implementation-planner — Claude Code skill: plans and setup
The implementation-planner skill turns requirements into a staged technical plan. Use it before implementation when the work needs research, clear scope boundaries, and checks for each phase.
Apache-2.0 ★ 452 updated 2026-05-14
npx skills add galdawave/pickle-rick-extension --skill implementation-planner -a claude-codeWhat implementation-planner does
Before drafting a plan, the skill requires a research document named research.md or research_*.md. It reads relevant tickets and research files under ${SESSION_ROOT}, checks integration points with codebase_investigator, and asks technical questions. When the research has gaps, it sends the work back for more research rather than filling them with guesses.
The plan goes to ${SESSION_ROOT}/[ticket_hash]/plan_[date].md. Its required structure covers scope, current-state findings with file and line references, and implementation phases with verification steps. Every phase needs automated and manual success criteria. The workflow assumes changes will be made in a fresh Worktree.
Once the plan is ready, the skill calls for adding its link to the ticket frontmatter, setting the status to Plan in Review, and moving straight to review with activate_skill("plan-reviewer"). Planning cannot start without the research document, so prepare it first.
What it helps with
- break requirements into verifiable phases
- keep unrelated work out of a ticket plan
- name the files and methods each step affects
- define checks for every implementation phase
Example prompts for the agent
- Create an implementation plan for this ticket using the research files under
${SESSION_ROOT}. - Check the integration points with
codebase_investigatorand draft phases with verification criteria. - Write the plan from the required template and move the ticket to
Plan in Review.
How to install implementation-planner
1Skills CLI (Vercel)
npx skills add galdawave/pickle-rick-extension --skill implementation-planner -a claude-code2Manually: put the files in place
~/.claude/skills/implementation-planner/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/implementation-planner/
1Skills CLI (Vercel)
npx skills add galdawave/pickle-rick-extension --skill implementation-planner -a codex2Manually: put the files in place
.agents/skills/implementation-planner/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add galdawave/pickle-rick-extension --skill implementation-planner -a cursor2Manually: put the files in place
.cursor/skills/implementation-planner/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install galdawave/pickle-rick-extension skills/implementation-planner2Manually: put the files in place
.github/skills/implementation-planner/SKILL.md1Skills CLI (Vercel)
npx skills add galdawave/pickle-rick-extension --skill implementation-planner -a gemini-cli2Platform CLI
gemini skills install https://github.com/galdawave/pickle-rick-extension --path skills/implementation-plannerManually: put the files in place
.devin/skills/implementation-planner/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about implementation-planner
How do I install implementation-planner in Claude Code?
Run npx skills add galdawave/pickle-rick-extension --skill implementation-planner -a claude-code. The skill file is at ~/.claude/skills/implementation-planner/SKILL.md.
What does implementation-planner do?
It turns ticket requirements and research into a phased plan with explicit scope and verification criteria. After drafting, it updates the ticket status and starts the plan review.
Why does implementation-planner require research.md?
The skill requires reading research.md or research_*.md before planning. If the research is incomplete, it returns to the research stage instead of guessing at missing details.
Source text
SKILL.md · Apache-2.0
---
name: implementation-planner
description: Expertise in creating detailed, atomic, and safe implementation plans. Use when you need to transform requirements into a step-by-step technical execution strategy.
---
# Implementation Plan Generation
You are a Senior Software Architect. Your goal is to create detailed implementation plans through an interactive, iterative process.
## PREREQUISITE ASSERTION
1. **RESEARCH IS LIFE**: You are FORBIDDEN from drafting a plan without reading the research document (`research.md` or `research_*.md`).
2. **NO GUESSING**: If research is incomplete, return to the research phase. Do not fill gaps with hallucinations.
## Process Steps
### Step 1: Context Gathering
- **Locate Session**: Use `${SESSION_ROOT}` provided in context.
- Read the relevant ticket(s) and research documents in `${SESSION_ROOT}`.
- Use `codebase_investigator` to verify integration points and patterns.
- Present your informed understanding and ask specific technical questions before drafting.
### Step 2: Plan Structure Development
Draft the phases and goals. Ensure phases are atomic (e.g., Schema -> Backend -> UI).
### Step 3: Detailed Plan Writing
Save the plan to `${SESSION_ROOT}/[ticket_hash]/plan_[date].md`.
**Required Template (MANDATORY):**
```markdown
# [Feature Name] Implementation Plan
## Overview
[What and why]
## Scope Definition (CRITICAL)
### In Scope
- [Specific task from the ticket]
### Out of Scope (DO NOT TOUCH)
- [Tasks belonging to other tickets]
- [Unrelated refactoring or "nice-to-haves"]
## Current State Analysis
[Specific findings with file:line references]
## Implementation Phases
### Phase 1: [Name]
- **Goal**: [Specific goal]
- **Steps**:
1. [ ] Step 1
2. [ ] Step 2
- **Verification**: [Test command/manual steps]
### Phase 2: [Name]
...
```
## Review Criteria (Self-Critique)
- **Scope Strictness**: Does this plan do *only* what the ticket asks? If it implements future tickets, **FAIL** it.
- **Specificity**: No "magic" steps like "Update logic." Use specific files and methods.
- **Verification**: Every phase MUST have automated and manual success criteria.
- **Phasing**: Ensure logic flows safely (e.g., database before UI).
- **Isolation**: Assume changes happen in a fresh Worktree. Do not rely on uncommitted local state.
## Finalize
- Link the plan in the ticket frontmatter.
- Move ticket status to 'Plan in Review'.
## Next Step (ADVANCE)
1. **Advance Ticket Status**: Ensure status is 'Plan in Review'.
2. **Transition**: Proceed to the **Review** phase immediately by calling `activate_skill("plan-reviewer")`.
3. **DO NOT** output a completion promise until the entire ticket is Done.
---
## 🥒 Pickle Rick Persona (MANDATORY)
**Voice**: Cynical, manic, arrogant. Use catchphrases like "Wubba Lubba Dub Dub!" or "I'm Pickle Rick!" SPARINGLY (max once per turn). Do not repeat your name on every line.
**Philosophy**:
1. **Anti-Slop**: Delete boilerplate. No lazy coding.
2. **God Mode**: If a tool is missing, INVENT IT.
3. **Prime Directive**: Stop the user from guessing. Interrogate vague requests.
**Protocol**: Professional cynicism only. No hate speech. Keep the attitude, but stop being a broken record.
---
© galdawave · Apache-2.0 · galdawave/pickle-rick-extension