Agent Tooling
Skills that build, configure or extend agents and other skills.
Search and filter within Agent Tooling
4387 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| agentsop-repo-state-gatingagentsope/SkillAlchemyA 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the workspace into Greenfield / Brownfield-large / Mid-size-familiar / Library-SDK, then maps the state to an agent strategy (autonomy, context primitive, tool choice). Use BEFORE picking Cursor vs Claude Code vs Aider, BEFORE turning on repo-map, BEFORE writing the first prompt. Skip only if the same repo was gated within the last day and nothing changed. Search keywords: greenfield vs brownfield, new project vs existing codebase, project setup strategy, legacy codebase agent, where to start a coding agent. | Stars: 483 | Updated | Claude CodeCodex | Unverified | Install |
| agentsop-reranker-stageagentsope/SkillAlchemyAdds and tunes a reranker stage for RAG using the retrieve-wide, rerank-narrow pattern. Use when relevant documents appear in the initial top-N but are buried by noise, top-1 precision or MRR is low despite adequate recall, or too many marginal chunks consume context. Covers cross-encoder, API, and local rerankers; N-to-k selection; and latency/cost tradeoffs. Do not use when retrieval recall itself is failing. | Stars: 483 | Updated | Claude CodeCodex | Unverified | Install |
| agentsop-selfhost-decisionagentsope/SkillAlchemyProject-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing where to run inference, or when cost / data-residency pressure forces a re-evaluation. | Stars: 483 | Updated | Claude CodeCodex | Unverified | Install |
| agentsop-session-state-hygieneagentsope/SkillAlchemyDecision protocol for managing the context/session state of an AI coding tool: when to /clear, when to keep context, and how to detect "context bleed" — the failure mode where stale conversation history biases the model against the current task. Surfaces a discipline that Aider (/clear), Claude Code (/clear), CrewAI (memory=False, re-instantiate), and LangGraph (new thread_id, subgraph isolation) all encode separately but none name as a skill. | Stars: 483 | Updated | Claude CodeCodex | Unverified | Install |
| agentsop-structured-output-pickeragentsope/SkillAlchemyDecide where to enforce structured LM output (constrain at decode time with Outlines vs validate-and-retry with Instructor vs grammar with Guidance) and which failure stance to take (Assert/hard-fail vs Suggest/soft-retry). Use when an LM's output is parsed or typed by downstream code and you must pick one enforcement library plus its failure handling, when malformed output is burning tokens on retries, or when choosing between decode-time vs validation-time constraints for local vs API models. | Stars: 483 | Updated | Claude CodeCodex | Unverified | Install |
| agentsop-tool-scopingagentsope/SkillAlchemyEnhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-based frameworks (CrewAI, LangChain) document only as a passing best-practice: which agent gets which tool, and why blanket-sharing every tool to every agent is a correctness and blast-radius risk. Activates when an agent system has tools AND there is more than one agent (or one agent holding many tools). Treat a tool as a capability grant; scope by least-privilege. ENHANCE overlay — read alongside [[crewai]], [[agentsop-http-tool-wrapping]], [[agentsop-llm-tool-idempotency]]. Search keywords: which tools per agent, least-privilege agent, agent tool access, tool permissions, limit agent tools, scope tools to roles.overlay_type: enhancement | Stars: 483 | Updated | Claude CodeCodex | Unverified | Install |
| agentsop-trajectory-to-semantic-opsagentsope/SkillAlchemySOP for distilling reusable semantic operators (data-science operation skills) from agent execution trajectories: read action/observation traces, classify per-task failures, bind data-semantic constraints (input semantics / operation decision / output constraints / validation), and feed bounded edits back through an optimizer such as SkillOpt. Use when mining agent runs for cross-task operation knowledge, when a data-science skill keeps failing on the same operation family (join cardinality, group granularity, unit, time alignment), or when wiring trajectory history into a skill optimizer without polluting the skill body. | Stars: 483 | Updated | Claude CodeCodex | Unverified | Install |
