agentsclimarketplace

Context & AI engineering

25,841 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Agent pre deploy review

    thaolst/ai-growth-agents-for-marketers/skills/agent-pre-deploy-review Skill

    5★ repo

    Review an AI agent prompt and setup before deploying it in real work. Use when the user has built or customized an agent and wants a thorough review before depending on it for real campaign work. Input: agent description, system prompt, example input, example output. Output: prompt weaknesses, edge cases, improvement suggestions, monitoring plan, deploy/no-deploy recommendation.

  • Amadeus approval handoff

    amadeus-dlc/amadeus/.agents/skills/amadeus-approval-handoff Skill

    5★ repo

    Run the AI-DLC `approval-handoff` stage (ideation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage approval-handoff --single`: the engine emits one run-stage directive for approval-handoff and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.

  • Imagegen magick

    uid13/skills/skills/imagegen-magick Skill

    5★ repo

    生成或编辑矢量/程序化图像(博客封面、Logo、图表、徽章、UI 组件、PPT 封面、社交媒体图片等)。当用户需要基于模板/参数生成具有精确排版、字体控制、尺寸约束的设计类图像时使用。使用 SVG 编写 + ImageMagick 渲染。不适合:照片级写实、复杂纹理、人物肖像等需要生成模型的场景(请改用 imagegen 类技能)。适配 opencode、codex、Claude Code、Cursor、Copilot、Gemini CLI 等 Agent 平台。

  • NewzAI MCP Server

    Gauraviitkgp/news-mcp/ai.newzai.api/news-mcp MCP server

    no license5★ repo

    News MCP: real-time headlines & custom news search across 7 regions. Free, just sign in with Google.

  • UK Hansard MCP Server from MCPBundles

    thinkchainai/mcpbundles/com.mcpbundles/uk-hansard MCP server

    no license5★ repo

    Search Parliamentary questions and motions from UK House of Commons

  • Database mcp sqlite

    arifulislamat/database-mcp/io.github.arifulislamat/database-mcp-sqlite MCP server

    5★ repo

    MCP server for SQLite databases. Read-only by default, row caps, statement timeouts.

  • innovationlab

    doc2mcp/doc2mcp/io.github.doc2mcp/innovationlab MCP server

    5★ repo

    MCP server for innovationlab documentation, generated by doc2mcp.

  • Mcp server

    gitscrum-core/mcp-server/io.github.gitscrum-core/mcp-server MCP server

    5★ repo

    MCP server for GitScrum — manage tasks, sprints, time tracking, and client workflows via AI

  • Horus flow mcp

    horustechltd/horus-flow-mcp/pro.horustek/horus-flow-mcp MCP server

    5★ repo

    Crypto & equity orderflow: whale detection, spoofing, liquidation heatmaps, smart money for AI

  • Subagent patterns

    VersoXBT/claude-initial-setup/skills/agent-orchestration/subagent-patterns Skill

    4★ repo

    Patterns for when and how to use Claude Code subagents via the Agent tool. Use when the user needs to delegate research, run parallel investigations, protect the main context window, or asks about subagent types like Explore or Plan.

    The same file is in 2 other repositories

  • Cookoff

    2389-research/test-kitchen/skills/cookoff Skill

    4★ repo

    This skill should be used when moving from design to implementation. Triggers on "let's build", "implement this", "looks good let's code", "ready to implement". Presents options for parallel agent competition (cookoff), single subagent, or local implementation. Each agent creates own plan from shared design for genuine variation.

    The same file is in 3 other repositories

  • Benchmark

    josephneumann/claude-corps/skills/benchmark Skill

    4★ repo

    Use when you need measured performance evidence by running a repeatable command on the current branch and a baseline ref

  • Midjourney prompting

    leggiemint/legnext-skills/midjourney-prompting Skill

    4★ repo

    Expert Midjourney prompt engineering skill. Use this skill when users need help crafting effective Midjourney prompts, converting natural language descriptions into optimized prompts, or want guidance on Midjourney parameters and techniques. Specializes in V7 best practices, the 7-Element Framework, and photography terminology.

