agentsclimarketplace

Context & AI engineering

25,991 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

  • Idea to architecture agent

    aetox-skills/idea-to-architecture-agent Skill

    4★

    Question-first architecture proposal discipline for AI agents. Use when a user provides a raw idea, product concept, feature request, business goal, or system goal without an existing implementation and needs a reviewable architecture proposal with assumptions, open questions, risks, decision options, workflows, module boundaries, and handoff notes.

  • Skill creator plus

    yaniv-golan/skill-creator-plus/skill-creator-plus/skills/skill-creator-plus Skill

    4★ repo

    Based on Anthropic's skill-creator — with bug fixes, working Cowork support, and official best practices baked in. Claude skill for creating, testing, and improving other Claude skills.

  • Ai and agents

    toolbox-playground/super-claudio/skills/ai-and-agents Skill

    4★ repo

    AI integration and agent building skill. Use when the user wants to use the Claude API, build AI-powered apps, create Claude Code skills or agents, connect MCP servers, or improve their prompts and AI workflows. Trigger on: "use the Claude API", "Anthropic API", "build an AI app", "create a Claude skill", "write a skill for Claude Code", "build an agent", "MCP server", "Model Context Protocol", "connect Claude to X", "prompt engineering", "improve my prompt", "system prompt", "AI workflow", "LLM integration", "build a chatbot", "fine-tuning", "Claude Code plugin", "create a plugin", "AI pipeline", "multi-agent", "tool use", "function calling". Also trigger when the user mentions: superpowers, skill-creator, claude-md-management, pr-review-toolkit, context7, or any Claude Code plugin by name. Do NOT trigger for: general code questions without AI integration (use software-development).

  • Handoff

    ananthanandanan/skills/skills/engineering/handoff Skill

    4★ repo

    Generate a Markdown handoff document summarizing the current conversation so another agent (Claude, Codex, opencode, pi, ampcode, Cursor, or a fresh session) can resume without re-deriving context. Produces docs/<slug>-handoff.md. Invoke explicitly when a session is near its context limit.

  • Slop score skill

    closestfriend/slop-score-skill Skill

    no license4★

    Run Sam Paech's eqbench Slop Score heuristic against a piece of writing — scores AI "slop" (overused words, slop trigrams, and "not X, but Y" contrast patterns) on a 0–100 scale and flags the specific offending phrases. Use when the user wants to slop-score writing, check a draft for AI-slop / GPT-isms, or get a Paech-style slop readout. Independent of any literary-critic agent or persona.

  • Indykite agent gateway

    indykite/skills/indykite-agent-gateway Skill

    4★ repo

    Deploy and configure IndyKite Agent Gateway (IAG) in front of agent-to-agent (A2A) workflows or MCP servers. Use when wiring up A2A or MCP policy enforcement, modeling workflows in the IKG, or debugging IAG 401/403 responses.

  • Image generation

    ahmedraza28/image-generation-skill/skills/image-generation Skill

    4★ repo

    Best practices for prompting any text-to-image model (e.g. Imagen, Gemini Image, GPT Image, DALL·E, Stable Diffusion, Flux, Ideogram, Leonardo, Midjourney) to produce predictable, production-quality images. Use this skill whenever the task involves calling an image generation API, generating images programmatically, writing or revising prompts for image models, producing illustrations / photos / logos / posters / mockups / infographics / UI shots with AI, or debugging poor image output. Apply this even when the user just says "generate an image of X" — well-structured prompts dramatically outperform terse ones across every current model, and the cost of a bad prompt is almost always paid in retries.

  • Agent browser locale

    magarcia/skills/skills/agent-browser-locale Skill

    4★ repo

    Test locale- and i18n-specific browser behavior with agent-browser by forcing a non-English JavaScript runtime locale through CDP. Use when reproducing or verifying bugs involving date/time markers, number or currency separators, Intl APIs, RTL behavior, or behavior that differs under locales such as sv-SE, tr-TR, zh-TW, de-DE, or ar-EG.

  • Agent eval harness

    megandmartin/agent-skills-repo/skills/agent-mastery/agent-eval-harness Skill

    4★ repo

    Builds and runs a mini eval for any skill or agent task — 3–5 test prompts, an expected-behavior rubric, a pass threshold set before running, then a scored verdict table. Use when the user says "eval this skill", "does this actually work", "test the agent on this", "build an eval", or before trusting any new skill, prompt change, or model swap. Don't use for choosing which model tier to run once the eval exists — that's model-cost-optimizer.

