发现 Skills

Production-grade skill for generating clear, well-documented code examples, implementation patterns, configuration files, and integration samples with multi-language support.

Convert URDF robot descriptions to MJCF format for MuJoCo simulation. Handles meshes, joints, actuators, and collision geometries.

Google's Wycheproof test vectors for cryptographic implementation testing.

Automatically activates when working with Tailwind CSS v4. Trigger this skill when writing Tailwind classes, adding utility styles, using @theme or @apply directives, or styling React/Angular components.

Engineering practices for building production LLM applications — model selection, structured outputs, streaming, prompt caching, retry logic, cost and latency control, observability, and the boring infrastructure that determines whether an LLM feature ships or stays a demo. Use this skill whenever the task involves calling an LLM API from application code, designing the architecture of an LLM-powered feature, debugging flaky or expensive LLM calls, hardening a prototype for production, choosing between models or providers, or any work where someone says "we have a prompt that works, now we need to ship it." Trigger even when the user does not explicitly say "production" — most LLM code becomes production code, and the practices here apply from day one.

This skill should be used when the user asks to 'pick up an issue' or 'work on an issue'.

Design and apply compression strategies for long-running agent sessions. Use when: approaching context limits, reducing token costs, summarizing conversations, optimizing multi-turn interactions, or implementing compaction for agents that run many sequential tasks.

Official LottieFiles motion design principles — timing curves, easing, choreography, Disney's 12 principles adapted for UI. Implementation-agnostic: works with CSS, GSAP, Framer Motion, Lottie. Supports 40+ agents.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Self-contained SaaS automation — invoke directly, do not decompose. Transforms a Vibes app into a multi-tenant SaaS with subdomain-based tenancy. Adds Clerk authentication, subscription gating, and generates a unified app with landing page, tenant routing, and admin dashboard.

Senior power-engineer playbook for contingency violations. Use when N-1 or N-2 studies reveal voltage or thermal problems and the agent needs to move from ranking contingencies to identifying preventive or corrective actions.

Specific workflows and standards for maintaining the husky-rs project.

Comprehensive debugging methodology for finding and fixing bugs (formerly debugging). This skill should be used when debugging code, investigating errors, troubleshooting issues, performing root cause analysis, or responding to incidents. Covers systematic reproduction, hypothesis-driven investigation, and root cause analysis techniques. Use when encountering exceptions, stack traces, crashes, segfaults, undefined behavior, or when bug reports need investigation.

A valid test skill with proper formatting. This skill should pass all validations and serves as a reference for the expected format.

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

Role-based and attribute-based access control testing including permission matrices, privilege escalation prevention, and resource-level authorization.

Comprehensive file upload testing including format validation, size limits, malware scanning, storage verification, and concurrent upload handling.

Build reusable test data factories with realistic fake data generation, relationship handling, and deterministic seeding for reproducible tests.

Core academic workspace tools: LaTeX compilation, Jupyter execution, PDF loading, UI control, content updates, and arXiv paper conversion. Use when the user asks to compile LaTeX, run Python code, load PDFs, display data, or control workspace editors.

Retroactive audit of an implemented AI phase's evaluation coverage. 2 states — A (AI-SPEC.md + SUMMARY exists, audit against spec) B (SUMMARY only, audit against best practices). Spawns maxv-eval-auditor. Produces scored EVAL-REVIEW.md with verdict, score/100, and critical gap count.

API contract testing, authentication flows, rate limit handling, and error scenario coverage for n8n integrations with external services. Use when testing n8n node integrations.

AQE skill

Build content-focused websites with Eleventy (11ty). Use when creating templates (.njk, .liquid), working with data cascade, collections, or deploying static sites.

Use when the user wants to implement a new feature, fix a bug, or explicitly requests development using TDD (write tests first). Trigger scenarios: tdd, test-driven, test-driven development, write tests first, red-green-refactor, unit tests, test driven, TDD development, using TDD, tests-first, I'm starting to develop a new feature.