Skills de Claude Code · página 133

Scaffold a new ECS component header under include/gz/sim/components/, wire its CMake listing, and (if needed) register it with ComponentFactory for serialization. Trigger when the user asks to add a new component or a per-entity data field.

Scaffold a new Nav 2 plugin (controller, planner, behavior, smoother, goal-checker, progress-checker, costmap layer, or BT node). Wires pluginlib registration, parameter declaration on the lifecycle node, and a minimal integration test. Trigger when the user asks to write or extend a Nav 2 plugin.

Scaffold a new ROS 2 package (ament_python or ament_cmake) inside a colcon workspace, restructured to follow this template's Clean Architecture layout. Trigger when the user asks to create a new ROS 2 package or to bootstrap a Clean-Architecture-compliant codebase.

Bootstrap a complete ROS 2 colcon workspace from scratch — directory layout, .gitignore, top-level README, this .claude/ config, an interfaces package and a first Clean Architecture package, and a bringup package. Trigger when the user asks to create a new workspace / start a new ROS 2 project from zero.

Scaffold a new gz-sim system plugin under src/systems/<name>/ — header, source, CMake glue, plugin registration, and an integration test stub. Trigger when the user asks to create a new system, controller, or plugin that hooks into the simulation loop.

ROS2 bag recording and analysis utilities with Clean Architecture (Python & C++)

Scaffold a ros2_control hardware component (SystemInterface / ActuatorInterface / SensorInterface) and its bringup — the plugin (on_init/on_configure/on_activate, RT-safe read()/write()), URDF <ros2_control> wiring, controllers.yaml + launch, pluginlib export. Trigger when the user asks to integrate hardware or bring up a robot under ros2_control.

Scaffold or extend a ros2_control controller or broadcaster (ControllerInterface / ChainableControllerInterface) — base-class choice, command/state interface configuration, lifecycle, real-time-safe update(), generate_parameter_library, pluginlib export, tests. Trigger when the user asks to write a ros2_control controller or broadcaster.

ROS2 Diagnostics and Health Monitoring with Clean Architecture (Python & C++)

Clean Architecture compatible ROS2 launch files and parameter management (Python)

ROS2 Managed (Lifecycle) Node implementation with Clean Architecture (Python & C++)

ROS2 messaging patterns and best practices with Clean Architecture (Python & C++)

Guide for creating ROS2 nodes following Clean Architecture principles (Python & C++)

ROS2 Service and Action implementation with Clean Architecture (Python & C++)

ROS2 test strategies and patterns with Clean Architecture (Python & C++)

ROS2 TF2 and Transform management with Clean Architecture (Python & C++)

Bridge a VDA 5050 v3.0.0 fleet-control interface (MQTT/JSON) onto Nav 2 under Clean Architecture — domain entities, MQTT/Nav 2 adapters behind ports, order→NavigateThroughPoses mapping, state aggregation, action handlers. Trigger when the user asks to build or extend a VDA 5050 connector / fleet bridge.

Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.

Design stable, versioned, self-documenting APIs. Easy to use correctly, hard to use incorrectly. Apply Hyrum's Law from day one.

Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.

Get layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work with it safely.

Structured code review focusing on correctness, security, and maintainability. Correctness before style. Every reviewer comment must be actionable.

Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.

Systematic root cause analysis for production and development bugs. Hypothesis-driven debugging — never guess-and-check.

Document decisions, not just implementations. ADRs for architectural choices, inline docs for non-obvious code, and runbooks for operational knowledge.

Graceful degradation and meaningful error messages. Errors are first-class citizens, not afterthoughts. Every error path is designed, not discovered.

Accessible, performant, responsive UI patterns. Component design, state management discipline, and Core Web Vitals compliance.

Trunk-based development with atomic commits, clean history, and meaningful commit messages. Every commit should be deployable.

Transforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.

Detects and mitigates LLM hallucinations in production pipelines. Validates AI-generated facts, code, and decisions before they reach end users or downstream systems.

Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.

Build in verifiable increments. Never implement more than can be tested right now. Ship partial working systems over complete broken ones.

Test real system boundaries, not mocks of mocks. Integration tests verify that components work together, not that they work in isolation.

Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.

Designs and coordinates multi-agent pipelines where specialized agents collaborate to complete complex tasks. Includes communication protocols, failure handling, and state management.

Structured logging, distributed tracing, and alerting for AI systems and traditional services. You can't fix what you can't see.

Measure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.

Zero-downtime deployments with pre-flight checks, staged rollouts, and rollback plans. Never ship to production without a verified rollback strategy.

Guards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect. Validates AI inputs and outputs at every trust boundary.

Patterns for Retrieval-Augmented Generation (RAG) and agent memory systems. Retrieves only relevant context, prevents context bloat, and maintains coherent state across sessions.

Safe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct.

Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action.

Applies OWASP Top 10, secrets management, and least-privilege principles before any code ships. Security is a build step, not an afterthought.