| agentsop-vllmagentsope/SkillAlchemyDecision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs, OOM triage, and when NOT to use vLLM. Activates when a coder-agent is choosing or tuning an inference engine, debugging vLLM throughput/latency/OOM, or comparing vLLM against TGI/SGLang/TensorRT-LLM/llama.cpp. | Stars: 483 | Updated | Claude CodeCodex | Unverified | Install |
| Lensagentsope/SkillAlchemyLens — Add a cognitive lens to any problem. It accepts a task description and produces an enhanced description that surfaces hidden dimensions, prerequisites, and lines of inquiry—the things you do not know you do not know. Use when the user asks to brainstorm, analyze, generate a skill, distill, or fuse, or when the input is too simple and needs to be expanded. | Stars: 483 | Updated | Claude CodeCodex | Unverified | Install |
| pavedpath-codeJia-Ethan/pavedpath-codePavedPath Code is the code-focused edition of PavedPath. It helps agents solve software engineering problems by finding proven implementation paths from GitHub repositories, issues, pull requests, discussions, code examples, release notes, and open-source evidence. | Stars: 439 | Updated | Claude CodeCodex | Unverified | Install |
| image-useleeguooooo/image-useBackend-neutral image generation: create new raster images and looping GIF/WebP animations through the local one-file image-use CLI (formerly chatgpt-imagegen), using the user's ChatGPT subscription by default, the Codex backend as fallback, or an optional Gemini subscription — no API key or daemon. Triggers: image generation, generate an image, draw a picture, 画图, 画一张, 生成图片, 生图, 配图. Use for photos, illustrations, icons, hero banners, mockups, sprites, concept art, animation loops, and figures for documents, proposals, blog posts, or READMEs; save outputs in the workspace. Auto mode uses the logged-in ChatGPT browser via chrome-use. Gemini users can pass --backend gemini or agy. Proactively propose useful figures while authoring long-form content. Do not use for editing existing images, SVG/vector work, code-native graphics, established icon systems, explicit high-quality or transparent API output, or end-user image-generation services. | Stars: 422 | Updated | Claude CodeCodex | Unverified | Install |
| super-video-makerBomx/OpenVideoEnd-to-end AI video production skill for agentic frameworks. Use when the user asks to make, edit, repurpose, caption, soundtrack, or export videos using HeyGen avatars, Seedance or ByteDance b-roll, OpenAI image generation and editing, AI UGC ads, Remotion, HyperFrames, screen recordings, FFmpeg, captions, ElevenLabs music, Suno, or social-video variants. | Stars: 350 | Updated | Claude CodeCodex | Unverified | Install |
| shellgamesMemTensor/skills-votePlay board games on ShellGames.ai — Chess, Poker, Ludo, Tycoon, Memory, and Spymaster. Use when the agent wants to play games against humans or other AI agents, join tournaments, chat with players, check leaderboards, or manage a ShellGames account. Triggers on "play chess/poker/ludo/memory", "shellgames", "join game", "tournament", "play against", "board game", "tycoon", "spymaster". | Stars: 309 | Updated | Claude CodeCodex | Unverified | Install |
| skills-voteMemTensor/skills-voteFind the most relevant external agent skills for the current task, then submit grounded feedback about which skills were actually used and useful in the same session. Whenever you start a task, use this skill first. | Stars: 309 | Updated | Claude CodeCodex | Unverified | Install |
| skills-vote-localMemTensor/skills-voteUse when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery. | Stars: 309 | Updated | Claude CodeCodex | Unverified | Install |
