发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
oklch-skill
OKLCH color space for web projects. Convert hex/rgb/hsl to oklch, generate palettes, check contrast, handle gamut boundaries, and theme with Tailwind v4. Triggers on oklch, color conversion, palette generation, contrast ratio, gamut, display p3, design tokens, hue drift, chroma, dark mode colors.
excel
Automates Microsoft Excel via pywin32 (COM) for interactive pair work. Attaches to a running Excel instance, selects an already-open workbook by name, and runs agent-generated Python to manipulate sheets/cells/formulas and save/export.
notion
Notion API for creating and managing pages, databases, and blocks.
Angular API State Pattern
A best-practice pattern for handling API interactions and state management in Angular using Services and Signals.
code-review
Expert in conducting thorough code reviews for Python projects using GitHub MCP, covering test coverage, security practices, PEP 8 compliance, and code organization. Use when reviewing code or PRs.
coding-pipeline
Orchestrated coding pipeline for feature builds. Spawns a 7-stage sub-agent pipeline (Plan → Setup → Implement → Verify → Test → PR → Review) with dedicated agent personas and retry loops. Use when: building features, fixing bugs, or refactoring code across multiple files. NOT for: simple one-liner fixes, reading code, or non-coding tasks.
claude-api
Load when a workflow-router-selected owner workflow needs Claude API or Anthropic SDK build, debug, migration, or tuning work; skip provider-neutral, OpenAI, or non-Anthropic model work.
mcp-server-patterns
Build MCP servers with the Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
dev-team
Orchestrate a multi-phase software development agent team with requirements gathering, planning, development, review, and reporting. Spawns specialized agents (requirements engineer, staff engineers, senior devs, QA, PO) that work in parallel workstreams with 95% certainty gates and quality reviews. Use whenever the user wants a full dev team, a coordinated multi-agent build, or says things like "build a team", "dev team", "agent team", "orchestrate development", or describes complex multi-phase work requiring planning, implementation, and review.
accessibility-testing
Test web accessibility using axe-core plus manual checks: screen reader testing, keyboard-only navigation, and color-contrast validation to ensure WCAG compliance. Trigger: "accessibility", "a11y", "WCAG", "screen reader", "axe-core"
content-style
Use when drafting marketing content; enforces grade-8 readability, bans em dashes, requires word-count bands, and a skimmable structure
using-skills
Use at session start and before every task - establishes mandatory skill discovery and usage protocols to ensure relevant expertise is always applied
sglang-serving
Serve LLMs with SGLang for structured generation and high-throughput inference. Use when launching an SGLang server, using RadixAttention, producing constrained JSON/regex output, or performing structured decoding.
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
gps-msg-file
Create GPS message TOML files for configuring GPS receivers via satpulsetool
Running Log
Persistent schema-driven running log with three-component architecture - quick-capture ideas, AI auto-detection, and backlog review librarian
cognitive-complexity
Use when code is hard to understand, a module has too many parameters or deep nesting, functions exceed 40 lines, abstractions feel leaky, or you need to evaluate deep-module vs shallow-module design per Ousterhout principles
elixir-patterns
Use when structuring Elixir code, deciding whether to use GenServer or plain functions, designing supervision trees, handling overload or unbounded message queues, organizing Phoenix contexts, or needing idiomatic OTP patterns
eaai-benchmark-paper
Paper-writing automation wrapper for the BPR benchmarking study (cards, draft assembly, consistency checks).
firecrawl-search
Web search and scraping via the Firecrawl API. Use when you need to search the web, scrape websites (including JS-heavy pages), crawl entire sites, or extract structured data. Handles anti-bot defenses, JS rendering, and PDFs.
sench-team
Analyze a company's team structure and founders. Returns employee list by department with LinkedIn URLs, founder backgrounds, and team composition analysis. No external tools required.
analyzing-test-coverage
Analyze code coverage metrics and identify untested code paths. Use when analyzing untested code or coverage gaps. Trigger with phrases like "analyze coverage", "check test coverage", or "find untested code".
appfolio-install-auth
Configure AppFolio Stack API authentication with OAuth 2.0. Use when setting up property management API access, registering as an AppFolio Stack partner, or configuring client credentials for API calls. Trigger: "install appfolio", "setup appfolio", "appfolio auth", "appfolio API key".