autonomous-skill
Skill18 starsChanged 7 months agoMITView on GitHub
Use when user wants to execute long-running tasks. Trigger phrases: "autonomous", "自主執行", "long-running task".
3 other projects use a version of this.
Adopted by
Most recently taken up by
- andrasp/claude-code-flowtheir own version, first seen Oct 20, 2026
- allanninal/claude-code-skillstheir own version, first seen Oct 17, 2026
- myysophia/codex-configtheir own version, first seen Oct 8, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- myysophia/codex-config★ 195same name
- allanninal/claude-code-skills★ 1same name
- andrasp/claude-code-flow★ 1same 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 repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
6
Distinctive
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
- Distinctive: line 28
Commit after meaningful progress so the work can resume safely later.
- Distinctive: line 31
Use 10-30 concrete checkbox items.
- Distinctive: line 33
Prefer outcome-based tasks, not vague reminders.
- Distinctive: line 35
If a task is blocked, add a new checkbox for the fallback path instead of stalling.
- Very specific: line 38
Read task_list.md and progress.md.
- Distinctive: line 43
Commit with a descriptive message before ending the session.
- Very specific: line 46
Use progress.md to capture:
- Distinctive: line 54
Start: "Please use autonomous skill to [description]"
“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.
Files
Autonomous Skill
Execute complex tasks across multiple sessions without losing context.
Directory Structure
.autonomous/<task-name>/
├── task_list.md # Tasks with checkboxes
├── progress.md # Session notes / blockers / decisions
└── logs/ # Optional command output or runner logsWhen To Use
- Multi-hour implementation work
- Tasks that naturally decompose into many small checkpoints
- Work that may require retries, pauses, or multiple Claude sessions
Core Rules
- Break the work into small, testable checklist items.
- Finish one item completely before moving to the next.
- Record decisions, blockers, and retries in
progress.md. - Re-run relevant tests before marking a step done.
- Commit after meaningful progress so the work can resume safely later.
Task List Best Practices
- Use 10-30 concrete checkbox items.
- Each item should be completable in roughly 5-15 minutes.
- Prefer outcome-based tasks, not vague reminders.
- Include setup, implementation, validation, and cleanup steps.
- If a task is blocked, add a new checkbox for the fallback path instead of stalling.
Session Workflow
- Read
task_list.mdandprogress.md. - Pick the first unfinished checkbox.
- Implement only the current slice of work.
- Validate the change with the existing test or verification flow.
- Mark the checkbox done and append a short progress note.
- Commit with a descriptive message before ending the session.
Handoff Notes
Use progress.md to capture:
- what changed
- what remains
- commands/tests already run
- known risks or assumptions
- exact blocker details if something failed
Usage
- Start: "Please use autonomous skill to [description]"
- Continue: "Continue the autonomous task [task-name]"
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
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.

