long-lived staging branch — it silently deletes work added to main after the last sync.
    • Cherry-pick conflict rule: prefer the staging branch's behavior + main's config/tokens (env names, IDs, version pins). If the cherry-pick surfaces a pre-existing bug on main, present it to the user as a decision (fix here / separate PR / leave) — do not silently fix it inside the promotion.
  8. Full prod gate on the promotion PR. Run all three: code-review bot + diff-analysis + security-review on the accumulated diff. Paste all three reports inline. Block on any HIGH / auth / data-correctness finding. A human merges to main — the agent does not.
  9. Deploy + monitor. Watch the prod deploy and error stream; confirm the feature is live.
  10. Close out. Update TEAM-BOARD.md, link both PRs (staging + promotion), record findings, hand off if heavy.

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