  • Maw execute task

    pockerhead/maw/skills/maw-execute-task Skill

    4★ repo

    Adversarial multi-agent development pipeline. Use when the user says "take the next task", "work through tasks", "run the pipeline", or wants to implement a task from the task board with full planning, review, implementation, and QA cycle. Supports flags: --worktree (force worktree mode), --no-worktree (force branch-only mode). These override the saved setting for the current run only. Supports positional arg: a task number or ID (e.g. `/maw-execute-task 3`, `/maw-execute-task TASK-003`) to run a specific task out of priority order instead of picking the highest-priority pending task. Model-invocation is guarded: if invoked by the model rather than an explicit user command, the auto-invoke guard applies (see Invocation guard) — confirmation is required before any state change unless the user disabled the guard in maw/settings.json.

  • Fable orchestrate

    Zihao-Wu06/claude-code-orchestrate/vendor/fable-orchestrate Skill

    no license4★ repo

    Run a multi-model orchestration workflow with Fable 5 as the lead. Delegate reasoning-heavy work (architecture, debugging, algorithm design) to a deep-reasoner subagent (Opus), mechanical work (boilerplate, tests, formatting, bulk edits) to a fast-worker subagent (Sonnet), and fresh-perspective or high-stakes problems to Codex, a different-vendor GPT-5 peer. Use to orchestrate, delegate, fan out, get a second opinion from Codex, run Opus and Codex in parallel and synthesize, or act as tech lead.

  • Ableton mcp

    PerIPan/music-workflow-skills/ableton-mcp Skill

    4★ repo

    Use when controlling Ableton Live through the AbletonMCP server — creating tracks/clips/scenes, pushing MIDI notes, loading instruments or effects, setting device parameters, mixing, automation, or debugging the Live connection. Contains the hard limits and gotchas (note chunking, browser URIs, EQ Eight formulas, index shifts).

  • Agent owasp compliance

    MarieLynneBlock/arcanum-artifex/skills/agentic/agent-owasp-compliance Skill

    no license4★ repo

    Assess tool-using and multi-agent AI systems against OWASP ASI-style controls, mapping evidence to prompt injection, tool governance, agency, escalation, trust boundaries, audit, identity, policy integrity, supply chain, and behavioural monitoring risks.

  • Claude design prompter

    erenisci/claude-design-prompter/claude-design-prompter Skill

    4★ repo

    DEPRECATED — use Acta (acta-design-prompt) at https://github.com/erenisci/acta. Using brand decisions established by /claude-design-brand, generate paste-ready Claude Design prompts (and persist files) for Logo, All-Pages (every detected app page in one doc), or Landing — and resolve Claude Design follow-up questions consistently. Trigger on /claude-design-prompter, "generate logo prompt", "generate all pages", "generate landing", "answer Claude Design question".

  • Agents md generator

    n-n-code/n-n-code-skills/.agents/skills/agents-md-generator Skill

    4★ repo

    Create or revise repository AGENTS.md files from repo inspection, existing docs, and a small number of high-impact clarifications. Use when the user asks to create an AGENTS.md, improve agent instructions for a repo, convert CLAUDE.md-style guidance into AGENTS.md, or write coding-agent instructions for a repository.

  • Cookbook

    DjordjeMojsilovic/Djordjes-Claude-Setup/cookbook Skill

    no license4★ repo

    Use this skill whenever the user is building something with the Claude API and would benefit from a known-good reference implementation from Anthropic's official Claude Cookbooks. Trigger on any request that touches Claude API features — RAG, tool use, agents (Agent SDK or Managed Agents), vision/multimodal, prompt caching, batch processing, extended thinking, citations, JSON mode, message batches, finetuning, evals, skills, memory, parallel tools, structured output, sub-agents — or on integrations (Pinecone, MongoDB, LlamaIndex, Wikipedia, Wolfram, ElevenLabs, Deepgram, VoyageAI). Trigger even when the user doesn't explicitly say "cookbook": questions like "how do I do X with Claude", "what's the recommended pattern for Y", "show me how to build Z with the Anthropic API", "I want to add tool use to my app", or "best way to handle long contexts" should pull this skill. Do NOT trigger for unrelated coding questions, Claude.ai UI questions, or pure prompting questions that don't involve the API.

  • Obsidian archive

    bgorkem/bgorkem-skills/plugins/obsidian-archive/skills/obsidian-archive Skill

    4★ repo

    Distils the current conversation into a concise reference note and saves it to the user's Obsidian vault in a configurable archive folder. Requires the mcp-obsidian MCP server. Use when the user asks to archive, save, log, capture, or file away the current conversation/chat/session — e.g., "archive this conversation", "save this to my vault", "add this to Obsidian", "remember this for later". Do not use for saving arbitrary content the user has pasted in.

