发现 Skills

This skill should be used when the agent needs to give a spoken voice update to the user, or when reminded by a Stop hook to provide audio feedback. Use this skill to speak a short summary of what was accomplished.

Specialized workflow for identifying memory leaks and CPU bottlenecks in Node.js applications.

Installs and configures Zellij terminal multiplexer from GitHub releases. Use when setting up Zellij for terminal workspace management.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Generate comprehensive documentation from code

Generate comprehensive unit tests for code files

Create a new agent definition file following the development-guides agent template and registry conventions. Covers persona design, tool selection, skill assignment, model choice, frontmatter schema, required sections, registry integration, and discovery symlink verification. Use when adding a new specialized agent to the library, defining a persona for a Claude Code subagent, or creating a domain-specific assistant with curated skills and tools.

Sharpen and maintain knives using whetstones, field stones, and improvised abrasives. Covers blade anatomy, bevel assessment, whetstone technique (coarse to fine progression), stropping, sharpness testing, field sharpening methods, and ongoing edge maintenance. Use when a knife fails the fingernail test, when cutting tasks require excessive pressure, before a trip where a sharp blade is essential, after heavy use, or when a blade has visible nicks or a rolled edge. Applicable to bushcraft blades, folding knives, and garden cutting tools.

Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.

Use this skill whenever the task involves planning, scaffolding, or generating UI layouts, screens, dashboards, forms, or components in a Next.js / React project. Activates on phrases like "create a screen", "plan the layout", "scaffold a page", "build a dashboard", "design a form", "generate UI for", "create components for", or any frontend structure request. Produces framework-agnostic UI plans in OpenUI Lang and the corresponding shadcn/ui implementation code. Works entirely offline — no external API required.

Master AI agent fundamentals — architectures, ReAct patterns, cognitive loops, and autonomous system design

Resolve TypeScript declaration entry files (.d.ts) for an import/dependency (oxc-resolver). Suitable for tasks like locating interface/type-definition/declaration-file (.d.ts) entry points — especially in pnpm or monorepo setups.

Code review command for Flutter/Dart: checks Effective Dart, null safety, Riverpod/Bloc state management, Serverpod endpoints, Jaspr components, and security vulnerabilities. Run before merging PRs.

Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the [REDACTED] decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source first model router routes all tiers to [REDACTED] by default — Claude only kicks in as an escape hatch when needed. Includes [REDACTED] API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth profile rotation for Venice API keys, Gateway Guardian v4 with billing-aware escalation, through-OpenClaw inference probes, proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, and nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver to prevent dashboard overload, bundled security skills, zero-dependency wallet management via macOS Keychain, x402 payment client for agent-to-agent USDC payments, and ERC-8004 agent registry reader for discovering trustless agents on Base.

Use when refactoring production code and you want to ensure test files are not modified. Activate with /freeze-tests to block all edits to test files for safe refactoring.

Testing in production with feature flags, canary deployments, synthetic monitoring, and chaos engineering. Use when implementing production observability or progressive delivery.

How to adjust VRM MToon material outline thickness with three-vrm. Covers outline width modes, where MToon exposes outline properties, and practical fixes for outlines that become too thick after scaling models.

This skill should be used when the user asks to "publish on KDP", "publish my book", "Amazon book publishing", "Kindle Direct Publishing", "self-publish", "publish on Amazon", "KDP workflow", "submit to Amazon KDP", "publish to Kindle", or mentions Amazon/KDP book publishing. It guides the complete workflow for publishing a book through Amazon KDP, handling both technical books and fiction/nonfiction.

This skill should be used when the user says "decompile this prompt", "reverse engineer this prompt", "analyze this prompt", "break down this prompt", "what does this prompt do", "adapt this prompt for", "simplify this prompt", "split this prompt", "migrate this prompt", "why does this prompt work", "explain this system prompt", "what techniques is this using", "convert this prompt from X to Y", "what framework is this prompt using", "optimize this prompt", "look at this prompt", or pastes an existing prompt and wants it analyzed, adapted, simplified, or understood. Covers prompt anatomy, technique identification, structural analysis, cross-platform migration, and weakness mapping.

Extracts the most quotable, shareable statements from content and formats them for social media use. Use when finding pull quotes, social proof, or highlight-worthy statements.

SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when a user says "batch experiments", "queue experiments", "run grid", "multi-seed sweep", "auto-chain experiments", or when /run-experiment is insufficient for 10+ jobs that need orchestration.

Add, configure, or build MCP servers in Claude Code. USE WHEN user says 'add an MCP', 'connect to', 'add integration', 'setup MCP', 'connect MCP server', 'add notion', 'add youtube', 'configure MCP', 'build an MCP', 'create MCP server'.

Test @data-client/vue composables and components - renderDataCompose, mountDataClient, fixtures, jest, nock, Vue 3 reactive props, useSuspense testing

Write Rust tests to verify the correctness of Rust code.