Prevents overengineering by enforcing minimum viable code. No speculative features, no premature abstractions, no unnecessary complexity.

Enforces minimal code modifications — touch only what you must. Prevents drive-by refactoring, comment deletions, and style changes unrelated to the task.

Breaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel work and reduces integration risk.

Red-green-refactor cycle with meaningful coverage. Tests are written before implementation. Coverage is a side effect of good tests, not the goal.

Forces explicit reasoning before writing any code. Surfaces assumptions, manages confusion, and prevents hallucination by demanding clarity upfront.

Find academic papers across 5 sources (OpenAlex / Semantic Scholar / CrossRef / PubMed / arXiv) with adjustable depth — Quick scan (5 min) to Audit prep (3 hr). Use when the user wants to find papers, run a literature search, gather references, or scope a research topic. Triggers on: search verbs ('find papers', 'literature search', 'papers about X'), review types ('scoping review', 'systematic review', 'SR prep', 'literature review', 'lit review', 'help me write a lit review'), Chinese ('找文献', '找论文', '论文搜索', '学术检索', '文献检索', '文献综述', '综述前期', '求文献'). Outputs Shadcn HTML report + BibTeX/RIS/CSV + PRISMA-S log. Do NOT use for: concept explanations ('what is X' / 'X 是什么'), writing requests ('help me write a paragraph' / '帮我写'), single-paper interpretation or PDF download with full bibliographic metadata (use paper-downloader-portable), or when the user already has a literature set ready (use literature-set-review).

Meihua Yishu (梅花易數) Plum Blossom I Ching divination skill. Use when users request divination, fortune telling, hexagram casting, or character analysis (測字). Triggers on: 占卜, 算卦, 問卦, 起卦, 解卦, 測字, 拆字, meihua, plum blossom, I Ching divination, 梅花易數.

Build REST APIs with proper error handling, status codes, request validation, response formatting, and rate limiting. Apply when creating API routes, handling errors, validating input, or designing API responses.

Harden REST and GraphQL APIs against common attack vectors. Apply when building API endpoints, implementing authentication, handling file uploads, or exposing APIs to external consumers.

Deploy Node.js applications on AWS using EC2, RDS, and managed services with security best practices. Apply when setting up AWS infrastructure, configuring databases, managing security, or optimizing costs.

Rapidly fix build failures, type errors, and lint issues with minimal diffs. Apply when builds fail, TypeScript reports errors, or CI/CD pipelines break. Focuses on getting the build green fast.

STRIDE-based threat modeling for application architecture. Apply when designing new systems, reviewing architecture, or assessing security posture of existing applications.

Production-ready Docker patterns for multi-stage builds, security hardening, and orchestration. Apply when creating Dockerfiles, docker-compose configs, or deploying containerized applications.

Enforces Conventional Commits, PR standards, merge conflict resolution, and branch management. Apply when committing code, opening PRs, resolving conflicts, managing branches, or handling Git operations.

Deploy Node.js applications on Google Cloud with Cloud Run, Cloud Firestore, and Google APIs. Implement OAuth2 authentication and manage service accounts. Apply when building serverless applications, integrating Google services, or deploying to GCP.

Structured production incident triage, resolution, and post-mortem. Apply when production systems are down, degraded, or behaving unexpectedly. Covers detection, containment, resolution, and learning.

Implement CloudWatch monitoring, error tracking with Sentry, structured logging, and alert configuration. Apply when setting up monitoring, tracking errors, debugging production issues, or configuring dashboards.

Configure serverless PostgreSQL databases on Neon with connection pooling, branching, and Edge Function integration. Apply when setting up serverless databases, connecting from Edge Functions, or managing database branches.

Build Next.js 15 applications using App Router, Server Components, Client Components, Server Actions, and streaming. Apply when creating pages, handling data fetching, implementing routes, or optimizing performance.

Implement authentication with NextAuth.js v5, Google OAuth, credentials provider, session management, and protected routes. Apply when building auth flows, protecting routes, managing sessions, or implementing RBAC.

Systematic security audit against OWASP Top 10:2025. Apply when reviewing code that handles authentication, user input, API endpoints, data storage, or any security-sensitive functionality.

Systematic web application penetration testing methodology. Apply when performing authorized security assessments, bug bounty hunting, or pre-deployment security validation. Covers recon, scanning, exploitation, and reporting.

Optimize Next.js bundle size with code splitting, tree shaking, lazy loading, and build configuration. Apply when improving performance, reducing bundle size, analyzing dependencies, or optimizing load times.

Build end-to-end tests with Playwright, Feature Object pattern, cross-browser testing, and visual regression. Apply when testing critical user flows, automating regression testing, or validating integrations.

Design database schemas, create migrations, manage data relationships, and sync with production using Prisma. Apply when designing database schemas, creating migrations, or defining data models.

