Découvrez les skills testing security llm ai, comparez leurs dépôts et consultez leurs instructions.
Prepares meeting materials by gathering context from Notion, enriching with Claude research, and creating both an internal pre-read and external agenda saved to Notion. Helps you arrive prepared with comprehens...
专门用于在对话结束时，根据用户反馈和对话内容总结优化并迭代现有 Skills 的核心工具。它通过吸取对话中的“精华”（如成功的解决方案、失败的教训、特定的代码规范）来持续演进 Skills 库。
Start MARVIN session with briefing. Use when user types /marvin or starts a new session. Loads context, reviews state, gives daily briefing.
Create new MARVIN skills on request. Use when user says "give yourself the ability to X" or "create a skill for Y". Generates proper skill structure with SKILL.md.
AI-driven browser automation via Model Context Protocol
Send a task to OpenCode via the `oask` CLI and wait for the reply. Use only when the user explicitly delegates to OpenCode (ask/@opencode/let opencode/review); not for questions about OpenCode itself.
Async via cask, end turn immediately; use only when user explicitly delegates to Codex (ask/@codex/let codex/review); NOT for questions about Codex itself.
Async via oask, end turn immediately; use only when user explicitly delegates to OpenCode (ask/@opencode/let opencode/review); NOT for questions about OpenCode itself.
Fetch the latest reply from Claude storage via the `lpend` CLI. Use only when the user explicitly asks to view the Claude reply/response (e.g. "看下 Claude 回复/输出"); do not run proactively after `lask` unles...
Send a task to Claude via the `lask` CLI and wait for the reply. Use only when the user explicitly delegates to Claude; not for questions about Claude itself.
Send a task to Gemini via the `gask` CLI and wait for the reply. Use only when the user explicitly delegates to Gemini (ask/@gemini/let gemini/review); not for questions about Gemini itself.
Test connectivity with Claude via the `lping` CLI. Use when the user explicitly asks to check Claude status/connection (e.g. "l ping", "Claude alive?"), or when troubleshooting Claude not responding.
Async via gask, end turn immediately; use only when user explicitly delegates to Gemini (ask/@gemini/let gemini/review); NOT for questions about Gemini itself.
Fetch the latest reply from Gemini (shorthand: g/gm) via the `gpend` CLI. Use only when the user explicitly asks to view the Gemini/gm reply/response (e.g. "看下 g 回复/输出"); do not run proactively after `gas...
Build neuro-symbolic LLM applications with Synalinks framework. Use when working with DataModel, Program, Generator, Module, training LLM pipelines, in-context learning, structured output, JSON operators, Branc...
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, wor...
Z.AI CLI providing: - Vision: image/video analysis, OCR, UI-to-code, error diagnosis (GLM-4.6V) - Search: real-time web search with domain/recency filtering - Reader: web page to markdown extraction - Repo: Git...
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
Simple operations on user-provided text files including summarization.
Perform statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
Export analysis results, data tables, and formatted spreadsheets to Excel files using openpyxl. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
Create professional PDF reports with text, tables, and embedded images using reportlab. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
Transform, clean, reshape, and preprocess data using pandas and numpy. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
Create publication-quality plots and visualizations using matplotlib and seaborn. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.