popup-studio-ai/bkit-claude-code/pdca
Claude Code and agent skill by popup-studio-ai/bkit-claude-code
- community
Checking that the SKILL.md file is still in the repository.
Unified PDCA cycle management — plan, design, do, analyze, iterate, report. PDCA runs per-feature (9-phase: pm→plan→design→do→check→act→qa→report→archive); for multi-feature scope/budget grouping use /sprint (v2.1.13, 8-phase container that may host PDCA cycles inside). Triggers: pdca, plan, design, analyze, report, status, next, iterate
Install
npx vskill@latest install popup-studio-ai/bkit-claude-code/pdcaSKILL.md
PDCA Skill
Unified Skill for managing PDCA cycle. Supports the entire Plan → Design → Do → Check → Act flow.
Arguments
| Argument | Description | Example | |
|---|---|---|---|
pm [feature] | Run PM Agent Team analysis (pre-Plan) | /pdca pm user-auth | |
plan [feature] | Create Plan document | /pdca plan user-auth | |
design [feature] | Create Design document | /pdca design user-auth | |
do [feature] | Do phase guide (start implementation) | /pdca do user-auth | |
analyze [feature] | Run Gap analysis (Check phase) | /pdca analyze user-auth | |
iterate [feature] | Auto improvement iteration (Act phase) | /pdca iterate user-auth | |
qa [feature] | Run QA phase (L1-L5 tests) | /pdca qa user-auth | |
report [feature] | Generate completion report | /pdca report user-auth | |
archive [feature] | Archive completed PDCA documents | /pdca archive user-auth | |
cleanup [feature] | Cleanup archived features from status | /pdca cleanup | |
team [feature] | Start PDCA Team Mode (requires Agent Teams) | /pdca team user-auth | |
team status | Show Team status | /pdca team status | |
team cleanup | Cleanup Team resources | /pdca team cleanup | |
status | Show current PDCA status | /pdca status | |
next | Guide to next phase | /pdca next |
Action Details
pm (PM Analysis Phase)
Run PM Agent Team for product discovery and strategy analysis before Plan phase.
- Call pm-lead Agent (orchestrates 4 sub-agents)
- pm-lead runs Phase 1: Context Collection (project info, git history)
- pm-lead runs Phase 2: Parallel Analysis (3 agents simultaneously)
- pm-discovery: Opportunity Solution Tree (Teresa Torres)
- pm-strategy: Value Proposition (JTBD 6-Part) + Lean Canvas
- pm-research: 3 Personas + 5 Competitors + TAM/SAM/SOM
- pm-lead runs Phase 3: PRD Synthesis via pm-prd agent
- Beachhead Segment (Geoffrey Moore) + GTM Strategy
- 8-section PRD generation
- Output PRD to
docs/00-pm/{feature}.prd.md - Create Task:
[PM] {feature} - Update
.bkit/state/pdca-status.json: phase = "pm" - Guide user to next step:
/pdca plan {feature}
Output Path: docs/00-pm/{feature}.prd.md
Requirements:
- Agent Teams enabled:
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 - Project level: Dynamic or Enterprise (Starter not supported)
plan (Plan Phase)
- Template Loading: Read
${CLAUDE_PLUGIN_ROOT}/templates/plan.template.mdto understand the required Plan document structure and sections. Use this template's sections as your document outline. This is MANDATORY — do not generate Plan documents from memory or assumptions. - PRD Auto-Reference: Check if
docs/00-pm/{feature}.prd.mdexists
- If found: Read PRD and use as context for Plan document (improves quality significantly)
- If not found: Proceed normally (tip: run
/pdca pm {feature}first for better results)
- Check if
docs/01-plan/features/{feature}.plan.mdexists - If not, create based on
plan.template.md - If exists, display content and suggest modifications
- Checkpoint 1 — Requirements Confirmation: Present understanding of the feature (problem, scope, constraints) and use AskUserQuestion: "요구사항 이해가 맞나요? 빠진 건 없나요?" Wait for user confirmation before proceeding.
- Checkpoint 2 — Clarifying Questions: Identify underspecified elements (edge cases, error handling, integration points, compatibility). Present organized question list. Wait for answers before generating the document.
- Generate Plan document with user-confirmed requirements
- Complete predecessor Task first: If a
[PM] {feature}Task exists and is stillin_progress, use TaskList to find it and TaskUpdate it tostatus: "completed"before creating the Plan Task (see Phase Transition Rule). Then Create Task:[Plan] {feature} - Update
.bkit/state/pdca-status.json: phase = "plan" - Write
## Executive Summaryat document top with 4-perspective table (Problem/Solution/Function UX Effect/Core Value), each 1-2 sentences - Context Anchor Generation: After generating Plan document, extract Context Anchor (WHY/WHO/RISK/SUCCESS/SCOPE) from Executive Summary, Requirements, and Risk sections. Write as
## Context Anchortable between Executive Summary and Section 1. This anchor propagates to Design/Do documents for cross-session context continuity. - MANDATORY: After completing the document, also output the Executive Summary table in your response so the user sees it immediately without opening the file
Output Path: docs/01-plan/features/{feature}.plan.md
Tip: For features with ambiguous requirements or multiple implementation approaches,use/plan-plus {feature}instead. Plan Plus adds brainstorming phases (intent discovery,alternatives exploration, YAGNI review) before document generation for higher-quality plans.
design (Design Phase)
- Template Loading: Read
${CLAUDE_PLUGIN_ROOT}/templates/design.template.mdto understand the required Design document structure. Use this template's sections as your document outline. This is MANDATORY — do not generate Design documents from memory or assumptions. - Verify Plan document exists (required - suggest running plan first if missing)
- Read Plan document to understand requirements and scope
- PRD Context Loading: Check if
docs/00-pm/{feature}.prd.mdexists. If found, read the Executive Summary and Beachhead/GTM sections to inform architecture decisions with market context. This prevents strategic context loss at the Plan→Design handoff. - Context Anchor Embed: Copy Plan's
## Context Anchortable to Design document top (between header metadata and ## 1. Overview). If Plan has no Context Anchor (legacy), skip this step gracefully. - Generate 3 Architecture Options (inspired by feature-dev Phase 4):
- Option A — Minimal Changes: Least modification, maximum reuse of existing code. Fast but potentially coupled.
