CLIPPY development protocol — evidence-based investigation, design, implementation, and verification workflow for Claude Code
Autonomous app development — from idea to working product across sessions. Use when the user says "auto", "autonomous", "build me", "create me", or wants hands-off development with investigation-first discipline. Requires OMC (oh-my-claudecode) for execution.
This skill should be used when the user says "clippy", "use clippy", "with clippy", or asks to "build a feature", "investigate the codebase", "refactor this", "implement X", or requests evidence-based development requiring investigation before implementation.
Internal skill — decomposes design artifacts into a task graph with units, dependencies, and parallelism groups. Called by autopilot after design is complete.
Internal skill activated by composer for implementation phase. Do not activate directly.
Investigation and design phase with V1 evidence standards. Two modes — interactive (activated by composer, menu-driven) or autonomous (invoked directly with --autonomous, self-looping, returns structured results). Use autonomous mode when an external orchestrator needs pre-implementation investigation.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Two complementary protocols for AI assistant behavior, designed to improve code quality, investigation thoroughness, and development workflow. CLIPPY handles development work (new features, refactoring). DANEEL handles investigation and debugging (wrong behavior, understanding existing systems).
Models: Claude or Opus is recommended for best results; the protocols should work with any reasonably capable model.
Mission: Working Solutions, First Time
Traditional AI workflow:
Ask → AI implements → Bugs → Fix → More bugs → Fix...
CLIPPY workflow:
Request → Investigate + Design (loop) → Implement → Verify → Done
The key difference: Iteration happens during investigation and design, not after coding.
INVESTIGATE & DESIGN — Evidence-based investigation with user control
IMPLEMENT — Build following verified design
VERIFY — Systematic check that implementation follows architecture
Mission: Root Cause Found, First Time
When to use: Debugging wrong behavior, understanding existing systems, investigating unfamiliar architecture.
claude plugin marketplace add Gunther-Schulz/coding-clippy
claude plugin install clippy@coding-clippy
Restart Claude Code or run /reload-plugins to activate.
| Component | Description |
|---|---|
clippy:composer | Skill — auto-invoked on investigation/development requests, or invoke with /clippy:composer |
clippy:investigate-design | Internal phase skill (activated by composer) |
clippy:implement | Internal phase skill (activated by composer) |
clippy:verify | Internal phase skill (activated by composer) |
Start explicitly:
/clippy:composer implement feature X
Or just describe the task — the composer skill auto-activates on investigation/development requests.
CLIPPY shows a menu after every response. Options depend on the current phase:
| Phase | Options |
|---|---|
| INVESTIGATE & DESIGN | c continue, i implement (requires [READY]) |
| Post-implementation | v verify, d done |
| VERIFY | c another round, d done |
Free-form feedback is always available — ask questions, challenge findings, redirect investigation.
For tools without plugin support, attach the protocol file directly:
CLIPPY.md or DANEEL.md into the chat| File | Purpose |
|---|---|
CLIPPY.md | Full development protocol (investigation, design, implementation, verification) |
DANEEL.md | Investigation & debugging protocol (understand, investigate, root cause) |
CLIPPY_MINI.md | Lighter two-phase investigation protocol |
CONVENTIONS.md | Meta-protocol guidelines (for creating protocols, not direct AI usage) |
plugin/ | Claude Code plugin (skills) |
claude plugin marketplace update coding-clippy
claude plugin update clippy@coding-clippy
Then /reload-plugins or restart Claude Code.
claude plugin uninstall clippy@coding-clippy
claude plugin marketplace remove coding-clippy
Skills live in plugin/skills/. The plugin structure:
npx claudepluginhub gunther-schulz/coding-clippyGuide for designing effective Claude Code skills and plugins
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Code transformation: Dev SDLC orchestrator (code-shipping pipeline), plan, assert, audit, review, test, refactor, debug, for-sure. Hosts engineering agents.
AI Pair Programming Suite - Intelligent code review, bug hunting, and real-time programming assistance
Describe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
PROJECT.md-first autonomous development with hybrid auto-fix documentation. 8-agent pipeline, auto-orchestration, docs auto-update on commit (true vibe coding). Knowledge base system with 90% faster repeat research. Strict mode enforces SDLC best practices automatically. Works for ANY Python/JavaScript/TypeScript/Go project.