Supports iterative planning, design, and analysis workflows.

Install

mkdir -p .claude/skills/pdca-lowyshin && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17554" && unzip -o skill.zip -d .claude/skills/pdca-lowyshin && rm skill.zip

Installs to .claude/skills/pdca-lowyshin

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Unified skill for managing the entire PDCA cycle. Auto-triggered by keywords: "plan", "design", "analyze", "report", "status". Replaces legacy /pdca-* commands. Use proactively when user mentions PDCA cycle, planning, design documents, gap analysis, iteration, or completion reports. Triggers: pdca, 계획, 설계, 분석, 검증, 보고서, 반복, 개선, plan, design, analyze, check, report, status, next, iterate, gap, 計画, 設計, 分析, 検証, 報告, 计划, 设计, 分析, 验证, 报告, planificar, diseño, analizar, verificar, planifier, conception, analyser, vérifier, rapport, planen, Entwurf, analysieren, überprüfen, Bericht, pianificare, progettazione, analizzare, verificare, rapporto Do NOT use for: simple queries without PDCA context, code-only tasks.
709 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Create Plan documents for features
  • Generate Design documents based on plans
  • Provide implementation guides for the Do phase
  • Perform gap analysis between design and implementation
  • Automate code fixes and re-verification in Act phase
  • Generate completion reports for features

How it works

The skill manages the PDCA cycle by creating and updating documentation files for each phase. It uses specific agents like 'gap-detector' and 'pdca-iterator' for analysis and iteration.

Inputs & outputs

You give it
/pdca plan user-auth
You get back
docs/01-plan/features/user-auth.plan.md

When to use pdca

  • Planning a new iteration
  • Analyzing project results
  • Reporting on process status

About this skill

PDCA Skill

Unified Skill for managing PDCA cycle. Supports the entire Plan → Design → Do → Check → Act flow.

Arguments

ArgumentDescriptionExample
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
report [feature]Generate completion report/pdca report user-auth
archive [feature]Archive completed PDCA documents/pdca archive user-auth
statusShow current PDCA status/pdca status
nextGuide to next phase/pdca next

Action Details

Output Path: docs/01-plan/features/{feature}.plan.md

Product thinking checkpoint (Gstack office-hours)

Before finalizing the plan, the agent must:

  • Challenge the premises of the request.
  • Ask the user at least one "Taste Decision" question.
  • Consider the "10-star version" vs the "shameful MVP".

design (Design Phase)

  1. Verify Plan document exists (required - suggest running plan first if missing)
  2. Create docs/02-design/features/{feature}.design.md
  3. Use design.template.md structure + reference Plan content
  4. Create Task: [Design] {feature} (blockedBy: Plan task)
  5. Update .bkit-memory.json: phase = "design"

Output Path: docs/02-design/features/{feature}.design.md

do (Do Phase)

  1. Verify Design document exists (required)
  2. Provide implementation guide based on do.template.md
  3. Reference implementation order from Design document
  4. Create Task: [Do] {feature} (blockedBy: Design task)
  5. Update .bkit-memory.json: phase = "do"

Guide Provided:

  • Implementation order checklist
  • Key files/components list
  • Dependency installation commands

analyze (Check Phase)

  1. Verify Do completion status (implementation code exists)
  2. Call gap-detector Agent
  3. Compare Design document vs implementation code
  4. Calculate Match Rate and generate Gap list
  5. Create Task: [Check] {feature} (blockedBy: Do task)
  6. Update .bkit-memory.json: phase = "check", matchRate

Output Path: docs/03-analysis/{feature}.analysis.md

iterate (Act Phase)

  1. Check results (when matchRate < 90%)
  2. Call pdca-iterator Agent
  3. Auto-fix code based on Gap list
  4. Auto re-run Check after fixes
  5. Create Task: [Act-N] {feature} (N = iteration count)
  6. Stop when >= 90% reached or max iterations (5) hit

Iteration Rules:

  • Max iterations: 5 (adjustable via bkit.config.json)
  • Stop conditions: matchRate >= 90% or maxIterations reached

report (Completion Report)

  1. Verify Check >= 90% (warn if below)
  2. Call report-generator Agent
  3. Integrated report of Plan, Design, Implementation, Analysis
  4. Create Task: [Report] {feature}
  5. Update .bkit-memory.json: phase = "completed"

Output Path: docs/04-report/{feature}.report.md

archive (Archive Phase)

  1. Verify Report completion status (phase = "completed" or matchRate >= 90%)
  2. Verify PDCA documents exist (plan, design, analysis, report)
  3. Create docs/archive/YYYY-MM/{feature}/ folder
  4. Move documents (delete from original location)
  5. Update Archive Index (docs/archive/YYYY-MM/_INDEX.md)
  6. Update .pdca-status.json: phase = "archived", record archivedTo path
  7. Remove feature from activeFeatures

Output Path: docs/archive/YYYY-MM/{feature}/

Documents to Archive:

  • docs/01-plan/features/{feature}.plan.md
  • docs/02-design/features/{feature}.design.md
  • docs/03-analysis/{feature}.analysis.md
  • docs/04-report/features/{feature}.report.md

Important Notes:

