agentleFS
fnayoufnayou/dotfiles/.claude/skills/create-plan/SKILL.md

create-plan

Skill2 starsChanged 5 months agoMITView on GitHub

Produces a numbered implementation plan under docs/plans/. Locate and read the relevant PRD under docs/prd/. Confirm goals, non-goals, safety requirements, and acceptance criteria. Locate and read the relevant architecture document under docs/architecture/. Confirm layout, decisions, and risks. Break the implementation into the smallest safe, individually verifiable steps. Each task must: Do not group multiple distinct changes into one task. For each task, list: List any commands that will be run. Flag dangerous commands explicitly. For each task, specify a safe…

39 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects 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

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 37 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not group multiple distinct changes into one task.

    line 31
  2. Distinctive:

    Write the plan to a numbered file:

    line 73
  3. Distinctive:

    Use the next available number in the sequence.

    line 80

“Common” is measured: kept by at least 6 in 10 of the 37 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

Skill: create-plan

Produces a numbered implementation plan under docs/plans/.

When to use

  • An architecture has been approved and the user is ready to begin implementation.
  • A PRD is approved and the Architect has produced a design.
  • A specific, well-scoped task needs to be broken into safe steps.

Process

Step 1 — Read the PRD

Locate and read the relevant PRD under docs/prd/. Confirm goals, non-goals, safety requirements, and acceptance criteria.

Step 2 — Read the architecture

Locate and read the relevant architecture document under docs/architecture/. Confirm layout, decisions, and risks.

Step 3 — Create ordered tasks

Break the implementation into the smallest safe, individually verifiable steps.

Each task must:

  • Be specific and actionable.
  • Produce a visible, verifiable result.
  • Be safe to stop after if needed.

Do not group multiple distinct changes into one task.

Step 4 — Identify files affected

For each task, list:

  • Files to be created.
  • Files to be modified.
  • Files to be deleted (flag these — requires safety review).

Step 5 — Identify commands needed

List any commands that will be run. Flag dangerous commands explicitly.

Step 6 — Identify validation steps

For each task, specify a safe read-only command or check to verify it completed correctly.

Example:

git status   # Verify only expected files are changed
ls -la stow/common/zsh/   # Verify directory structure is correct

Step 7 — Identify rollback strategy

State how to undo the plan if something goes wrong. Prefer git-based rollback:

git checkout -- <file>    # Undo a specific file change
git reset HEAD~1          # Undo the last commit (before push)

Step 8 — Do not implement or mark Complete

This skill produces a plan only. The Builder implements. Do not create or modify dotfile packages or home directory files.

Set the initial status to Draft. The Planner does not approve plans — that is the user's role after plan review passes. See docs/claude/DOCUMENT-LIFECYCLE.md for all valid statuses and transitions.

Step 9 — Produce the plan document

Write the plan to a numbered file:

docs/plans/0001-bootstrap-claude-operating-layer.md
docs/plans/0002-add-zsh-common-package.md

Use the next available number in the sequence.

Plan document template

# Plan: [Title]

**Number:** 0001
**Status:** Draft | Approved | Complete | Superseded
**Date:** YYYY-MM-DD
**PRD:** [number]
**Architecture:** [number]

## Objective

[One sentence: what this plan achieves]

## Assumptions

- [assumption]

## Ordered Tasks

1. [Task description]
2. [Task description]
3. [Task description]

## Files Affected

- path/to/file — created
- path/to/file — modified

## Safety Checks

- [check before starting]
- [check during execution]

## Validation Commands

```bash
git status

Rollback Strategy

[How to undo if something goes wrong]

Completion Criteria

  • [verifiable condition]
  • [verifiable condition]

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.