Implement Next.js SEO with metadata, structured data, sitemaps, Open Graph tags, and technical SEO. Apply when optimizing pages for search engines, adding social sharing, or improving discoverability.

Save, resume, and compact Claude Code sessions for long-running work across context windows. Apply when approaching context limits, switching tasks, or continuing multi-session work.

Smart context compaction that preserves critical information. Apply when context usage approaches 60-80% to recover usable context without losing important decisions, progress, or reasoning.

Build consistent, accessible UI components with Tailwind CSS, shadcn/ui, and custom design tokens. Apply when styling components, creating design systems, implementing responsive layouts, or optimizing CSS performance.

Enforce strict Test-Driven Development with Red-Green-Refactor discipline. Apply when implementing new features, fixing bugs, or refactoring code. Ensures tests are written before implementation.

Apply TDD with RED-GREEN-REFACTOR cycles, separate unit tests from integration tests, ensure comprehensive coverage. Apply when writing tests, evaluating test coverage, testing databases, or testing admin flows.

Deploy Next.js to Vercel with zero-config, manage environment variables, set up CI/CD pipelines, and optimize production performance. Apply when deploying to Vercel, configuring environments, or setting up CI/CD workflows.

Write fast unit tests with Vitest, coverage reporting, mocking, and snapshots. Apply when testing utilities, components, services, or building test coverage.

This skill should be used when the user wants to query their Google NotebookLM notebooks for citation-backed, source-grounded answers, or manage notebooks, sources, and Studio content (audio, report, video, infographic, presentation, data table, flashcards, quiz, mind map). It drives the @roomi-fields/notebooklm-mcp engine — via the notebooklm MCP tools when they are available in the session, otherwise via its HTTP REST API — and covers Google login, citation formats, the daily-quota-aware batch/ingestion pattern, and source discovery.

Use when a task needs an isolated hidden Linux desktop or workspace-owned browser: GUI app QA, web/browser/shopping automation, sandboxed app observation, or stale workspace cleanup. Routes agent-workspace-linux MCP tools on demand. Does NOT apply to host desktop/Chrome control, generic MCP setup, or pure code/file edits.

Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.

Design Apple-style iOS/macOS interfaces following Human Interface Guidelines. Creates HIG-compliant components with SF Symbols, San Francisco typography, and proper accessibility. Supports optional modern effects. Use when designing Apple-style UI, iOS/macOS interfaces, HIG-compliant components, or implementing design system specifications.

Restructures a chaotic or overgrown MEMORY.md into a clean 2-layer architecture based on how Claude Code's autoDream system organizes memory — a lightweight pointer index (always loaded) and topic files (loaded on demand). Stale or superseded memories are deleted or corrected in place — not archived. Use this skill whenever the user says \"clean up MEMORY.md\", \"reorganize my memory files\", \"MEMORY.md is getting too long\", \"fix my memory structure\", or when you observe that MEMORY.md exceeds 200 lines, contains full paragraphs instead of pointers, or mixes index entries with topic content.

Define agent tools using the fail-closed design pattern — unified name/schema/security/execution in one class, with three-layer execution (validate → permission → call). Use this skill whenever the user wants to define a new agent tool, add permission or validation logic to an existing tool, or asks about 'build a tool', '定义一个工具', 'create a tool for X', '工具定义'. Framework-agnostic: works with hermes-agent, LangChain, or any Python agent framework.

Analyzes Chinese public company financial statements (balance sheet, income statement, cash flow) to assess asset quality, profit authenticity, cash flow health, solvency, and overall investment value. Use when the user provides financial data or a company name and asks whether financials are healthy, whether profits are real, whether there are red flags, or whether the company is a good investment. Based on the book "一本书读懂财报" by Xiao Xing (Tsinghua University).

>

Use Business Adventures for "why did this fail?", "analyze this crisis", "what pattern applies?", or "what would Brooks notice?

Apply John Bogle stewardship capitalism logic to separate investing from

Apply John Bogle index investing rules for low-cost funds, asset allocation,

Developer implementation guide for adding compact memory to an Agent — covers fork agent pattern for compaction, trigger strategy, summary format design, and memory restoration in subsequent sessions. Use when a developer asks how to implement compact memory, context compression, or memory persistence in their agent built with Claude Agent SDK or Anthropic API.

Apply Jonah Berger''s STEPPS framework. Trigger on: "why is this not spreading?", "make this campaign contagious", "diagnose viral content".

Apply China contract drafting review with San Guan Si Bu Fa. Trigger on contract review, drafting, clauses, or deal structure.

Apply Brittany Hodak's SUPER Model for customer loyalty, referrals, word of mouth, personalization, service recovery, and scalable customer experience.

Analyze Wall Street conflicts. Trigger on: "can I trust this advisor?", "is this forecast reliable?", "whose interest does this serve?".

Apply Keynes policy reasoning. Trigger on: "will austerity work?", "inflation or deflation?", "analyze this economic crisis".

|

|