AI Ml AI agent skills

8,771 skills in the archive. Read a skill’s instructions or open its original repository.

• Deepchat Cli

  by @ThinkInAIXYZ

  Use DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configuration, Skills, and MCP operations. Activate when a user asks to invoke DeepChat…

• Deepchat Settings

  by @ThinkInAIXYZ

  DeepChat app settings modification (DeepChat 设置/偏好) skill. Activate ONLY when the user explicitly asks to change DeepChat's own settings/preferences (e.g., theme, language, font size...). Do NOT activate for OS/system settings,…

• Feishu Tools

  by @ThinkInAIXYZ

  Use the Feishu/Lark plugin MCP tools for Feishu documents, spreadsheets, knowledge content, and other matching workspace operations.

• Memory Management

  by @ThinkInAIXYZ

  Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.

• Code Review

  by @ThinkInAIXYZ

  Comprehensive code review assistant that analyzes code quality, security, and best practices

• Git Commit

  by @ThinkInAIXYZ

  Generate well-formatted git commit messages following conventional commit standards

• Officecli

  by @Sylinko

  Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

• Context7 Docs Research

  by @Devin-AXIS

  Resolve the correct library and retrieve a small, relevant set of version-aware official documentation before answering a technical question.

• Notion Knowledge

  by @Devin-AXIS

  Search connected Notion pages and databases, verify the relevant sources, and produce concise answers that preserve links and uncertainty.

• Dry Refactoring

  by @kucherenko

  Guided workflow to eliminate copy-paste duplication detected by jscpd. Refactor exact, renamed and near-miss clones using extract function, parameterize, module, constant, or base class strategies, starting from the hotspots the…

• Jscpd

  by @kucherenko

  Copy-paste detector for 220+ languages. Detect exact, renamed and near-miss duplicated code, measure duplication percentages, and find refactoring hotspots with the codebase summary.

• Mathmodel To Ei

  by @jihe520

  将用户提供的一篇完整数学建模竞赛论文改写为面向 EI 会议投稿的英文研究论文，内置 IEEE conference LaTeX 模板，完成研究主线提炼、结构重组、图表整理、证据核验与源码/PDF 交付。适用于数模论文转会议论文、竞赛论文英文改稿及已有会议稿迭代。

• Skill Creator

  by @FlorianBruniaux

  Scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources. Use when creating a custom skill, standardizing skill structure across a team, or packaging a skill for distribution.

• Self Assessment

  by @FlorianBruniaux

  Interactive skill assessment with personalized learning path generation

• Talk Stage4 Position

  by @FlorianBruniaux

  Generates 3-4 strategic talk angles with strength/weakness analysis, title options, CFP descriptions, and a peer feedback draft, then enforces a mandatory CHECKPOINT for user confirmation before scripting. Use when deciding how…

• Talk Stage5 Script

  by @FlorianBruniaux

  Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk…

• Update Threat Db

  by @FlorianBruniaux

  Update the guide's threat intelligence through AgentSec Triage, research new coding-agent and MCP security advisories, and synchronize the security feed. Use for threat database refreshes or mise a jour de la base de menaces,…

• Voice Refine

  by @FlorianBruniaux

  Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.

• Source Command Track Mentions

  by @FlorianBruniaux

  Search for new online mentions of the Claude Code Ultimate Guide or Florian Bruniaux's public project portfolio and update the relevant tracker

• Sandbox Unblock

  by @FlorianBruniaux

  Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured…

• Talk Stage3 Concepts

  by @FlorianBruniaux

  Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment. Use when you need a structured inventory of concepts…

• Talk Stage2 Research

  by @FlorianBruniaux

  Performs git archaeology, changelog analysis, and builds a verified factual timeline by cross-referencing git history with source material. REX mode only (skipped automatically in Concept mode). Use when building a REX talk and…

• Talk Pipeline

  by @FlorianBruniaux

  Orchestrates the complete talk preparation pipeline from raw material to revision sheets, running 6 stages in sequence with human-in-the-loop checkpoints for REX or Concept mode talks. Use when starting a new talk pipeline,…

• Talk Stage6 Revision

  by @FlorianBruniaux

  Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating…

• Talk Stage1 Extract

  by @FlorianBruniaux

  Extracts and structures source material (articles, transcripts, notes) into a talk summary with narrative arc, themes, metrics, and gaps. Auto-detects REX vs Concept type. Use when starting a new talk from any source material or…

• Scaffold

  by @FlorianBruniaux

  Interactive coach that asks 4-5 questions to determine whether you need an agent, command, skill, hook, or rule, then generates a ready-to-use template. Usage: /scaffold (no arguments needed, starts the coaching session)

• Rtk Optimizer

  by @FlorianBruniaux

  Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens.

• Session Save

  by @FlorianBruniaux

  Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.

• Source Command Methodology Advisor

  by @FlorianBruniaux

  Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack

• Verify Release

  by @FlorianBruniaux

  Use when checking whether a Proofpack release candidate has complete local evidence before packaging.

