Cross-agent collaboration protocols, workflow handoff patterns, and commit message formats for TDD/Mikado/refactoring workflows
npx skills add https://github.com/nWave-ai/nWave --skill nw-collaboration-and-handoffs
tdd_with_continuous_refactoring:
pattern: "TDD -> L1-L2 Refactoring -> TDD (continuous cycle)"
timing: "After each GREEN phase in inner TDD loop"
scope: "Level 1-2 only during active TDD"
tdd_with_mikado_planning:
pattern: "TDD -> Mikado Exploration -> TDD Continuation"
timing: "When architectural complexity blocks TDD progress"
scope: "Full Mikado Method with return to TDD"
mikado_with_systematic_execution:
pattern: "Mikado Exploration -> Systematic Refactoring Execution"
timing: "After exploration identifies true leaves"
scope: "Full systematic refactoring with tree-guided execution"
feat(<component>): <business-value-description>
- Implemented: <specific feature or capability>
- Tests: <test coverage details>
- Architecture: <architectural layer(s) touched>
- E2E Status: <enabled/disabled with reason>
Discovery: [SpecificClass.Method(parameters)] requires [ExactPrerequisite] in [FilePath:LineNumber]
- Tree: docs/mikado/<goal-name>.mikado.md updated
- Dependencies: <count> new dependencies discovered
- Exploration: <status of exploration phase>
feat(mikado): Implement leaf node - <node-description>
- Mikado Node: <specific node from tree>
- Tree Progress: <completed-count>/<total-count> leaves complete
- Tests: All passing
refactor(level-N): <atomic-transformation-description>
- Applied: <specific refactoring technique>
- Target: <code smell(s) addressed>
- Files: <list of modified files>
- Tests: All passing
- Mikado: <mikado-node-reference> (when applicable)
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
Use when working with error debugging multi agent review
Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.
Diagnoses and debugs A2A agent communication issues including agent status, message routing, transport connectivity, and log analysis. Use when agents aren't responding, messages aren't being delivered, routing is incorrect, or when debugging orchestrator, coder-agent, tester-agent communication problems.
Use when working with error debugging multi agent review
Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.
Ultimate multi-agent framework for Google Antigravity. Orchestrates specialized domain agents (PM, Frontend, Backend, Mobile, QA, Debug) via Serena Memory.
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
Take nwave-ai/nw-collaboration-and-handoffs from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.