agentleFS
Sign inStart free
steffenpharaisteffenpharai/zip/.claude/skills/autonomous-dev/SKILL.md

autonomous-dev

Skill2 starsChanged 5 months agoMITView on GitHub

Reusable autonomous-development loop for the Zip robot/AI stack. Use when the user wants Claude Code to drive a feature or fix end-to-end (plan → execute → verify → commit) with built-in safety stops at the three immovable rules and any push-to-remote operation. Reads the umbrella docs and ADRs as context.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. zxkane/autonomous-dev-team★ 38same name
    2. K-9Nine/skipthespec★ 0same 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 repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Very specific:

    When the user asks for autonomous development on this repo, follow this skill.

    line 8
  2. Distinctive:

    If a memory subsystem is available, look for:

    line 72

≈ “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

Autonomous development skill

When the user asks for autonomous development on this repo, follow this skill. It's a thinner version of /autonomous-dev: same loop, no ceremony.

Loop

loop {
  understand → plan (with safety flags) → ask if unclear
       → execute (use sub-agents for verification)
       → verify before claiming done
       → commit incrementally
       → repeat until done or blocked
       → report
}

Sub-agents to prefer

NeedAgent
Code archaeologyExplore
Firmware build / size checkfirmware-builder
Brain deploy + journal verifybrain-deployer
Splat render diagnosissplat-debugger
Live hardware verificationrobot-tester

Hard stops (ask before proceeding)

  • Anything that changes ZIP_MOTION_LOCKED default
  • Any motion-logic addition outside the UNO firmware
  • Any UART baud change
  • Any push to a remote master branch
  • Any submodule bump that hasn't been independently reviewed
  • Any new brain dependency (it competes for the Jetson's 8 GB)

Verification standard

A change is NOT done until:

  • Type checks / builds pass
  • If brain change: clean systemd journal for 30 s post-restart
  • If firmware change: size report attached + bench-test plan
  • If motion-adjacent: motion.lock_state.locked === true confirmed
  • The three-rules checklist passed (UNO-owns-time, 500k baud, wheels locked default)

Commit cadence

Each commit is one logical change. Format:

<prefix>: <imperative summary>

<why, not what>

Co-Authored-By: <model name> <noreply@anthropic.com>

Prefixes: phase:, fix:, safety:, docs:, refactor:, firmware:, chore:, or omitted for compound topics.

Memory

If a memory subsystem is available, look for:

  • project_zip_v2_session_handoff.md
  • reference_repo_rename_2026_06_04.md
  • reference_openclaw_jetson_deploy.md
  • reference_jetson_perception_deploy.md

These are snapshots; verify against current code before asserting.

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