agentleFS
fmindfmind/dot/skills/task-prompts/SKILL.md

task-prompts

Skill13 starsChanged yesterdayMITView on GitHub

Write agent task, delegation, and handoff prompts; resume or compact agy and Claude Code sessions.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write self-contained prompts for an agent without this conversation.

    line 15
  2. Very specific:

    Capture state: check git status --short --branch, completed proof, exact stopping point, remaining work, failed approaches, and key …

    line 20
  3. Very specific:

    Save and verify: write .agents/prompts/<YYYY-MM-DD>-<slug>.md under git rev-parse --show-toplevel (or ~/.agents/prompts/ outside Git), …

    line 22
  4. Very specific:

    Cite, never paste: keep failures and proof gaps.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Task and Continuation Prompts

Write self-contained prompts for an agent without this conversation. agent-frameworks owns embedded application prompts; prefer native resume or compaction via continuation when session state carries over.

Workflow

  1. Choose the mode: fresh task or continuation; lock down outcome, latest corrections, scope, and acceptance criteria.
  2. Capture state: check git status --short --branch, completed proof, exact stopping point, remaining work, failed approaches, and key decision rationales. Before /clear, follow continuation to save and copy the handoff.
  3. Draft non-empty sections: objective, authority, constraints and rejected approaches, verified facts, current state, next step, verification, and return (plus ordered slices only when needed).
  4. Save and verify: write .agents/prompts/<YYYY-MM-DD>-<slug>.md under git rev-parse --show-toplevel (or ~/.agents/prompts/ outside Git), confirm zero hidden-context assumptions, and report the path.

Task guides

<!-- guides:start -->
  • continuation: Resume, compact, or fork agy and Claude Code sessions, or copy a handoff prompt before /clear.
<!-- guides:end -->

Gotchas

  • Authority travels with the task: separate approved actions from proposals; writing a prompt grants no new permission.
  • Cite, never paste: keep failures and proof gaps; reference path:line instead of copying code or AGENTS.md.
  • Keep .agents/prompts/ untracked: global Git ignore covers it (git check-ignore -v .agents/prompts/x.md); add no repo ignore rule, and commit prompts only on request.

Documentation

  • Companions: clipboard, git-worktree.

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.