  • Agent prompt engineering

    agentailor/skills/agent-prompt-engineering Skill

    4★ repo

    Comprehensive guide for designing effective system prompts for autonomous AI agents based on Anthropic's production practices. Use when creating or refining prompts for agents that operate in loops with tool access, including when asked to write agent instructions, system prompts, agent configurations, or when improving agent reliability and decision-making capabilities.

  • Agent browser

    Firzus/agent-skills/skills/engineering/agent-browser Skill

    4★ repo

    Drive a real browser from the CLI — navigate, snapshot, click, fill, screenshot, emulate. Use when the user wants to interact with a website, test or review a web UI, take screenshots, extract page data, or attach to a CDP endpoint (Chrome, Tauri/WebView2, Electron), or when another skill needs browser evidence.

  • Council

    Endokelp/DecisionCouncil/skills/council Skill

    4★ repo

    Evidence-bound multi-agent council for high-stakes decisions. Scout uses last30days, Advocate and Skeptic debate, Fact Checker uses deep-research Quick mode. Delivers ranked options with #1 marked, dissent preserved, and the condition that would flip the verdict. Use when user says council this, /council, run the council, pressure-test this, stress-test this, war room this, debate this, or names this skill for vendor, architecture, purchase, or strategy forks. Lite by default. Not for code review, trivia, or cheap reversible choices. Cursor and Claude Code.

  • Create handoff

    EnkrateiaLucca/skills/skills/create-handoff Skill

    4★ repo

    Write a structured, timestamped handoff document that captures the current session's context (what was done, what changed, key learnings, next steps) so a fresh agent session can resume the work without replaying the prior conversation. Use when the user says "create a handoff", "save a handoff", "write a status.md", "end-of-session summary", "save session context", or wants to wrap up a working session so it can be picked up later.

  • Add skill

    Paldom/icon-designer-skills/.claude/skills/add-skill Skill

    4★ repo

    Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).

    The same file is in 11 other repositories

  • Harness map

    dreamiurg/harness-map/skills/harness-map Skill

    4★ repo

    Generate an interactive, self-contained HTML dependency map of a repository's AI harness — skills, slash commands, agents, and MCP servers, with typed evidence-backed edges showing which skills hand off to which, what delegates to which agents, and what uses which MCP servers. Use when the user asks to map, visualize, diagram, or audit their agent harness, skills, subagents, or MCP setup. Works on any repo with .claude/, skills/, or .mcp.json surfaces. Output is a single offline HTML file.

  • Agent registry

    srinandan/agent-registry-skill/agent-registry Skill

    4★ repo

    Use this skill whenever the user wants to interact with Google Cloud's Agent Registry using gcloud commands. Triggers on any mention of "agent registry", "agent-registry", "mcp-servers", "gcloud agents", "register an agent", "list agents", "create a service", "agent service", or any request to manage agents, MCP servers, endpoints, or services in Google Cloud Agent Registry. Also triggers on requests to integrate or use the Google Agent Development Kit (ADK) with the Agent Registry.

  • Ai agent design

    05-deepak-patidar/claude-skills/ai-agent-design Skill

    4★ repo

    Designing and building AI agents — tool design, agent loops, context management, permissions/guardrails, memory, multi-agent orchestration, MCP, and agent evaluation. Use when building an agent that takes actions (calls tools/APIs, writes files, automates workflows), designing tool schemas, debugging agent misbehavior, or when the user says "AI agent", "agentic", "tool calling", "function calling", "MCP server", "autonomous", or "multi-agent".

  • Graphsmith

    SathiaAI/graphsmith Skill

    4★

    Build and fix reliable multi-agent AI workflows for any skill level, from first-time builders to senior engineers. ALWAYS use this skill when the user asks to "build an agent", "automate" a task or workflow, wants "AI to do X for me", describes a multi-step job, mentions agents, bots, pipelines, swarms, or orchestration, or has an automation that "keeps breaking", "forgets where it left off", "loops forever", "duplicates work", or "makes stuff up". Also use to review, harden, or migrate an agent loop to a multi-agent architecture, or when multiple agents or sessions must build in parallel without conflicts ("agents keep overwriting each other", "coordinate parallel agents"). Trigger even if the user never says "agent". Includes an executable scaffolder, architecture linter, crash-recovery test harness, and multi-agent coordination rules, plus KnoSky grounding (auto-updated) so answers about existing code carry citations instead of guesses.