  • Init project memory

    jkm-4314/claude-code-skills/init-project-memory Skill

    4★ repo

    Use when the user says "init memory", "set up memory", "scaffold memory", "init project memory", or invokes /init-project-memory — creates the .claude/ session memory system in a new project

  • Dispatching parallel agents

    izyanrajwani/agent-skills-library/skills/dispatching-parallel-agents Skill

    no license4★ repo

    Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared state or ordering dependencies.

    The same file is in 8 other repositories

  • Gemini prompting

    dysfunc/ai-plugins-cc/dist/plugins/gemini/skills/gemini-prompting Skill

    4★ repo

    Internal guidance for composing Gemini prompts for planning, research, diagnosis, and review tasks inside the Gemini Claude Code plugin

  • Supreme ai engineering

    davccavalcante/supreme-coding-guidelines-skill.ah/skills/supreme-ai-engineering Skill

    no license4★ repo

    Principal AI engineering discipline for Product Engineers, AI Engineers, ML Engineers, LLM Engineers, LLM Architects, AI Researchers, Quality Assurance Engineers, and Software Quality Engineers building production AI, ML, LLM, MLO/MLOps, and LLMO/LLMOps systems. Forces eval-first design (golden datasets and acceptance thresholds defined before code), deterministic feedback loops (telemetry, drift detection, regression eval gates) before first production user, pipeline discipline (data → feature → train → register → deploy → monitor with input/output contracts at every gate), prompt and model governance (versioned registries with semantic versioning, A/B + canary + shadow + dark launch as standard), production reliability (graceful degradation, circuit breakers, prompt-injection defense, chaos testing), QA discipline (golden test sets, regression gates in CI, statistical significance for research claims, ablation completeness, dataset contamination checks), and operational excellence (observability, runbooks, post-incident review, continuous calibration). Requires ah-parser. Output mode follows the user preference set at parser activation; user code, prompts, eval outputs, logs, traces, and model artifacts are always preserved verbatim.

  • Indykite authzen evaluation

    indykite/skills/indykite-authzen-evaluation Skill

    4★ repo

    Make a single KBAC authorization decision via the IndyKite AuthZEN REST API (`POST /access/v1/evaluation`) - returns a boolean `decision` for one (subject, action, resource) triple, optionally with per-request `context.input_params`. Use for a single yes/no question - "can ada PROVISION gpu-node-7?", "is this user allowed to delete this document?", "gate this operation on a live check", or debugging why one decision is false. Not for many checks at once (use indykite-authzen-evaluations), not for enumerating which actions/resources/subjects are allowed (use indykite-authzen-search-action / -search-resource / -search-subject), and not for authoring the policy behind the decision (use indykite-authzen-kbac-policies). For the same decision over MCP/JSON-RPC see indykite-mcp-server (`authzen_evaluate`).

  • Handoff

    keli-wen/skills/skills-zh/handoff Skill

    no license4★ repo

    当另一个 agent 或 session 要接管任务或继续未完成工作时,生成最小充分交接。触发语:/handoff、「把任务交给下一个 agent」「生成 handoff」「让另一个 session 继续」、session 转移、任务所有权转移,或当前上下文退化时重开一个干净 session(交接给未来的自己)。持久 artifact 用引用不用复制,输出前抹掉 secrets。

  • Agent docs

    SteveVitali/agent-skills/skills/agent-docs Skill

    4★ repo

    Create or converge agent documentation (AGENTS.md hierarchy) for a codebase — bootstrap mode generates docs from scratch, refresh mode detects and fixes drift

  • Tool design

    agentailor/skills/tool-design Skill

    4★ repo

    Design tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise). Use when writing a new tool for an agent, reviewing or fixing an existing tool definition, deciding how to split capabilities into tools, or debugging why an agent misuses, mis-selects, or floods its context with a tool. Applies equally to standalone tools and MCP-server tools — a tool is a tool.

  • Claude agent converter

    dceoy/ai-coding-agent-skills/skills/claude-agent-converter Skill

    4★ repo

    Agent skills for AI coders

  • Ai build quality

    05-deepak-patidar/claude-skills/ai-build-quality Skill

    4★ repo

    Getting reliably high-quality software out of ANY AI model (Claude, GPT, Gemini, local models) — task packaging, context, verification, and drift control. Use when delegating coding work to an AI model, writing prompts/specs for AI-driven development, reviewing AI-generated code, setting up CLAUDE.md/AGENTS.md-style project instructions, or when the user says "have the AI build", "prompt for", "why did the model do this wrong", or "AI code review".

