Skills de Claude Code · página 105

DELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes *deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.

Orchestrates the full DELIVER wave end-to-end (roadmap > execute-all > finalize). Use when all prior waves are complete and the feature is ready for implementation.

Shared density-resolution contract for wave skills. Canonical detail on the D12 cascade, density resolver call, ad-hoc override workflow, and DocumentationDensityEvent telemetry emission. Referenced from nw-discover / nw-discuss / nw-design / nw-devops / nw-distill / nw-deliver.

Rollback procedures, risk assessment, pre/post-deployment validation, and contingency planning. Load when orchestrating deployment or preparing rollback plans. For deployment strategy details (canary, blue-green, rolling), see `cicd-and-deployment` skill.

Evaluation criteria and scoring for data engineering artifact reviews

Apple LeanUX++ design workflow, journey schema, emotional arc patterns, and CLI UX patterns. Load when transitioning from discovery to visualization or when designing journey artifacts.

7 agentic design patterns with decision tree for choosing the right pattern for each agent type

Designs system architecture with C4 diagrams and technology selection. Routes to the right architect based on design scope (system, domain, application, or full stack). Two interaction modes: guide (collaborative Q&A) or propose (architect presents options with trade-offs).

Designs CI/CD pipelines, infrastructure, observability, and deployment strategy. Use when preparing platform readiness for a feature.

Generates C4 architecture diagrams (context, container, component) in Mermaid or PlantUML. Use when creating or updating architecture visualizations.

Conducts evidence-based product discovery through customer interviews and assumption testing. Use at project start to validate problem-solution fit.

Question-first approach to understanding user journeys. Load when starting a new journey design or when the discovery phase needs deepening.

4-phase discovery workflow with decision gates, phase transitions, success metrics, and state tracking

Conducts Jobs-to-be-Done analysis, UX journey design, and requirements gathering through interactive discovery. Use when starting feature analysis, defining user stories, or creating acceptance criteria.

Acceptance test creation methodology for the DISTILL wave. Domain knowledge for the acceptance designer agent: port-to-port principle, prior wave reading, wave-decision reconciliation, graceful degradation, and document back-propagation.

Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence. Use when the team has a validated problem but hasn't chosen a solution approach.

Review criteria for the nw-diverger-reviewer — validates JTBD rigor, research quality, option diversity, taste application correctness, and recommendation coherence in DIVERGE wave artifacts

DIVIO/Diataxis four-quadrant documentation framework - type definitions, classification decision tree, and signal catalog

Creates evidence-based documentation following DIVIO/Diataxis principles. Use when writing tutorials, how-to guides, reference docs, or explanations.

Strategic and tactical DDD patterns, bounded context discovery, context mapping, aggregate design rules, and decision frameworks for when to apply DDD

Definition of Ready checklist criteria, antipattern detection patterns, UAT quality rules, and domain language enforcement for product owner review

Critique dimensions, severity framework, verdict decision matrix, and review output format for documentation assessment reviews

Use when a DELIVER roadmap already exists and you need to dispatch exactly one identified step through its TDD cycle. Use nw-roadmap to create the plan, nw-deliver for the whole wave, and nw-continue to resume at the next inferred step.

Fast-forwards through remaining waves end-to-end without stopping for review between waves.

Archives a completed feature to docs/evolution/, migrates lasting artifacts to permanent directories, and cleans up the temporary workspace. Use after all implementation steps pass and mutation testing completes.

Toyota 5 Whys methodology with multi-causal branching, evidence requirements, and validation techniques

Creates new specialized agents using the 5-phase workflow (ANALYZE > DESIGN > CREATE > VALIDATE > REFINE). Use when building a new AI agent or validating an existing agent specification.

TLA+ and PlusCal for specifying distributed system invariants. Decision heuristics for when formal verification adds value, key patterns, state explosion management, and alternatives comparison.

Algebra-driven API design with monoids, semigroups, and interpreters via algebraic equations

Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec

Domain modeling with algebraic data types, smart constructors, and type-level error handling

F# language-specific patterns, Railway-Oriented Programming, and Computation Expressions

Haskell language-specific patterns, GADTs, type classes, and effect systems

Hexagonal architecture patterns with pure core and side-effect shell for functional codebases

Kotlin language-specific patterns with Arrow, Raise DSL, and coroutine-based effects

Core functional programming thinking patterns and type system foundations, language-agnostic

Scala 3 language-specific patterns with ZIO, Cats Effect, and opaque types

Naming conventions, API ergonomics, and usability patterns for functional code

5-layer agent output validation, I/O contract specification, vertical slice development, and test doubles policy with per-layer examples

Git change frequency hotspot analysis — find the most-changed files in your codebase

Infrastructure as Code patterns (Terraform, Kubernetes), observability design (SLOs, metrics, alerting, dashboards), and pipeline security stages. Load when designing infrastructure, observability, or security scanning.

Mom Test questioning toolkit, JTBD analysis, interview conduct, assumption testing framework, and hypothesis design

Evidence collection methods, problem categorization, analysis techniques, and solution design patterns

JTBD methodology for extracting real jobs behind feature requests — job statements, abstraction layers, first-principles extraction, ODI outcome statements, and opportunity scoring

Translating JTBD analysis to BDD scenarios - job story to Given-When-Then patterns, forces-based test discovery, job-map-based test discovery, and property-shaped criteria

Core JTBD theory and job story format - job dimensions, job story template, job stories vs user stories, 8-step universal job map, outcome statements, and forces of progress

JTBD discovery techniques adapted for AI product owner context. Four Forces extraction, job dimension probing, question banks, and anti-patterns for interactive feature discovery conversations.

