writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
Skill by tim-hub
Chalk Labs
Need help deploying writing-plans?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tim-hub-writing-plans
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/writing-plans
What's inside
- Skill name
writing-plans- Description
- Use when you have a spec or requirements for a multi-step task, before touching code
- License
- MIT
- Instructions
- 21 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- plan-document-reviewer-prompt.md
SKILL.md (first lines)
# Writing Plans Write for an engineer who knows the language but nothing about this codebase or problem domain. Every step carries what they need: exact paths, real code, real test code, the command to run and the output to expect. 1. Check scope. If the spec spans independent subsystems, write one plan per subsystem; each must produce working, testable software on its own. 2. Map the files before defining tasks — what gets created, what gets modified, what each is responsible for. One responsibility per file. Files that change together live together. Follow the codebase's existing patterns. 3. Draw task boundaries at the smallest unit that carries its own test cycle. Fold setup, config, scaffolding and docs into the task whose deliverable needs them. Split only where a reviewer could reject one task while approving its neighbour. 4. Break each task into 2-5 minute steps: write the failing test, run it and watch it fail, write minimal code, run it and watch it pass, commit. 5. Open the plan with the goal in one sentence, the architecture in two or three, the tech stack, and a Global Constraints section listing project-wide requirements with values copied verbatim from the spec. 6. Give each task a Files block with exact paths, and an Interfaces block naming what it consumes from earlier tasks and what later tasks rely on, with exact signatures. Each task's implementer sees only their own task. 7. Write steps as `- [ ]` checkboxes. Code steps carry the actual code in a fenced block. Verification steps carry the command and its expected output. 8. Save to `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`. 9. Re-read the plan against the spec: every requirement has a task, no placeholders remain, and names and types match across tasks. Never write "TBD", "add error handling", "handle edge cases", "write tests for the above", "similar to Task N", or any reference to a type or function no task defines. Repeat code rather than cross-referencing — tasks get read out of order. Terminal state: invoke executing-plans. Depth: plan-document-reviewer-prompt.md
From tim-hub/superpowers-slim, MIT.
More from tim-hub/superpowers-slim
- 0.546score
finishing-a-development-branch
tim-hub
Use when implementation is complete and tests pass, and the work needs integrating
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
receiving-code-review
tim-hub
Use when code review feedback has arrived, before implementing the suggestions
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
requesting-code-review
tim-hub
Use when work is implemented and needs review before merging
SkillBFreshness: B★ 1Claude Code +9 - 0.521score
systematic-debugging
tim-hub
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
SkillBFreshness: B★ 1Claude Code +9 - 0.521score
verification-before-completion
tim-hub
Use when about to claim work is complete, fixed, or passing, before committing or creating a PR
SkillBFreshness: B★ 1Claude Code +9 - 0.516score
executing-plans
tim-hub
Use when you have a written implementation plan to execute task by task
SkillBFreshness: B★ 1Claude Code +9 - 0.514score
brainstorming
tim-hub
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 3, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/tim-hub/superpowers-slim
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tim-hub
- 0.546score
finishing-a-development-branch
tim-hub
Use when implementation is complete and tests pass, and the work needs integrating
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
receiving-code-review
tim-hub
Use when code review feedback has arrived, before implementing the suggestions
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
requesting-code-review
tim-hub
Use when work is implemented and needs review before merging
SkillBFreshness: B★ 1Claude Code +9 - 0.530score
Body Fat Calculator
tim-hub
Estimates body fat percentage with the US Navy method and keeps your values in the browser.
ArtifactNo sign-upIn-browser★ 1health lifestyle - 0.521score
verification-before-completion
tim-hub
Use when about to claim work is complete, fixed, or passing, before committing or creating a PR
SkillBFreshness: B★ 1Claude Code +9 - 0.521score
systematic-debugging
tim-hub
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get writing-plans running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
writing-plans skill. Agent Mart. https://agentmart.dev/skills/tim-hub-writing-plans (last updated 2026-10-24)