- Option B — Clean Architecture: Best separation of concerns, most maintainable. More files, more refactoring.
- Option C — Pragmatic Balance: Good boundaries without over-engineering. Recommended default.
- Present comparison table with trade-offs (complexity, maintainability, effort, risk)
- Checkpoint 3 — Architecture Selection: Use AskUserQuestion: "3가지 설계안 중 어떤 걸 선택하시겠습니까?" Include recommendation. Wait for user selection.
- Create
docs/02-design/features/{feature}.design.mdusing selected architecture - Use
design.template.mdstructure + reference Plan content - Session Guide Generation: Analyze Design's
## 11. Implementation Guidestructure to generate Module Map and Recommended Session Plan. Add as### 11.3 Session Guidewithin Implementation Guide section. This enables/pdca do {feature} --scope module-Nfor multi-session incremental implementation. - Design Anchor Integration (Pencil MCP): If the feature involves UI and Pencil MCP is available:
- Suggest: "UI 컨셉 페이지를 1-2개 먼저 만든 후
/design-anchor capture {feature}로 디자인 토큰을 잠그세요" - If Design Anchor already exists (
docs/02-design/styles/{feature}.design-anchor.md), embed it in the Design document as## Design Anchorsection - This ensures design tokens (colors, typography, spacing) are locked before implementation
- Complete predecessor Task first: Use TaskList to find the
[Plan] {feature}Task (and any earlier phase Task for this feature stillin_progress) and TaskUpdate each tostatus: "completed"— this resolves theblockedBychain and prevents stale phase status from leaking into prompt context (see Phase Transition Rule). Then Create Task:[Design] {feature}(blockedBy: Plan task) - Update
.bkit/state/pdca-status.json: phase = "design"
Output Path: docs/02-design/features/{feature}.design.md
do (Do Phase)
- Verify Design document exists (required)
- Read Design document FULLY (read the entire document, not just a summary. This is critical — full context reload ensures each session starts with complete architectural context)
- Full Upstream Context Loading (Phase 2+3): Load the COMPLETE upstream document chain:
- Read PRD (
docs/00-pm/{feature}.prd.md) — extract WHY context (JTBD, value proposition, market positioning) - Read Plan (
docs/01-plan/features/{feature}.plan.md) — extract Context Anchor, Success Criteria, Requirements - This ensures implementation decisions are guided by strategic intent from PRD→Plan→Design, not just the Design spec
- Decision Record Chain Display: Extract and display key decisions from PRD→Plan→Design as a unified chain. Format:
`` 📋 Decision Record Chain [PRD] Target: {market/user segment} — {rationale} [Plan] Architecture: {selected option} — {rationale} [Design] State Mgmt: {selected approach} — {rationale} ``
- Success Criteria Tracking: Extract Success Criteria from Plan document. Display as implementation checklist — each criterion must be addressed during implementation. Mark criteria that are covered by the current --scope.
- Parse --scope parameter: If arguments contain
--scope <value>, extract module list (comma-separated scope keys). Match against Design's Session Guide Module Map. Filter implementation items to show only matching modules. - Display Context Anchor: Show the Context Anchor table from Design document header. Format: "📌 Context Anchor" + WHY/WHO/RISK/SUCCESS/SCOPE table. This reminds the user WHY we're building this feature.
- Session Guide Display:
- If no --scope: Show full Module Map from Design + recommend session split + proceed with full implementation guide
- If --scope provided: Show only the selected modules' implementation items
- Summarize implementation scope:
- Files to create: N
- Files to modify: M
- Estimated changes: ~X lines
- Checkpoint 4 — Implementation Approval: Present scope summary and use AskUserQuestion: "이 범위로 구현을 시작해도 되겠습니까?" DO NOT START IMPLEMENTATION WITHOUT USER APPROVAL.
- After approval, provide implementation guide based on
do.template.md - Reference implementation order from Design document (filtered by --scope if provided)
- Code Comment Convention (Phase 3): During implementation, add Design reference comments for key architectural decisions:
- At module/file level:
// Design Ref: §{section} — {decision rationale} - At critical logic:
// Plan SC: {success criteria being addressed} - These comments create traceable links from code back to design decisions
- Complete predecessor Task first: Use TaskList to find the
[Design] {feature}Task (and any earlier phase Task for this feature stillin_progress) and TaskUpdate each tostatus: "completed"— this resolves theblockedBychain and prevents stale phase status from leaking into prompt context (see Phase Transition Rule). Then Create Task:[Do] {feature}(blockedBy: Design task) - Update
.bkit/state/pdca-status.json: phase = "do"
--scope Parameter:
Guide Provided:
- Context Anchor (WHY/WHO/RISK/SUCCESS/SCOPE)
- Session scope (filtered or full)
- Implementation order checklist
- Key files/components list
- Dependency installation commands
analyze (Check Phase)
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/pdca/SKILL.md
Popularity
- Repository stars
- 583
- Repository forks
- 148
- 7-day trend score
- 32
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 16 Mar 2026, 7 months ago.
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/popup-studio-ai/bkit-claude-code/pdca)