• Source Command Audit Whitepapers

  by @FlorianBruniaux

  Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards

• Source Command Audit Prose

  by @FlorianBruniaux

  Add descriptive prose to bare sections in whitepapers (FR + EN) using 9 parallel agents

• Source Command Ccguide Refresh Docs

  by @FlorianBruniaux

  Re-fetch official Anthropic Codex docs and update current snapshot (baseline unchanged)

• Source Command Ccguide Diff Docs

  by @FlorianBruniaux

  Compare official Anthropic docs baseline vs current snapshot (no network — instant)

• Source Command Ccguide Daily

  by @FlorianBruniaux

  Daily update check — official Anthropic docs diff + guide/CC releases digest

• Source Command Ccguide Init Docs

  by @FlorianBruniaux

  Fetch official Anthropic Codex docs and store as local baseline snapshot

• Sandbox Status

  by @FlorianBruniaux

  Display native sandbox status, configuration, and recent violations

• Security

  by @FlorianBruniaux

  Rapid security assessment focused on OWASP Top 10 vulnerabilities

• Security Check

  by @FlorianBruniaux

  Quick configuration security check against known threats database

• Source Command Update Infos Release

  by @FlorianBruniaux

  Update Codex releases tracking (guide + landing + version bump)

• Validate Changes

  by @FlorianBruniaux

  Evaluate staged changes using LLM-as-a-Judge before committing

• Security Audit

  by @FlorianBruniaux

  Comprehensive security audit with scored posture assessment

• Sonarqube

  by @FlorianBruniaux

  Analyze SonarCloud quality issues for a specific PR

• Source Command Sync

  by @FlorianBruniaux

  Check guide/landing synchronization status

• Source Command Changelog

  by @FlorianBruniaux

  View recent CHANGELOG entries

• Build Mobile Threejs Games

  by @MengTo

  Build, tune, or test a Three.js game for mobile web. Use for touch movement, action controls, target selection, touch inventory, safe areas, portrait/landscape layouts, responsive HUD, battery/performance budgets, and real…

• Landing Page Generator

  by @FlorianBruniaux

  Generate complete, deploy-ready landing pages from any repository. Use when creating a homepage for an open-source project, building a project website, converting a README into a marketing page, or standardizing landing pages…

• Guide Recap

  by @FlorianBruniaux

  Transform CHANGELOG entries into social content (LinkedIn, Twitter/X, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate release notes, announcements, social media posts, or recap summaries from guide updates.

• Design Patterns

  by @FlorianBruniaux

  Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native…

• Ccboard

  by @FlorianBruniaux

  Launch and navigate the ccboard TUI/Web dashboard for Claude Code. Use when monitoring token usage, tracking costs, browsing sessions, or checking MCP server status across projects.

• Learning Path

  by @FlorianBruniaux

  Run the local Claude Code learning path, record evidence, and schedule evidence-based reviews.

• Pr Triage

  by @FlorianBruniaux

  4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to…

• Issue Triage

  by @FlorianBruniaux

  3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze…

• Mcp Integration Reference

  by @FlorianBruniaux

  Template for skills that integrate with an MCP server. Demonstrates the reference file pattern: Claude reads a domain-specific MCP cheatsheet before making any tool calls, reducing query failures caused by server-specific…

• Eval Agents

  by @FlorianBruniaux

  Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants,…

• Eval Hooks

  by @FlorianBruniaux

  Audit Claude Code hooks defined in settings.json files for validity, performance safety, and correctness. Resolves each command against the filesystem, checks exit-code strategy for blocking hooks, flags missing timeouts, and…

• Eval Rules

  by @FlorianBruniaux

  Audit .claude/rules/ files for structural correctness, glob validity, and real-world usefulness. Resolves each paths: pattern against actual project files, then asks the user whether each rule is still relevant and useful. Can…

• Eval Skills

  by @FlorianBruniaux

  Audit all skills in the current project for frontmatter completeness, effort level appropriateness, allowed-tools scoping, and content quality. Produces a scored report with effort-level recommendations for each skill. Use when…

• Handoff Update

  by @FlorianBruniaux

  Update an existing handoff document with current session progress. Applies section-specific merge rules: append-only for Work Done (never deletes history), replace for Status and Next Steps, merge for Files and Discoveries.…

• Recipe Template

  by @FlorianBruniaux

  Template for commands that implement a structured recipe: validate preconditions, then execute numbered steps. Fork this and replace the placeholder content. The 'Context Validation Checkpoints' section is the key pattern,…

• Plan Pipeline

  by @FlorianBruniaux

  Orchestrates the complete planning pipeline: product direction (ceo-review) -> architecture (eng-review) -> implementation plan (start) -> validation (validate) -> execution (execute). Run stages individually or let the…

• Handoff Create

  by @FlorianBruniaux

  Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current status, next steps, and code snippets. Use before ending a session or…

• Cyber Defense Team

  by @FlorianBruniaux

  Orchestrate a 4-agent cyber defense pipeline to analyze log files for threats. Use when investigating security logs, detecting anomalies in access patterns, classifying breach severity, or generating incident reports from…

• Git Ai Archaeology

  by @FlorianBruniaux

  Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.