  • Agent team mesh

    Songhonglei/better-agent-skills/skills/agent-team-mesh Skill

    4★ repo

    Team-wide P2P mesh for OpenClaw agents running on different containers/pods. Each agent's gateway listens on its own pod IP:18789 over WebSocket; the mesh CLI lets you ping, send-and-await-reply, broadcast, and discover the whole team. No broker, no Supabase, no central server — just direct WS calls between teammates' agents. Includes auto-detect of "this machine's identity" (USER.md / sso.json / env var), secure token storage (separate chmod 600 file, not committed to git), message size limits (4KB warn / 8KB block), --dry-run preview for both send and broadcast, and an optional IM fallback hook when an agent is unreachable. Triggers: "message my teammate's agent", "ping bob's agent", "broadcast to the team", "agent mesh", "team agent communication".

  • Claude md rules creator

    anilcancakir/claude-code/plugins/ac/skills/claude-md-rules-creator Skill

    4★ repo

    Plan-first development partner for Claude Code: interview-driven plans, tier-routed agents (haiku/sonnet/opus), and an adversarial review chain that verifies through real usage.

  • Yocto agent suite

    prashantdivate/awesome-yocto-ai-agent-skills/yocto-agent-suite Skill

    4★ repo

    One-router Yocto Project skill suite for AI coding agents. Use when a request mentions Yocto, OpenEmbedded, Poky, BitBake, embedded Linux builds, BSPs, board flashing, QEMU boot tests, CI/release automation, security hardening, CVE review, secure boot, OTA updates, firewall policy, or when the right specialized Yocto skill is unclear.

  • Company context agent

    EthanYoQ/AgentHive/roundtable-skills/company-context-agent Skill

    4★ repo

    AgentHive 圆桌职能角色 Skill:公司上下文 Agent。用于商业策略讨论中的维护公司战略、资源、能力和历史约束的上下文。 当用户选择「Company Context Agent」「公司上下文 Agent」或需要该职能参与圆桌时使用。

  • Agent forge

    sinclarespeaking143/openclaw-superagent/skills/agent-forge Skill

    no license4★ repo

    Создание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агента (9 шагов, с памятью и автоулучшением), улучшение существующего (5 шагов). Triggers: 'создай скилл', 'новый скилл', 'создай агента', 'новый агент', 'улучши скилл', 'skill creator', 'agent creator', 'скиллмейкер'.

    The same file is in 1 other repository

  • Gemini embeddings

    akrindev/google-studio-skills/skills/gemini-embeddings Skill

    no license4★ repo

    Generate text embeddings using Gemini Embedding API via scripts/. Use for creating vector representations of text, semantic search, similarity matching, clustering, and RAG applications. Triggers on "embeddings", "semantic search", "vector search", "text similarity", "RAG", "retrieval".

  • Elnora agent

    Elnora-AI/elnora-plugins/elnora/skills/elnora-agent Skill

    4★ repo

    This skill should be used when the user asks about "Elnora agent capabilities", "what can the agent do", "what tools does Elnora have", "what can Elnora do", "agent tools", "web search", "academic search", "PubMed", "ArXiv", "Exa", "Tavily", "Perplexity", "Valyu", "ToolUniverse", "scientific tools", "agent memory", "code execution", "sandbox", "search papers", "search literature", "drug discovery", "protein analysis", "clinical trials", "file operations", "agent skills", or any question about what the Elnora AI Agent can do when you send it a task.

    The same file is in 1 other repository

  • Claude worker

    Syysean/web-ai-skills/claude-worker Skill

    4★ repo

    Use this skill to send a prompt to Claude.ai and get a response. Triggers when the user wants to query Claude.ai via browser, use Claude as an external AI worker, or when the web-ai-router directs a task to Claude. Best for general QA, writing, analysis, and coding tasks. Requires login — session is persisted in Chrome profile.

  • Crux wiki

    mehdiforoozandeh/crux/skills/crux-wiki Skill

    4★ repo

    A literature wiki for a crux research vault — Andrej Karpathy's LLM-wiki pattern applied to a crux project. The PI curates immutable sources under `raw/`; you (the agent) compile them into a persistent, interlinked `wiki/` of background, prior methods, SOTA, baselines, datasets, and definitions, and draw on it to ask sharper questions and design better hypotheses. The crux engine owns the bookkeeping (source hashes, the generated `WIKI.md` index, structural lint via `crux validate`); you supply the reading and synthesis. One-way by design: literature → wiki → informs the tree; a project's own findings never enter the wiki. Use when a crux user wants a project-relevant literature base. Triggers: "ingest this paper", "add to the wiki", "what does the literature say", "compile a wiki", "lint the wiki", literature review, prior work / SOTA / baselines for a crux project, crux wiki, LLM wiki.

