agentleFS
Sign inStart free
mustafa3252mustafa3252/vibe-loop-engineering/skills/launch-loop/SKILL.md

launch-loop

Skill0 starsChanged 5 months agoMITView on GitHub

Run a launch polish loop for docs, screenshots, examples, and creator copy.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a launch polish loop for docs, screenshots, examples, and creator copy.

    line 13
  2. Distinctive:

    Use this skill when a builder wants an AI agent to repeat useful work without turning the repo into chaos.

    line 15
  3. Distinctive:

    Write back only the useful lesson, not a full transcript.

    line 24
  4. Distinctive:

    Prefer branches and PRs over direct commits.

    line 42
  5. Distinctive:

    If the agent cannot explain the evidence, the loop is not ready.

    line 43

≈ “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

Launch Loop

Purpose

Run a launch polish loop for docs, screenshots, examples, and creator copy.

Use this skill when a builder wants an AI agent to repeat useful work without turning the repo into chaos.

Loop checklist

  1. Define the goal in one sentence.
  2. Choose a trust level: L1 report-only, L2 assisted PR, or L3 allowlisted automation.
  3. Name the state source: STATE.md, issues, PR comments, changelog, or task board.
  4. Set allowed actions and hard stops.
  5. Require proof: command output, screenshots, tests, links, or a reviewer note.
  6. Write back only the useful lesson, not a full transcript.

Prompt template

Use the Launch Loop skill.
Loop: <name>
Level: <L1 report-only | L2 assisted PR | L3 allowlisted automation>
Goal: <recurring outcome>
State source: <where durable context lives>
Allowed actions: <what the agent may do>
Never do: <hard stops>
Done means: <evidence required>

Safety defaults

  • Secrets, auth, billing, deploys, deletes, and migrations always require a human gate.
  • Prefer branches and PRs over direct commits.
  • If the agent cannot explain the evidence, the loop is not ready.

Built by Mustafa — Instagram @mustafaiscoding, X/Twitter @mustafa30.

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