agentleFS
ronedgecombronedgecomb/anything/skills/task-plan/SKILL.md

task-plan

Skill1 starsChanged 9 days agoApache-2.0View on GitHub

Create or maintain a concise plan, decision record, and handoff for a task when complexity, collaboration, or continuity benefits from one. Use when the user asks for a plan or when coordinating substantial work across steps or sessions. Supports conversation, project files, and non-code work without requiring Git.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. shawnclybor/clybor-claude-tooling★ 6same name
    2. es6kr/skills★ 2same name
    3. ozzy-labs/gh-tasks★ 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 repository12 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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. Distinctive:

    Use the smallest record that makes the work clear.

    line 9
  2. Very specific:

    When a new file is useful and writing is permitted, use a descriptive name in an appropriate project directory.

    line 14
  3. Distinctive:

    Leave tracking and ignore policy unchanged unless the user or project calls for a change.

    line 16
  4. Distinctive:

    Do not require Git, a branch, a pull request, or a formal specification.

    line 17
  5. Distinctive:

    Use assets/plan-template.md when helpful.

    line 21
  6. Distinctive:

    Add domain-specific sections only when they help, such as a data migration, publication wording, experiment design, or release steps.

    line 31
  7. Distinctive:

    Update the record when a material decision or state changes.

    line 37

≈ “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 plan

Use the smallest record that makes the work clear. Follow the user's requested format and existing project practice. A short task can use a few conversational steps; a task spanning sessions may need a saved plan.

Choose the medium

  • Reuse an existing plan or the project's chosen record location.
  • When a new file is useful and writing is permitted, use a descriptive name in an appropriate project directory. tasks/<task>.md is one option, not a requirement.
  • Without writable files, return the plan as text and identify it as unsaved.
  • Leave tracking and ignore policy unchanged unless the user or project calls for a change. Do not assume a plan must be private, ignored, or committed.
  • Do not require Git, a branch, a pull request, or a formal specification. If a spec is requested or already exists, link to it instead of replacing it.

Record what matters

Use assets/plan-template.md when helpful. Keep only applicable sections:

  • Outcome: the requested result and how to recognize success.
  • Context and constraints: facts, relevant instructions, boundaries, and dependencies.
  • Approach: actionable steps at the right scale, with owners only when work is delegated.
  • Decisions: confirmed answers and their consequences, separated from assumptions and open questions.
  • Progress: completed work, current state, the next step, and actual blockers.
  • Verification: checks or review methods appropriate to the artifact and their observed results.
  • Follow-ups: work outside this task, with a brief finding, evidence or location, and next step. Ask before adding it to an existing tracker unless already authorized; otherwise report it in the conversation without creating a tracker. Listing it does not authorize investigating, implementing, or delegating it.

Add domain-specific sections only when they help, such as a data migration, publication wording, experiment design, or release steps. An interview skill can help clarify decisions but is not a prerequisite.

A plan records intent; it does not grant permission to execute every proposed action.

Keep it current and transferable

Update the record when a material decision or state changes. Preserve the reason for significant revisions without copying the whole conversation.

Give a worker or another session the relevant content and current status. A path is sufficient only when that recipient can actually access it. Otherwise provide a self-contained snapshot or a permitted artifact transfer. Do not assume shared memory or a shared filesystem.

At completion, record the result and checks that actually ran. Identify outstanding decisions and follow-ups. Use a merge or publication status only when that event was part of the task and occurred.

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.