  • Ruledoctor

    syf2211/ruledoctor/skills/ruledoctor Skill

    4★ repo

    Use when the project has rule files (CLAUDE.md, AGENTS.md, .cursorrules, CONTRIBUTING.md, .github/copilot-instructions.md, .cursor/rules) or .ruledoctor.json required_reads; before git push, deploy, bulk delete, or when context was compacted. Read listed rules and required_reads first; refuse violations; re-read after long sessions. Default user message: files read + 3 hard constraints only unless user asks for full summary.

  • Korg recall mcp

    New1Direction/korg/io.github.New1Direction/korg-recall-mcp MCP server

    4★ repo

    Cross-vendor semantic memory: recall across Claude Code / Codex / Grok sessions by meaning.

  • Calendarmcp

    aernouddekker/macos-mcp/io.github.aernouddekker/calendarmcp MCP server

    4★ repo

    MCP server for macOS Calendar.app — calendar and event management via AppleScript

  • Agenium mcp server

    Aganium/agenium/io.github.chorghemaruti64-creator/agenium-mcp-server MCP server

    4★ repo

    Bridge MCP servers to the AGENIUM agent:// network via DNS discovery

  • Flyto indexer

    flytohub/flyto-indexer/io.github.flytohub/flyto-indexer MCP server

    4★ repo

    Code intelligence MCP server — impact analysis, semantic search, dependency graphs

  • Claude mail bridge team rules

    CodingJay-1/claude-mail-bridge/src/claude_mail_bridge/assets/skills/claude-mail-bridge-team_rules Skill

    3★ repo

    Use when operations involve emailing teammates (mail_teammates MCP tool). Defines strict privacy rules for team communication.

  • Cf handoff

    QBall-Inc/clear/skills/cf-handoff Skill

    3★ repo

    Generate a session handoff document. Use when ending a session, reaching token thresholds, or previewing handoff contents.

  • Bootstrap

    TimboGP/timbogp-marketplace/plugin/agentic-study-environment/skills/bootstrap Skill

    3★ repo

    Scaffold a new learning sub-project under the agentic-study-environment harness — create the directory, generate per-project AGENTS.md, CLAUDE.md, and PROGRESS.md from templates, and register the new project in the .studyenv/PROGRESS.md cross-project tracker. Use this skill whenever the user wants to start studying a new topic, paper, book, language, or domain with the tutor harness — phrases like "bootstrap a new project to learn X", "start a new sub-project for Y", "set up a learning project on Z", or "create a sub-project to study W" should all trigger this skill. Do not use for general project scaffolding outside the agentic-study-environment harness.

  • Openclaw

    AwardTravelFinder/award-travel-finder-plugin/openclaw Skill

    3★ repo

    Search award flight availability across 19 airlines and compare 14 loyalty program award charts via the Award Travel Finder MCP server. Find the best points and miles redemptions across British Airways, Qatar Airways, Cathay Pacific, Virgin Atlantic, Aeroplan, Iberia, Emirates, Qantas, Alaska, American, JetBlue, ANA, Singapore, Turkish, Etihad, Flying Blue, and more.

  • Ai engineer

    CODE-SAURABH/OpenSkills/ai-engineer Skill

    3★ repo

    Expert AI/LLM engineering guidance. Use when the user asks about RAG, OpenAI, Azure OpenAI, prompt engineering, AI agents, MCP, vector databases, or evaluation pipelines.

  • Claude chinese document style

    hachiwar/codex-skills/claude-chinese-document-style Skill

    no license3★ repo

    Create, edit, review, or standardize Simplified Chinese documents in Claude Code using formal academic and technical writing conventions. Use whenever Chinese Markdown, README files, reports, papers, specifications, product documentation, or prose needs correction of Chinese-English spacing, punctuation, numbers, units, terminology, headings, paragraphs, lists, tables, links, citations, or code formatting; removal of colloquial, promotional, or AI-like wording; or consistent editorial revision without changing technical meaning.

  • Session export

    y-a-v-a/session-export/skills/session-export Skill

    3★ repo

    Export the current (or a specified) Claude Code or OpenAI Codex session to a single self-contained HTML file, including any subagent transcripts. Use when the user asks to "export this session", "save the chat as HTML", "share this conversation", or wants an offline-readable record of a coding-agent session.