  • Ltspice

    svd-ai-lab/sim-plugin-ltspice/src/sim_plugin_ltspice/_skills/ltspice Skill

    4★ repo

    Use when the user asks Codex, Claude Code, or another AI coding agent to run, inspect, or debug LTspice circuits through sim-cli. Supports circuit simulation, waveform/log inspection, replayable artifacts, and troubleshooting.

  • Agent avatar manager

    Songhonglei/better-agent-skills/skills/agent-avatar-manager Skill

    4★ repo

    Manage your OpenClaw Agent's avatar. Send an image/URL directly, or describe a style and let Freepik vector search pick candidates for you. Auto-saves to the workspace avatars/ directory and updates IDENTITY.md. 当用户说「换头像」「找一张头像」「更新头像」「给我换个头像」「change avatar」时使用。 Requires a free Freepik API Key for auto-search mode (direct image/URL mode works without it). OpenClaw-only — relies on `openclaw agents set-identity`, `IDENTITY.md`, and `TOOLS.md` conventions.

  • Rhwp gui agent

    leeryong/rhwp-Agent-Skills_by_BLUESKY/skills/rhwp-gui-agent Skill

    no license4★ repo

    Control, test, and extend the rhwp web HWP/HWPX editor through its browser GUI and agent automation bridge. Use when an AI agent needs to run rhwp-studio, open or create HWP/HWPX files, exercise menus/toolbars/dialogs, verify document editing features, automate GUI operations with Puppeteer/CDP, use the hwpctl compatibility layer, or analyze rhwp commands, menus, and editor capabilities.

  • Agent creator

    anilcancakir/claude-code/plugins/ac/skills/agent-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.

  • Junyi ai weekly review

    junyifei/junyi-skills/junyi-ai-weekly-review Skill

    no license4★ repo

    AI 周度复盘。把你这一周和各个 AI agent 的日常协作记录,本地收集、清洗、脱敏并按天蒸馏,沉淀成《本周记录》(给自己看的事实底账加复盘)和《本周内容素材》(能直接写成内容的片段)两份本地 Markdown,每条都标原始出处。一周跑一次、抓过去 7 天。采集脚本不联网;蒸馏内容是否发送给模型服务商取决于所用 Agent,使用云端模型前必须告知并取得确认。内置 Claude Code、OpenClaw、Codex 适配器(已验证)与 custom 兜底(Hermes、WorkBuddy 为占位待验证)。需要本机装 Node.js。触发词:AI周度复盘、周报、本周AI复盘、本周和AI干了什么、ai weekly review、复盘这周的AI对话。

  • Agent estate

    MercuriusDream/agent-estate Skill

    no license4★

    Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.

  • Agamotto

    ShockRock2004/kamar-taj/agamotto Skill

    4★ repo

    Agamotto — adversarial AI code/plan review with foresight. Opens the Eye of Agamotto banner on summon and does a quick foresight self-review, then sends the work to an external reviewer (Codex, or a fresh Claude reviewer subagent if codex is not installed or configured) while Claude fixes, looping until approved. Auto-detects plan/code/code-vs-plan mode. Invoke with /agamotto.

  • Memory cli

    pygent-ai/memory-cli/skills/memory-cli Skill

    4★ repo

    Build, query, test, and optimize a local agent memory CLI where durable memories are represented as retrieval unit tests. Use when the user asks Codex to create, maintain, inspect, or improve a memory-cli project; when a workspace already contains a memory-cli, .memory, or memories project; or when Codex must add, update, retire, or validate durable memory records through a CLI contract.

  • Agent design

    tienenwu/fables/agent-design Skill

    4★ repo

    Use when creating a new custom agent/subagent definition (.claude/agents/*.md), auditing or rewriting existing agent definitions, deciding whether a task deserves a dedicated agent vs general-purpose with a good prompt, choosing an agent's tools whitelist or model tier, or when delegated agents keep going off-scope, dumping full transcripts back, or overlapping each other's roles.

  • Agentic dev docs

    mayuri-wylty/agentic-dev-docs Skill

    no license4★

    Strict manual-trigger skill for docs-first agentic software development planning. Use only when the user explicitly names `agentic-dev-docs`, says `use agentic-dev-docs skill`, invokes `$agentic-dev-docs`, or directly asks to run this exact skill.

