agentleFS
Sign inStart free
mattmirelesmattmireles/gemma-tuner-multimodal/.claude/skills/create-plan/SKILL.md

create-plan

Skill1.5k starsChanged 4 days agoMITView on GitHub

Create an implementation plan for this repo. Use when the user wants a checked-in plan (commonly under `docs/plans/`), wants the work scoped into phases, and expects the plan to be built from the README tree and repo README first, with Context7 only when current external library or framework behavior materially affects the plan. Do not use for implementing the work, informal brainstorming, or lightweight notes.

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 8

    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
  1. Very specific:

    Use this skill to turn a concrete request into a repo-native implementation plan.

    line 10
  2. Distinctive:

    Read references/index.md first.

    line 30
  3. Distinctive:

    Use Context7 only when the plan depends on current library, framework, or API behavior that may have changed.

    line 36
  4. Distinctive:

    If Context7 is insufficient, fall back to official vendor docs.

    line 37
  5. Distinctive:

    Write the first draft to the real target plan file with a clear structure and make it implementation ready:

    line 39
  6. Very specific:

    Optional external review: If scripts/run-cross-agent-plan-review.sh (or a similar checked-in helper) exists, run it on the saved draft, …

    line 45
  7. Distinctive:

    no missing policy that an implementer would have to invent

    line 47
  8. Distinctive:

    no fake certainty where the repo context is incomplete

    line 48
  9. Distinctive:

    no implementation work performed while planning

    line 49
  10. Distinctive:

    no unresolved reviewer finding silently ignored without explanation

    line 50

“Common” is measured: kept by at least 6 in 10 of the 35 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

Create Plan

Purpose

Use this skill to turn a concrete request into a repo-native implementation plan. The output is a real plan file checked into git (typically under docs/plans/...—follow existing layout if present). README/plans/ is gitignored in this repo for local-only drafts; use a tracked path unless the user explicitly wants a private scratch plan.

Use When

  • The work is large enough to need a real implementation plan.
  • The user wants a plan written into the repo.
  • The implementation needs phases, verification steps, and concrete files.

Do Not Use When

  • The user wants direct implementation instead of planning.
  • The request is still too vague to scope honestly.
  • The output should be a note, scratchpad, or brainstorm instead of a plan.

Procedure

  1. Read references/index.md first.
  2. Gather repo context in this order:
    • README.md, README/guides/README.md, and docs/CONTRIBUTING.md
    • README/notes/debug-notes.md when the work ties to past incidents
    • optional README/skills/ when the work interacts with agent/plan conventions
    • neighboring plans in the target plan subtree for local style
  3. Use Context7 only when the plan depends on current library, framework, or API behavior that may have changed.
  4. If Context7 is insufficient, fall back to official vendor docs.
  5. Choose the most specific existing subdirectory under the plan root that fits the work. If none exists yet, create a minimal sensible path (avoid noisy folder sprawl).
  6. Write the first draft to the real target plan file with a clear structure and make it implementation ready:
    • concrete phases
    • specific files where knowable
    • verification per phase
    • hard requirements
    • rollback or kill switch when relevant
  7. Optional external review: If scripts/run-cross-agent-plan-review.sh (or a similar checked-in helper) exists, run it on the saved draft, integrate findings, and move unresolved disagreements into Open Questions. If no such script exists, skip this step and do a careful self-audit instead.
  8. Audit the final plan before stopping:
    • no missing policy that an implementer would have to invent
    • no fake certainty where the repo context is incomplete
    • no implementation work performed while planning
    • no unresolved reviewer finding silently ignored without explanation

Canonical Docs

Read references/index.md first.

Handoff Rules

  • Hand off to execute-plan only after the plan is checked in and the user wants implementation.
  • Hand off to a domain skill only if the planning request narrows into a domain-specific technical question that must be answered before the plan can be completed.

Download now (ZIP)

  • Other versions37 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 37

    1. ComposioHQ/awesome-codex-skills★ 17ksame name
    2. composio-community/awesome-codex-skills★ 16ksame name
    3. netease-youdao/LobsterAI★ 6.2ksame name
    4. freestylefly/wesight★ 941same name
    5. gittower/git-flow-next★ 458same name
    6. JetBrains/youtrackdb★ 442same name
    7. OpenFn/lightning★ 317same name
    8. dannys-code-corner/incan★ 63same name
    9. DasDigitaleMomentum/opencode-processing-skills★ 60same name
    10. maxedapps/agent-skills★ 59same name

    27 more not listed

    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.

  • Used alongsideProjects with it also use codebase-migrate, support-ticket-triage 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.
    • ComposioHQSkill

      codebase-migrate

      Run large codebase migrations and multi-file refactors. Uses the Composio CLI to coordinate issue tracking, batched PRs, and CI verification while the agent executes the transforms locally across hundreds of files.

      Also in 5 projects that use this

    • ComposioHQSkill

      support-ticket-triage

      Triage customer support tickets/emails/chats into categories, priority, and next action; draft responses and create reproducible steps; use for Zendesk/Intercom/Help Scout exports or pasted threads.

      Also in 5 projects that use this

    • corticalstackSkill

      iterate-plan

      Revise an existing implementation plan in flow/plans/ based on feedback, researching when needed. Explicit-only; run only when invoked via /iterate-plan or explicitly asked.

      Also in 4 projects that use this

    • hebertzhuSkill

      develop-web-game

      Use when building or iterating on a web game and you need a tight implement-test-observe loop; prefer the bundled Playwright client, inspect screenshots and text state, and validate every meaningful change before moving on.

      Also in 3 projects that use this

    • petestewartSkill

      datadog-logs

      Query Datadog logs via the Logs Search API v2. Use when the user asks to "check the logs", "search logs", "find errors in Datadog", "look up logs for", "show me production logs", "check for errors", "search Datadog", or any request involving log search, error investigation, or production debugging that requires Datadog log data.

      Also in 3 projects that use this

    • +7 more from ComposioHQ
  • In this repository20 other files it gives its agents.

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