| ghostwritersuperzhang21/ghostwriterUse when switching AI persona/language style. Syncs 13+ character profiles (Ding Yuanying, Lin Daiyu, Lu Xun, Li Yunlong, etc.) from GitHub, generates persona prompts with thinking patterns, rhetoric, and speech traits. | Stars: 306 | Updated | Claude CodeCodex | Unverified | Install |
| oil-coveroil-oil/oil-cover生成小红书和 B 站 AI 工具实操视频封面,支持脚本模式与 Agent 自主模式、真实视频证据、三画幅输出和可选创作者头像。仅在用户明确提到 oil-cover、$oil-cover、使用 oil-cover 或指定本 Skill 时触发;普通封面、首图、视频封面请求不要自动触发。 | Stars: 301 | Updated | Claude CodeCodex | Unverified | Install |
| pocketmen-with-yousix-nut/PocketMen-with-youTurn 2+ user reference images into a high-fidelity animated Codex companion using PocketMen's own local stack. Prefer the open-weight Neural Local Studio (FLUX.2 klein 4B; optional Qwen-Image-Edit-2511 Identity-Max) on compatible hardware; otherwise fall back to the deterministic local renderer. Never require hatch-pet or OPENAI_API_KEY for the normal workflow. | Stars: 294 | Updated | Claude CodeCodex | Unverified | Install |
| delive-transcript-analyzerXimilalaXiang/DeLiveAnalyze, summarize, and extract insights from DeLive transcription sessions. Use when: user mentions DeLive, transcription, meeting transcripts, live captions, audio transcription, AI correction, corrected transcript, or transcript analysis; user wants to search, retrieve, summarize, correct, or process recorded transcripts; user asks about meeting notes, action items, discussion summaries, or transcript quality from DeLive. Requires DeLive app running locally with its MCP server or REST API. | Stars: 262 | Updated | Claude CodeCodex | Unverified | Install |
| find-skillsHezaoHezao/poirotDiscover available skills in the builtin library by keyword. | Stars: 261 | Updated | Claude CodeCodex | Unverified | Install |
| skill-authoringHezaoHezao/poirotAuthor SKILL.md: frontmatter, structure, writing principles. | Stars: 261 | Updated | Claude CodeCodex | Unverified | Install |
| skill-creatorHezaoHezao/poirotCreate, edit, and evaluate agent skills iteratively. | Stars: 261 | Updated | Claude CodeCodex | Unverified | Install |
| source-verificationHezaoHezao/poirot验证信源可信度的研究过程知识,指导 agent 在涉及事实声明时交叉核验信源 | Stars: 261 | Updated | Claude CodeCodex | Unverified | Install |
| subagent-driven-developmentHezaoHezao/poirotExecute plans task-by-task with two-stage review. | Stars: 261 | Updated | Claude CodeCodex | Unverified | Install |
| fskill-creatorAGI-comming/functional-skill-creatorCreate, maintain, or migrate functional skills; supports creating from a requirement brief and migrating an existing legacy skill directory into a functional skill structure. | Stars: 256 | Updated | Claude CodeCodex | Unverified | Install |
| fskill-creator-createAGI-comming/functional-skill-creatorCreate lane for fskill-creator; normalizes user briefs into create_context for the main skill to generate functional skills. | Stars: 256 | Updated | Claude CodeCodex | Unverified | Install |
| fskill-creator-migrateAGI-comming/functional-skill-creatorMigrate lane for fskill-creator; analyzes a legacy skill directory into behavior map, function split proposal, and source evidence. | Stars: 256 | Updated | Claude CodeCodex | Unverified | Install |
| basic-functional-skillAGI-comming/functional-skill-creatorStarter template for a functional agent skill. | Stars: 256 | Updated | Claude CodeCodex | Unverified | Install |
| ros2-engineering-skillsdbwls99706/ros2-engineering-skillsROS 2 engineering: rclcpp/rclpy, colcon/ament, launch, QoS/DDS, tf2/URDF, ros2_control, Nav2, MoveIt 2, sensors, runtime/artifact provenance, and hardware safety. Use for development, review, debugging, and ROS 1 migration to ROS 2. Not for general C++/Python, unrelated middleware, or web/mobile tasks. | Stars: 246 | Updated | Claude CodeCodex | Unverified | Install |
| mcd-party-officeryzg1226/mcd-party-officer麦当劳门店派对/包场/拼团的选址、成团调度与筹备助手。当用户想办生日派对、亲子派对、主题派对、品鉴会、读书会、麦麦体验营,或说「麦当劳派对」「派对拼团」「包场」「生日会怎么办」「哪家店能办派对」「还差几个人成团」「包场还是拼团划算」「帮我写拼团招募文案」「做一张派对邀请函」「孩子派对吃什么不超标」时使用。基于麦当劳官方 MCP(mcp.mcd.cn)的 party 系列工具:扫描全城场次、估算成团概率、对比包场与拼团成本、按官方营销活动日历挑最佳日期、审查儿童餐营养、生成招募卡与邀请函。 | Stars: 242 | Updated | Claude CodeCodex | Unverified | Install |