  • Aris novelty check

    JZKK720/cubecloud-skilldbundle-setup/upstream/aris-novelty-check Skill

    no license3★ repo

    Verify research idea novelty against recent literature. Use when user says "novelty check", "check novelty", "has anyone done this", or wants to verify a research idea is novel before implementing. Ported from wanshuiyin/Auto-claude-code-research-in-sleep (ARIS) — methodology only, Claude-Code-specific MCP deps stripped for VS Code Copilot.

  • Ai agent ux

    varunk130/ai-ux-skill-library/skills/ai-agent-ux Skill

    3★ repo

    Design user experiences for autonomous AI agents that act on behalf of users - control panels, consent flows, action previews, audit trails, and undo mechanisms. Use when: agentic AI, autonomous agents, AI autonomy controls, agent UX, AI actions, computer use, agent consent, agent audit trail.

  • Prompt pyramid

    storyAura/lora-tagging-skills/prompt-pyramid Skill

    3★ repo

    Reorder and purify scattered image-generation tags (Stable Diffusion, Flux, NovelAI, ComfyUI, WebUI, danbooru-style booru tags) into a single clean comma-separated prompt string built on a visual-weight pyramid. Use this skill PROACTIVELY whenever the user is writing or fixing a prompt for diffusion models — tags scattered across a list, an unordered tag dump, a character sheet needing a prompt, "help me organize these tags", "clean up this prompt", "why is the color bleeding onto the skin", "extra limbs / floating accessories", or any mention of 1girl/1boy, trigger words, LoRA character prompts, booru tags, danbooru tags, or ComfyUI/WEBUI positive prompt boxes. Also use it when the user pastes a raw tag list and wants it production-ready. Do not use it for natural-language conversational prompts (e.g. Midjourney-style sentences) — this skill is for comma-separated booru-style tags only.

  • Antigravity

    vibhasdutta/loop-engineer/platforms/antigravity Skill

    no license3★ repo

    Loop engineering wizard for Antigravity. Asks 3 questions, then orchestrates a fully autonomous parallel agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) until the goal is met. Uses invoke_subagent for true parallel dispatch. Researcher agents use the built-in research TypeName. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, no changes). Persistent memory, git integration.

  • Stack doctor

    drmahdikazempour/agent-stack/skills/stack-doctor Skill

    3★ repo

    Lint the agent-stack setup — CLAUDE.md token budget (≤800), each SKILL.md description (≤1024 chars) and body (≤500 lines), hook conflicts in settings.json, frontmatter validity, and adapter availability. Use when something feels off, before committing config changes, or to confirm a healthy setup. Wraps `agent-stack doctor`; exit code 1 means there are issues to fix.

  • Agents md writer

    jqaisystems/jqai-ai-skills/skills/agents-md-writer Skill

    3★ repo

    Generate the dual-agent workspace contract, an AGENTS.md skill registry plus a CLAUDE.md pointer, so one set of skills serves both Claude Code (which auto-discovers them) and agents like Codex (which need required-reading instructions). Use when the user says "set up AGENTS.md", "make my skills work in Codex too", "dual agent setup", or "workspace contract".

  • Agent browser

    magnusrodseth/dotfiles/.claude/skills/agent-browser Skill

    no license3★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

    The same file is in 2 other repositories

  • Skill discovery optimizer

    Bing-Bryan/skills-by-bing/skill-discovery-optimizer Skill

    3★ repo

    Audit, optimize, publish, and distribute existing Agent Skills whose core behavior already works. Invoke automatically as a preflight whenever the user asks to publish, release, sync, push, update, or upload one or multiple Agent Skills—or a skills monorepo—to GitHub, skills.sh, an Agent Skill marketplace, registry, or curated directory, even if they do not name this optimizer. Trigger for "把所有 Skills 更新到 GitHub", "同步 Skills 仓库并发版", "把这个 Skill 发布到其他技能市场", "publish these Agent Skills and verify installation", "audit my skill before publishing", "减少这个 Skill 的误触发", or "优化 Skill description 和 GitHub metadata". Review semantic routing, trust, installability, bilingual release materials, remote installation, and listing. Do not use to build core functionality, install someone else's skill, publish an ordinary non-skill repository, do generic bilingual README work or web GEO/SEO, run long-term growth analytics, or publish an MCP server.