Development

Enforces brevity and signal-over-noise in all outputs. Eliminates verbose explanations, filler phrases, and unnecessary elaboration. Use when documentation, artifacts, or responses need to be maximally concise and actionable.

Real-time web research/search with sources (outputs JSON).

Strict code review following Clean Code, Clean Architecture, and The Pragmatic Programmer principles. Use when: (1) reviewing code or pull requests, (2) detecting code smells or quality issues, (3) auditing architecture decisions, (4) preparing code for merge, (5) refactoring existing code, or (6) checking adherence to SOLID, DRY, YAGNI, KISS principles. Features a 3+4+2 questionnaire system to calibrate strictness from L1 (lab) to L5 (critical). Also triggers on: "is this code good?", "check...

Forth/Factor/Joy: stack-based concatenative programming where composition replaces application.

Multi-agent app builder with 7 modes - greenfield, iteration, bugfix, refactor, UI polish, migration, and audit. PM orchestrates specialized agents with feature branches. 98%+ quality gate, runtime verified, visual QA.

Claude Computer Use tool integration for desktop automation. Enables Claude to interact with computer environments through screenshots, mouse control, keyboard input, and application automation in sandboxed environments.

Use when creating tailored resumes for job applications - researches company/role, creates optimized templates, conducts branching experience discovery to surface undocumented skills, and generates professional multi-format resumes from user's resume library while maintaining factual integrity

Build with Solana compressed NFTs (cNFTs) - Merkle trees, minting at scale, transfers, and metadata. Use when creating large NFT collections or reducing mint costs.

Read and write compressed sequence files (gzip, bzip2, BGZF) using Biopython. Use when working with .gz or .bz2 sequence files. Use BGZF for indexable compressed files.

Requires detailed type annotations for all Python functions, methods, and class members.

This skill should be used when the user asks to "review test coverage", "audit test quality", "check tests for completeness", or mentions reviewing pytest test suites. Performs thorough test review following standard checklist for test isolation, mock usage, naming, and coverage.

A Claude Code skill that allows you to search, browse, and install skills from a database of 31,767+ community skills with intelligent folder-level downloads. Supports SVN export, Git sparse checkout, and HTTP fallback methods for complete skill folder installation.

CLI-first API testing for HTTP, GraphQL, gRPC, and TCP.

Fetches ALL open issues from any GitHub repository using pagination and generates a comprehensive analysis including category breakdown, age distribution, stale issues (30+ days), top discussed issues, prioritization, and detailed recommendations for triage. Handles large repositories (5000+ issues) efficiently.

Complete frontend development skill combining distinctive design aesthetics with technical excellence. Creates production-grade web applications using React, Next.js, TypeScript, and modern tooling. Use when building web components, pages, or applications that require both exceptional design quality and robust technical implementation. Handles everything from creative UI design to performance optimization, component scaffolding, bundle analysis, and deployment.

Forensic, high-fidelity context handover for seamless continuation in a new chat. Produces a single Markdown transfer artifact plus reusable templates, preserving decisions, requirements, non-negotiables, and open loops without truncation by judgment. Not for code continuation unless explicitly stated.

Exhaustive multi-dimensional project auditor covering code, runtime, infrastructure, security, performance, business logic, and human processes across 12 dimensions with confidence-tracked findings and explicit blind spot documentation. Includes dead code detection (Knip/depcheck), file size/token limit analysis for AI editing compatibility, and honest system health reporting.

Generate comprehensive compound profiles including structure, properties, bioactivity, and development status. Use for drug analysis, SAR studies, and competitive profiling. Keywords: compound, drug, molecule, structure, SMILES, bioactivity, IC50

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

Compare data structures (DuckDB, LanceDB) via ACSets with persistent homology coverage analysis and geometric morphism translation.

Composio OAuth integration for external service connections. CSRF-protected flow with state management, connection lifecycle transitions (pending→initiated→active), dynamic tool building from active connections, token expiration handling. Triggers on "composio", "oauth", "integration", "connection", "external service", "third-party".

vi sshagent.sh ```bash eval $(ssh-agent -s) > /dev/null ssh-add ~/.ssh/id_ed25519 ``` 会自动设置`SSH_AUTH_SOCK`环境变量 1. 打开命令行工具 2. 运行SSH代理 - windows系统：`start-ssh-agent`并输入私钥密码 - 类Unix系统：`ssh-agent $SHELL` 和 `ssh-add 私钥路径` (路径默认值是~/.ssh/id_ed25519)，输入私钥密码(可能暂不能关掉命令行工具才起效，等git操作一次后就可以关掉命令行了) 3. 运行命令`code`来启动VSCode 另外的思路：先启动VSCode，然后在VSCode命令行中运行SSH代理，接着其它操作。 你一般只能在VSCode打开一个项目，如果要打开多个项目就要启动多个VSCode，其实你可以`将多个项目集中到工作区里`方便统一进行管理。

Teaches component composition patterns in React 19 including children prop, compound components, and render props. Use when designing component APIs, creating reusable components, or avoiding prop drilling.

Rules pertaining to Composer dependency management, promoting best practices for declaring and updating dependencies.