JTBD opportunity scoring and prioritization - outcome statement format, opportunity algorithm, scoring interpretation, feature prioritization, and opportunity matrix template

JTBD workflow classification and routing - ODI two-phase framework, five job types with workflow sequences, baseline type selection, workflow anti-patterns, and common recipes

Draw.io 配图专家：用于生成和导出 `.drawio` 图表。在用户要求 draw.io、diagrams.net、流程图、架构图、时序图、ER 图、状态图、思维导图，或明确提到 `.drawio`、PNG、SVG、PDF 导出、技术文章配图时使用。默认输出专业技术风格，并遵循 floracat-architecture-diagram 的视觉规范。

|

Set up the Switch connector for Codex — register this Codex instance as a Switch agent and write the credentials the bundled MCP server reads. Use when the user asks to configure Switch, set up the plugin, register with a Switch server, or when the Switch tools report no identity.

How to take part in a Switch room. Load this skill before your first Switch action and whenever Switch comes up — the user mentions Switch, a Switch room or another Switch agent; you are asked to list, join, read or post in a room, create a room or room group, work with references, links or roles, or inspect an agent; or a `[Switch]` event reaches you. Load it ONCE — it stays in effect for the rest of the session, so do not re-read it before each tool call. Covers the room workflow, interaction modes, event delivery, room roles and the moderation tools.

Add a new model to an existing provider

Review a provider implementation for correctness and consistency with other providers

Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap .cursor/agents; Bootstrap .claude/agents; Copy robot agents. Part of cursor-rules-java project

Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. This should trigger for requests such as Create AGENTS.md; Update AGENTS.md file; Add agent instructions. Part of cursor-rules-java project

>

Generated skill from request: trinity auto-boot validator

Create your OpenAI Agents SDK skill in one prompt, then learn to improve it throughout the chapter

Create your OpenAI Agents SDK skill in one prompt, then learn to improve it throughout the chapter

Create your Google Agent Development Kit skill in one prompt, then learn to improve it throughout the chapter

Create your Claude Agent SDK skill in one prompt, then learn to improve it throughout the chapter

Build a specification-first Digital FTE that orchestrates accumulated intelligence from Lessons 1-7. Learn to compose execution skills into production-ready agents, validate against specifications, and position for monetization.

Create a skill that orchestrates the write-execute-analyze loop to autonomously process data. Learn to implement error recovery, iterate toward robust solutions, and test your skill across diverse input scenarios. This is where specification-driven development meets real problem-solving.

Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

Create your agent-integration skill from OpenAI SDK and LiteLLM documentation before learning framework integration

Work autonomously without waiting for hand-holding — complete tasks end-to-end without asking for permission at every step.

Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter

Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter

Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.

Main orchestrator for autonomous coding operations. Use when running autonomous sessions, coordinating components, managing the full lifecycle, or orchestrating implementations.

Manage checkpoints for rollback capability. Use when creating save points, rolling back changes, managing recovery points, or restoring previous states.

Manage git commits for autonomous coding. Use when committing feature implementations, creating descriptive commits, managing git workflow, or handling version control.

Validate acceptance criteria and feature completion. Use when checking if features pass, validating test results, verifying acceptance criteria, or determining feature completion status.

Create handoff packages for session transitions. Use when ending sessions, preparing for continuation, saving session state, or creating resumable context.

Manage knowledge graph for autonomous coding. Use when storing relationships, querying connected knowledge, building project understanding, or maintaining semantic memory.

Phase 4.0 — Acceptance Criteria lock checkpoint before implementation. Consolidates all ACs from PRD, TechSpec, and Tasks, presents to user for confirmation, and saves the locked AC list to accepted-criteria.md. Implementation only starts after explicit user confirmation.

Master controller for complete autonomous operation. Use when starting full autonomous projects, managing end-to-end workflow, controlling autonomous lifecycle, or running complete implementations.

Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.

Analyze context and decide on continuation via Stop hook. Use when determining if work should continue, analyzing completion status, making continuation decisions, or implementing the Two-Claude pattern.

Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation.

Add new Agent templates to the meta-agent-skills framework.

Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

|

|

a set of guidelines to build with Botpress's Agent Development Kit (ADK) - use these whenever you're tasked with building a feature using the ADK

Detects when user requests warrant critical analysis via /advise command

Agent Farm CLI quick reference. Use when running af commands to check correct syntax, subcommands, and flags. Prevents guessing at command names.

Agent skill for agent - invoke with $agent-agent

Agent skill for agentic-payments - invoke with $agent-agentic-payments

Agent skill for app-store - invoke with $agent-app-store

Agent skill for arch-system-design - invoke with $agent-arch-system-design

Agent skill for architecture - invoke with $agent-architecture

Use when designing an autonomous agent, planning agent architecture, building a scheduled automation, or creating a Claude Code agent workflow. Triggers: 'design an agent', 'build an automation', 'agent architecture', 'automate this workflow', 'create a scheduled agent', 'shell script agent'.

|

Validates agent configurations for model selection, tool permissions, focus areas, and approach quality. Use when reviewing, auditing, improving agents, or learning agent best practices.

Agent skill for authentication - invoke with $agent-authentication