  • Cannot archive before Report completion
  • Documents are deleted from original location after move (irreversible)
  • Feature name must match exactly

status (Status Check)

  1. Read .bkit-memory.json
  2. Display current feature, PDCA phase, Task status
  3. Visualize progress

Output Example:

📊 PDCA Status
─────────────────────────────
Feature: user-authentication
Phase: Check (Gap Analysis)
Match Rate: 85%
Iteration: 2/5
─────────────────────────────
[Plan] ✅ → [Design] ✅ → [Do] ✅ → [Check] 🔄 → [Act] ⏳

next (Next Phase)

  1. Check current PDCA phase
  2. Suggest next phase guide and commands
  3. Confirm with user via AskUserQuestion

Phase Guide:

CurrentNextSuggestion
Noneplan/pdca plan [feature]
plandesign/pdca design [feature]
designdoImplementation start guide
docheck/pdca analyze [feature]
check (<90%)act/pdca iterate [feature]
check (>=90%)report/pdca report [feature]
reportarchive/pdca archive [feature]

Template References

Templates loaded from imports are used when executing each action:

ActionTemplatePurpose
planplan.template.mdPlan document structure
designdesign.template.mdDesign document structure
dodo.template.mdImplementation guide structure
analyzeanalysis.template.mdAnalysis report structure
reportreport.template.mdCompletion report structure

Task Integration

Each PDCA phase automatically integrates with Task System:

Task Creation Pattern:
┌────────────────────────────────────────┐
│ [Plan] {feature}                       │
│   ↓ (blockedBy)                        │
│ [Design] {feature}                     │
│   ↓ (blockedBy)                        │
│ [Do] {feature}                         │
│   ↓ (blockedBy)                        │
│ [Check] {feature}                      │
│   ↓ (blockedBy, Check < 90%)           │
│ [Act-1] {feature}                      │
│   ↓ (on iteration)                     │
│ [Act-N] {feature}                      │
│   ↓ (Check >= 90%)                     │
│ [Report] {feature}                     │
│   ↓ (after Report completion)          │
│ [Archive] {feature}                    │
└────────────────────────────────────────┘

Agent Integration

ActionAgentRole
analyzegap-detectorCompare Design vs Implementation
iteratepdca-iteratorAuto code fix and re-verification
reportreport-generatorGenerate completion report

Usage Examples

# Start new feature
/pdca plan user-authentication

# Create design document
/pdca design user-authentication

# Implementation guide
/pdca do user-authentication

# Gap analysis after implementation
/pdca analyze user-authentication

# Auto improvement (if needed)
/pdca iterate user-authentication

# Completion report
/pdca report user-authentication

# Check current status
/pdca status

# Guide to next phase
/pdca next

Legacy Commands Mapping

Legacy CommandPDCA Skill
/pdca-plan/pdca plan
/pdca-design/pdca design
/pdca-analyze/pdca analyze
/pdca-iterate/pdca iterate
/pdca-report/pdca report
/pdca-status/pdca status
/pdca-next/pdca next
/archive/pdca archive

Auto Triggers

Auto-suggest related action when detecting these keywords:

KeywordSuggested Action
"plan", "planning", "roadmap"plan
"design", "architecture", "spec"design
"implement", "develop", "build"do
"verify", "analyze", "check"analyze
"improve", "iterate", "fix"iterate
"complete", "report", "summary"report
"archive", "cleanup", "store"archive

⚡ Optimization Integration

When using this skill for critical tasks, please run it within a /native-trace context to capture performance data for self-improvement via /aioptimize.

When not to use it

  • Simple queries without PDCA context
  • Code-only tasks without a PDCA framework

Limitations

  • Cannot archive before Report completion
  • Max iterations for auto-improvement is 5
  • Requires a matchRate of >= 90% to stop iteration

How it compares

This skill provides a structured, automated workflow for the PDCA cycle, integrating documentation and agent-based analysis, unlike a manual, ad-hoc approach.

Compared to similar skills

pdca side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
pdca (this skill)03moReviewIntermediate
linear101moNo flagsBeginner
zapier-workflows118moReviewBeginner
attio-skill-generator77moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

linear

lobehub

Linear issue management guide. Use when working with Linear issues, creating issues, updating status, or adding comments. Triggers on Linear issue references (LOBE-xxx), issue tracking, or project management tasks. Requires Linear MCP tools to be available.

10117

zapier-workflows

davila7

Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.

11101

attio-skill-generator

kesslerio

Generate use-case-specific Attio workflow skills from templates. Use when creating new skills for lead qualification, deal management, customer onboarding, or custom Attio workflows.

7100

automation-brainstorm

MacroMan5

Interactive workflow design advisor for Power Automate, n8n, Make, Zapier and other platforms. Guides users through planning automation workflows with smart questions about triggers, actions, data flow, and error handling. Uses research sub-agent to find best practices and generates detailed implementation plan. Triggers when user mentions "create workflow", "build flow", "design automation", "need ideas for", or describes workflow requirements without having a complete design.

778

daily-briefing

anthropics

Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar, CRM, and email. Trigger with "morning briefing", "daily brief", "what's on my plate today", "prep my day", or "start my day".

761

jira

davila7

Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.

1152

Search skills

Search the agent skills registry