• Handoff Resume

  by @FlorianBruniaux

  Load a handoff document and resume work from where a previous session left off. Parses scope, file references, completed work, and next steps, then confirms understanding before proceeding.

• Plan Pipeline Execute

  by @FlorianBruniaux

  Execute a validated plan: worktree isolation, TDD scaffolding, level-based parallel agents, quality gate with smoke test, PR creation and merge. Handles everything through to merged PR.

• Plan Pipeline Validate

  by @FlorianBruniaux

  2-layer plan validation: instant structural checks + trigger-based specialist agents. Auto-fixes issues using ADRs and first principles. Every issue must be resolved before execution.

• Ci All

  by @FlorianBruniaux

  Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.

• Autoresearch

  by @FlorianBruniaux

  Autonomous improvement loop: scan codebase metrics, scaffold experiment files, run agent-driven iterations until metric improves

• Best Of N

  by @FlorianBruniaux

  Generate bounded independent candidates, score them against a frozen rubric, and verify the selected result with a proof log.

• Plan Pipeline Eng Review

  by @FlorianBruniaux

  Engineering architecture gate: lock architecture, diagrams, edge cases, and test matrix before writing implementation code

• Plan Pipeline Ceo Review

  by @FlorianBruniaux

  Strategic product gate: challenge the brief, find the 10-star product hiding inside the request, before writing any code

• Check Cache Bugs

  by @FlorianBruniaux

  Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5

• Methodology Advisor

  by @FlorianBruniaux

  Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack

• Ci Tests

  by @FlorianBruniaux

  Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test)

• Review Plan

  by @FlorianBruniaux

  Structured plan review across 4 axes before writing any code (inspired by Garry Tan's workflow)

• Qa

  by @FlorianBruniaux

  Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop

• Ci Pipeline

  by @FlorianBruniaux

  Push current branch and return the pipeline tracking URL (GitLab or GitHub Actions)

• Ci Status

  by @FlorianBruniaux

  Show current pipeline status for the active branch (GitLab CI or GitHub Actions)

• Git Worktree

  by @FlorianBruniaux

  Create isolated git worktrees for feature development without switching branches

• Land And Deploy

  by @FlorianBruniaux

  Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.

• Git Worktree Clean

  by @FlorianBruniaux

  Clean up stale git worktrees with merged branch detection and disk usage report

• Optimize

  by @FlorianBruniaux

  Analyze and suggest performance improvements for code, queries, or systems

• Catchup

  by @FlorianBruniaux

  Restore context after /clear by summarizing recent work and project state

• Explain

  by @FlorianBruniaux

  Explain code, concepts, or system behavior with adjustable depth levels

• Git Worktree Status

  by @FlorianBruniaux

  Check status of background verification tasks running in a git worktree

• Investigate

  by @FlorianBruniaux

  Systematic root-cause debugging: find the cause before writing any fix

• Pr

  by @FlorianBruniaux

  Analyze changes, detect scope issues, and create a well-structured PR

• Refactor

  by @FlorianBruniaux

  Analyze code for SOLID violations and suggest targeted improvements

• Git Worktree Remove

  by @FlorianBruniaux

  Safely remove a git worktree with branch cleanup and safety checks

• Audit Codebase

  by @FlorianBruniaux

  Codebase health audit scoring 7 categories with progression plan

• Diagnose

  by @FlorianBruniaux

  Interactive troubleshooting assistant for Claude Code issues

• Learn Teach

  by @FlorianBruniaux

  Step-by-step explanation of a concept with progressive depth

• Commit

  by @FlorianBruniaux

  Generate a conventional commit message for staged changes

• Learn Quiz

  by @FlorianBruniaux

  Test understanding of recently written or accepted code

• Learn Alternatives

  by @FlorianBruniaux

  Compare different approaches to solve the same problem

• Review Pr

  by @FlorianBruniaux

  Perform a comprehensive code review of a pull request

• Generate Tests

  by @FlorianBruniaux

  Generate comprehensive tests for specified code

• Webcrawler Deep Crawl

  by @browser-act

  Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG) and in-scope outbound links. Use when user mentions deep crawl website,…

• Commit Ko

  by @epoko77-ai

  AI(Claude 등)가 제안한 한글 커밋 메시지의 사무적·번역투 어휘("~을 수행함", "~을 진행함", "~적 개선을 실시함" 등)를 실제 개발자가 쓰는 자연스러운 한국어 커밋 메시지로 다듬는 스킬. humanize-korean과 달리 산문 문단이 아니라 1~2줄짜리 커밋 메시지 register에 특화되어 진단·청킹 없이 단일 콜로 즉시 처리한다. 트리거 — "커밋 메시지 자연스럽게", "커밋 메시지…