writing-plans — for Claude Code writing-plans, informatik-ai-studio, community, for Claude Code, ide skills, SESSION_FILE, flow-plan, ## Task Structure, planning-only, Writing

v1.0.0

À propos de ce Skill

Scenario recommande : Ideal for AI agents that need announce at start: "i'm using the writing-plans skill to create the implementation plan.". Resume localise : Web app for AI-powered software generation, similar to Bolt.new/Lovable # Writing Plans Overview Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. This AI agent skill supports Claude Code, Cursor, and Windsurf

Fonctionnalités

Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Context: This should be run in a dedicated worktree (created by brainstorming skill).
If SESSION FILE parameter is provided: Save to SESSION FILE path (used by flow-plan)
Otherwise: Save to docs/plans/YYYY-MM-DD-<feature-name .md (standalone usage)
Session File Integration:

# Core Topics

efiadm efiadm
[0]
[0]
Updated: 2/20/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 10/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
10/11
Quality Score
55
Canonical Locale
en
Detected Body Locale
en

Scenario recommande : Ideal for AI agents that need announce at start: "i'm using the writing-plans skill to create the implementation plan.". Resume localise : Web app for AI-powered software generation, similar to Bolt.new/Lovable # Writing Plans Overview Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. This AI agent skill supports Claude Code, Cursor, and Windsurf

Pourquoi utiliser cette compétence

Recommandation : writing-plans helps agents announce at start: "i'm using the writing-plans skill to create the implementation plan.". Web app for AI-powered software generation, similar to Bolt.new/Lovable # Writing

Meilleur pour

Scenario recommande : Ideal for AI agents that need announce at start: "i'm using the writing-plans skill to create the implementation plan.".

Cas d'utilisation exploitables for writing-plans

Cas d'usage : Applying Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Cas d'usage : Applying Context: This should be run in a dedicated worktree (created by brainstorming skill)
Cas d'usage : Applying If SESSION FILE parameter is provided: Save to SESSION FILE path (used by flow-plan)

! Sécurité et Limitations

  • Limitation : Every plan MUST start with this header:
  • Limitation : IMPORTANT : Check if MODE parameter is set to planning-only:
  • Limitation : Assume they don't know good test design very well

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is writing-plans?

Scenario recommande : Ideal for AI agents that need announce at start: "i'm using the writing-plans skill to create the implementation plan.". Resume localise : Web app for AI-powered software generation, similar to Bolt.new/Lovable # Writing Plans Overview Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. This AI agent skill supports Claude Code, Cursor, and Windsurf

How do I install writing-plans?

Run the command: npx killer-skills add efiadm/informatik-ai-studio/writing-plans. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for writing-plans?

Key use cases include: Cas d'usage : Applying Announce at start: "I'm using the writing-plans skill to create the implementation plan.", Cas d'usage : Applying Context: This should be run in a dedicated worktree (created by brainstorming skill), Cas d'usage : Applying If SESSION FILE parameter is provided: Save to SESSION FILE path (used by flow-plan).

Which IDEs are compatible with writing-plans?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for writing-plans?

Limitation : Every plan MUST start with this header:. Limitation : IMPORTANT : Check if MODE parameter is set to planning-only:. Limitation : Assume they don't know good test design very well.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add efiadm/informatik-ai-studio/writing-plans. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use writing-plans immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

writing-plans

Install writing-plans, an AI agent skill for AI agent workflows and automation. Review the use cases, limitations, and setup path before rollout.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Writing Plans

Overview

Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.

Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.

Announce at start: "I'm using the writing-plans skill to create the implementation plan."

Context: This should be run in a dedicated worktree (created by brainstorming skill).

Save plans to:

  • If SESSION_FILE parameter is provided: Save to SESSION_FILE path (used by flow-plan)
  • Otherwise: Save to docs/plans/YYYY-MM-DD-<feature-name>.md (standalone usage)

Session File Integration: When invoked from /flow-plan, the SESSION_FILE variable is passed. In this case:

  1. Read the existing session file content
  2. Update the "Implementation Plan" section with the generated plan
  3. Preserve all other sections (Metadata, Summary, Requirements, etc.)
  4. Write back to the same SESSION_FILE path

Bite-Sized Task Granularity

Each step is one action (2-5 minutes):

  • "Write the failing test" - step
  • "Run it to make sure it fails" - step
  • "Implement the minimal code to make the test pass" - step
  • "Run the tests and make sure they pass" - step
  • "Commit" - step

Plan Document Header

Every plan MUST start with this header:

markdown
1# [Feature Name] Implementation Plan 2 3> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. 4 5**Goal:** [One sentence describing what this builds] 6 7**Architecture:** [2-3 sentences about approach] 8 9**Tech Stack:** [Key technologies/libraries] 10 11---

Task Structure

markdown
1### Task N: [Component Name] 2 3**Files:** 4 5- Create: `exact/path/to/file.py` 6- Modify: `exact/path/to/existing.py:123-145` 7- Test: `tests/exact/path/to/test.py` 8 9**Step 1: Write the failing test** 10 11```python 12def test_specific_behavior(): 13 result = function(input) 14 assert result == expected 15```

Step 2: Run test to verify it fails

Run: pytest tests/path/test.py::test_name -v Expected: FAIL with "function not defined"

Step 3: Write minimal implementation

python
1def function(input): 2 return expected

Step 4: Run test to verify it passes

Run: pytest tests/path/test.py::test_name -v Expected: PASS

Step 5: Commit

bash
1git add tests/path/test.py src/path/file.py 2git commit -m "feat: add specific feature"

## Remember
- Exact file paths always
- Complete code in plan (not "add validation")
- Exact commands with expected output
- Reference relevant skills with @ syntax
- DRY, YAGNI, TDD, frequent commits

## Execution Handoff

**IMPORTANT**: Check if `MODE` parameter is set to `planning-only`:
- If `MODE == planning-only`: Skip this entire section. Do NOT offer execution options.
- If `MODE` is not set or is `normal`: Proceed with execution handoff below.

---

**When MODE is NOT planning-only:**

After saving the plan, offer execution choice:

**"Plan complete and saved to `{SESSION_FILE or docs/plans/<filename>.md}`. Two execution options:**

**1. Subagent-Driven (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration

**2. Parallel Session (separate)** - Open new session with executing-plans, batch execution with checkpoints

**Which approach?"**

**If Subagent-Driven chosen:**
- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development
- Stay in this session
- Fresh subagent per task + code review

**If Parallel Session chosen:**
- Guide them to open new session in worktree
- **REQUIRED SUB-SKILL:** New session uses superpowers:executing-plans

---

**When MODE is planning-only (invoked from /flow-plan):**

After saving the plan, output:

**"Plan saved to `{SESSION_FILE}`. Planning complete.**

**Next steps (user action required):**
1. Review the plan in `{SESSION_FILE}`
2. Run `/flow-issue-create {SESSION_FILE}` to create issues
3. Run `/flow-feature-build` to implement"

**Do NOT offer to implement. Do NOT ask "Which approach?"**

Compétences associées

Looking for an alternative to writing-plans or another community skill for your workflow? Explore these related open-source skills.

Voir tout

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

widget-generator

Logo of f
f

Générez des plugins de widgets personnalisables pour le système de flux prompts.chat

flags

Logo of vercel
vercel

Le Cadre de Réaction

138.4k
0
Navigateur

pr-review

Logo of pytorch
pytorch

Tenseurs et réseaux neuronaux dynamiques en Python avec une forte accélération GPU

98.6k
0
Développeur