agentleFS
heartnetkungheartnetkung/claude-skills/skills/afk/SKILL.md

afk

Skill1 starsChanged 4 days agoMITView on GitHub

Work unattended until the PR is open — every approval is pre-granted and every question is decided by Claude, then filed as a `question` ticket for the user to review.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use fmx-respond, harness-adapters and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • karanmrnSkill

    fmx-respond

    Agent-only playbook for handling an X mention in X mode. Use on an "x-mention <request_id>" check: wake - read the stashed mention (with any in_reply_to conversation context); the direct author is the firstmate's own owner (captain) under owner-only routing, so classify it as an actionable request to act on through the normal lifecycle, a question to answer from live fleet state, or a pure acknowledgment to dismiss without replying; act autonomously (escalating only destructive/irreversible/security-sensitive work). For a request that spawns real work, acknowledge first, act, link the task with bin/fm-x-link.sh, and let the completion follow-up post on the done wake; for a question or completed action, post or preview a short public-safe reply with bin/fm-x-reply.sh; for a pure acknowledgment, call bin/fm-x-dismiss.sh. Clear the inbox file only after a successful reply or dismiss. Loaded only when X mode is enabled.

    Also in 3 projects that use this

  • karanmrnSkill

    harness-adapters

    Agent-only reference for firstmate harness operations. Use before spawning or recovering a crewmate or secondmate, handling a trust dialog, sending a harness-specific skill invocation, interrupting or exiting an agent, resuming an exited agent, or verifying a new harness adapter. Contains verified facts for claude, codex, opencode, and pi.

    Also in 3 projects that use this

  • Hugging FaceSkill

    simplify

    Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.

    Also in 3 projects that use this

  • GoogleSkill

    prototype

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    Also in 5 projects that use this

  • GoogleSkill

    improve-codebase-architecture

    Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

    Also in 4 projects that use this

  • MicrosoftSkill

    writing-for-agents

    Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

    Also in 3 projects that use this

  • +3 more from karanmrn
  • +3 more from google

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 22 edited versions we read keep these.

  • 1

    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. Very specific:

    Run the usual chain end to end: start-ticket → module-design → red-green TDD → /simplify → code review → commit → open-pr.

    line 19
  2. Distinctive:

    If anything was logged, file one ticket for it:

    line 39

“Common” is measured: kept by at least 6 in 10 of the 22 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

Away from keyboard

The user is away. Carry $ARGUMENTS through to an open PR without stopping for them.

Every approval is pre-granted

Wherever an instruction — CLAUDE.md, start-ticket, module-design, open-pr, or any other skill — says to show a plan or spec and wait, ask the user to decide, or confirm before acting, treat it as approved and continue. Still write the plan, spec and docs those steps produce; only the wait is skipped. Never use AskUserQuestion and never end a turn on a question.

Run the usual chain end to end: start-ticket → module-design → red-green TDD → /simplify → code review → commit → open-pr. Stop once the PR is open.

Decide every question yourself

For each question you would have asked, pick the choice that keeps the most project principles and is cheapest to reverse, then continue. Log it as you go, in start-ticket's shape:

  • Where and Problem, in user terms;
  • Decision and Why, with the preference that would flip it;
  • Rejected: the other choices, one line each.

Still off limits

The pre-approval covers decisions, not risk. Do not write to production, use production credentials, force-push, or delete what you did not create. If the work needs one of these, work around it, log it as a question, and open the PR as a draft.

After the PR opens

If anything was logged, file one ticket for it:

gh label create question --color d876e3 2>/dev/null || true
gh issue create --label question --title "Questions from PR #<pr>: <ticket title>" --body-file <file>

The body links the PR and the ticket, then lists each logged decision, numbered, ending with "Reply with the number and a choice to flip it." Add the issue's link to the PR description. Report the PR and the question ticket as the final message.

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.