maxingaussian/pi-plans/plan-small
Claude Code and agent skill by maxingaussian/pi-plans
- community
Checking that the SKILL.md file is still in the repository.
Create a small Pi plan before implementation. Use for small scoped repo changes needing 1 to 3 planning questions and one reviewer refinement pass; exclude direct implementation-only, factual/explanation, trivial command-only, or explicit no-plan requests.
Install
npx vskill@latest install maxingaussian/pi-plans/plan-smallSKILL.md
Plan Small
Use this skill when the user wants a compact plan before a repository change.
Pi Setup
Read ../../references/pi-planning-workflow.md and ../../references/state-and-config.md — both normative — and follow their setup, state, language, and reviewer rules. Initialize workspace state with the plans tool (action: "init"); state lives in .git/pi-plans/. Ask every question with the ask_choice tool; run the refinement round with the refine tool.
Depth Contract
- Inspect the target Git repo read-only before the first product question.
- Ask 1 to 3 planning questions via
ask_choice(recommended option first; the tool addsOthersecond-last andAuto-completelast). Every option you write carries adescriptionof✓ <advantage> / ✗ <drawback>in the configured language, kept terse — the user chooses by weighing what each option gains against what it costs. With 2-3 ready questions, batch them into ONEquestions: [...]form call; a single question uses the classicquestionform. - Batch protocol (0.4.0): when a round has several questions, submit them together as one
ask_choicecall withquestions: [...](2-8 items, recommended option first per question) — the tool opens one tabbed multiple-choice form with a submit page instead of asking one at a time. After the batch returns, think about the answers, then follow up in later calls (batch again for 2+ related follow-ups; singlequestionfor one).Escon the form returns the answered subset as partial answers — continue with what you got and re-ask only what matters. The final scope confirmation and the execution handoff are ALWAYS single-question calls withautoComplete: false; batches reject those questions. - Ask the final scope confirmation, then write
PLAN_v1.mdunder the artifact root (normally the configured workspace root, default./.git/pi-plans/plans/YYYY-MM-DD-topic/) per../../references/plan-artifact-template.md. - After each plan version, ask the merged accept/execute question via
ask_choicewithautoComplete: false— never runrefineunless the user picked another round at that question. Default: exactly one reviewer round (findings plus up to five questions); afterwards the recommended option is✓ Accept & execute nowin the merged accept/execute question (ask_choice withautoComplete: false: ✓ Accept & execute now / Accept, don't execute yet / another round), then theexecute_plantool.
Fit
A few local files, clear ownership, low risk, focused verification. Escalate to plan-normal for external API semantics, dependency behavior, compatibility research, cross-module design, or more than three meaningful decisions.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/plan-small/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/maxingaussian/pi-plans/plan-small)