psylch

Review an agent skill by combining automated linting with structured semantic analysis. Runs hard-rule validation, evaluates contextual findings, then performs deep review against best practices (description quality, workflow design, runtime robustness, script conventions, UX patterns). Produces actionable improvement suggestions with before/after examples. This skill should be used when reviewing a skill, validating skill structure, improving skill quality, checking skill conventions, or when the user says 'review skill', 'validate skill', 'check skill', 'improve skill', 'iterate on skill', '走查技能', '验证技能', '检查 skill', '改进技能', '优化 skill'.

Create new agent skills with best-practice templates. Guides through skill level selection (L0 pure prompt, L0+ with helper scripts, L1 with business scripts), environment strategy (stdlib/uv/venv), and generates ready-to-edit project files following runtime UX best practices. This skill should be used when creating a new skill, scaffolding a skill project, initializing skill templates, or when the user says 'help me build a skill', 'create a skill', '创建技能', '新建 skill'.

Package a agent skill into a complete GitHub repository ready for distribution via skills.sh. Generates README, LICENSE, plugin.json, marketplace.json, .gitignore, and the proper directory structure. Optionally initializes a git repo and creates a GitHub repository. This skill should be used when publishing a skill, packaging a skill for distribution, preparing a skill repo, or when the user says 'publish skill', 'package skill', 'release skill', '发布技能', '打包 skill'.

Discover music, get personalized recommendations, and download high-fidelity audio files. Use when user wants to find new music based on their taste, search for songs/albums/artists, get recommendations similar to artists they like, or download lossless audio (FLAC/Hi-Res) from Qobuz or TIDAL. Trigger phrases include "find music like", "recommend songs", "download album", "lossless", "Hi-Res", "FLAC", "music discovery", "similar artists", "setup music".

Search, validate, and save cloud drive resources via PanSou aggregation API and local Quark desktop APP integration. This skill should be used when the user wants to find and download resources from cloud drives (网盘资源搜索下载), especially when they mention keywords like "搜资源", "找片", "下载", "网盘", "夸克", "quark", "panso", "盘搜". Requires Quark desktop APP running and logged in with membership.

Search and download books from Z-Library and Anna's Archive. Use when user wants to find, search, download, or look up books, papers, or ebooks. Trigger phrases include "find book", "search book", "download book", "找书", "下载书籍", "搜书", "book search", "zlibrary", "anna's archive".

Explicitly opt into syncing agent decisions, provenance claims, and external artifacts to the local Oversight UI. Use only when the user asks for Oversight, the current managed run injects this skill, or you are deliberately testing Oversight. Do not auto-activate just because the daemon at http://localhost:7333 is reachable.

Sync decisions, provenance, and artifacts to the Oversight UI. Active when the `oversight` CLI and daemon (http://localhost:7333) are available. Falls back to plain chat otherwise.

Search, validate, and save cloud drive resources via PanSou aggregation API and local Quark desktop APP integration. This skill should be used when the user wants to find and download resources from cloud drives (网盘资源搜索下载), especially when they mention keywords like "搜资源", "找片", "下载", "网盘", "夸克", "quark", "panso", "盘搜". Requires Quark desktop APP running and logged in with membership.

Configures a complete terminal-based AI coding environment centered on Ghostty terminal with Fish shell, yazi, lazygit, Neovim (LazyVim), fzf, zoxide, atuin, and supporting tools. Includes CJK font optimization for Chinese/Japanese/Korean users on macOS with Apple Silicon. This skill should be used when setting up or modifying a Ghostty-based development environment, configuring terminal tools for vibe coding workflows, or troubleshooting Ghostty/Fish/yazi/lazygit issues.

Search and download books from Z-Library and Anna's Archive. Use when user wants to find, search, download, or look up books, papers, or ebooks. Trigger phrases include "find book", "search book", "download book", "找书", "下载书籍", "搜书", "book search", "zlibrary", "anna's archive".

Comprehensive technical research by combining multiple intelligence sources — Grok (X/Twitter developer discussions via browser automation), DeepWiki (AI-powered GitHub repository analysis), and WebSearch. Dispatches parallel subagents for each source and synthesizes findings into a unified report. This skill should be used when evaluating technologies, comparing libraries/frameworks, researching GitHub repos, gauging developer sentiment, or investigating technical architecture decisions. Trigger phrases include "tech research", "research this technology", "技术调研", "调研一下", "compare libraries", "evaluate framework", "investigate repo".

Initialize a project-level context management system with docs/ directory structure, Claude Code hooks for automatic context injection (session-start + subagent PreToolUse), and CLAUDE.md navigation. Use when starting a new project, bootstrapping context management, or when the user says '/ch-project-context init', 'init project context', 'setup context management', 'initialize docs structure'.

Discover music, get personalized recommendations, and download high-fidelity audio files. Use when user wants to find new music based on their taste, search for songs/albums/artists, get recommendations similar to artists they like, or download lossless audio (FLAC/Hi-Res) from Qobuz or TIDAL. Trigger phrases include "find music like", "recommend songs", "download album", "lossless", "Hi-Res", "FLAC", "music discovery", "similar artists", "setup music".

Generate Excalidraw diagrams and export to PNG/SVG images. Use when asked to 'create a diagram', 'draw a flowchart', 'visualize architecture', 'make a mind map', 'generate excalidraw', 'export diagram to png', 'diagram to image'. Supports flowcharts, relationship diagrams, mind maps, architecture diagrams, sequence diagrams, ER diagrams, and more. End-to-end: natural language -> .excalidraw JSON -> PNG/SVG image. Trigger: 'excalidraw', 'diagram', 'flowchart', 'visualize', 'architecture diagram', '画图', '流程图', '架构图', '思维导图', '导出图片'.

Architectural routing layer over agent-browser CLI: picks the right tool (agent-browser fresh Chromium / agent-browser shared real-Chrome / camofox-browser anti-detect) for each task, and adds login-watch, CAPTCHA/automation-block detection, per-domain site experience, and parallel multi-tab via CDP proxy. Triggers: 'parallel browse', 'open multiple tabs', 'batch scrape', 'captcha check', 'automation blocked', 'site pattern', 'better browser', 'cdp proxy', 'parallel tabs', 'login watch', 'cloudflare blocked', 'datadome', 'anti-detect scrape'.

Audit CLI tools for AI agent friendliness. Scores 7 base dimensions (structured output, exit codes, non-interactive mode, self-documentation, actionable errors, consistent grammar, token efficiency) plus 4 bonus dimensions (idempotency, composability, dry-run, agent teaching). Use when user says 'audit CLI', 'check agent friendliness', 'review CLI for agents', 'CLI agent experience', 'CLI AX audit', or '审计 CLI'.