  • Session recall

    iouovonoi/session-recall/session-recall Skill

    no license4★ repo

    Let your agent proactively recall local Copilot CLI sessions and reconnect past ideas.

  • Eval coach

    BayramAnnakov/eval-coach Skill

    4★

    Guide users through building comprehensive AI evaluation strategies using Evaluation-Driven Development (EDD)

  • Benchmark agents

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/.claude/skills/benchmark-agents Skill

    4★ repo

    Advanced AI agent benchmark scenarios that push Vercel's cutting-edge platform features — Workflow DevKit, AI Gateway, MCP, Chat SDK, Queues, Flags, Sandbox, and multi-agent orchestration. Designed to stress-test skill injection for complex, multi-system builds.

  • Intelligence add agent

    ainova-systems/intelligence-sync/intelligence/sync/skills/intelligence-add-agent Skill

    4★ repo

    Create new specialized agent

  • Agent doctor

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

    no license4★ repo

    Самодиагностика и автолечение OpenClaw. Проверка gateway, WAL, памяти, кронов, токенов. Автоматическое исправление типичных проблем.

    The same file is in 1 other repository

  • Openfoam

    svd-ai-lab/sim-plugin-openfoam/src/sim_plugin_openfoam/_skills/openfoam Skill

    4★ repo

    Use when the user asks Codex, Claude Code, or another AI coding agent to run, inspect, or debug OpenFOAM cases through sim-cli. Supports case checks, solver execution, log inspection, result artifacts, replayable CFD workflows, and benchmark tasks.

  • Humanize korean

    mskim8717/skill-runner/.claude/skills/humanize-korean Skill

    no license4★ repo

    AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 40+ AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스러운 한국어로 재작성한다. 트리거 — "AI 티 없애줘", "AI 같은 글 자연스럽게", "GPT/ChatGPT 문체", "AI 번역투 고쳐", "사람이 쓴 것처럼 윤문", "AI 윤문", "ChatGPT 티 제거", "한글 AI 탐지·윤문", "AI 글 사람처럼", "번역투 제거", "영어 인용 많은 글 윤문", "AI 글 티 안 나게", "휴머나이저", "humanize Korean", "AI detector bypass 한글". 후속 작업 — "특정 카테고리만 다시", "윤문 강도 조정", "장르 바꿔서", "이 문단만", "2차 윤문" 도 모두 이 스킬. 단순 맞춤법·오탈자 교정은 직접 처리, 번역은 번역 스킬, 내용 추가·삭제를 동반한 재작성은 별도 집필 스킬.

  • Multi agent governance

    levelsofself/mcp-nervous-system/skills/multi-agent-governance Skill

    4★ repo

    Use this skill when building, managing, or auditing multi-agent AI systems. Provides governance patterns for behavioral enforcement, drift detection, audit trails, role management, and accountability across autonomous AI agents. Compatible with any orchestration framework.

    The same file is in 1 other repository

  • Personal humanizer maker

    TaewoooPark/personal-humanizer-maker/skills/personal-humanizer-maker Skill

    4★ repo

    Feed in a Korean or English sample of your own writing, and this meta-skill (a skill factory) decomposes its style and argument flow with a quantitative profiler plus one specialist agent per axis, then auto-generates a personal humanizer skill. The output is a standalone humanize-NAME skill for the current host: Claude Code emits under ~/.claude/skills, while Codex emits under the Codex skill root. It includes SKILL.md, style_metrics.py with the author's baselines baked in, and before/after examples mined from the author's own text. A meaning-invariance covenant is injected into every generated skill. Triggers — "make a personal humanizer from my writing", "build a humanizer skill in my voice", "personal humanizer maker", "profile my writing style into a skill", "내 문체로 다듬는 스킬 만들어줘", "이 글로 개인 휴머나이저 빌드", "내 voice 스킬 제작", "샘플 넣으면 내 문체 뽑아주는 거". Rewriting a single text is the job of an already-generated personal skill; THIS skill is the factory that stamps those personal skills out.

  • Meta skill creator

    KimYx0207/meta-skill-creator/skills/meta-skill-creator Skill

    4★ repo

    创建、重构或验收可复用技能包。适用于把重复工作流做成跨宿主能力包,并明确触发规则、第一动作、渐进加载、资产模板、脚本校验、触发评测、基线对比、验收证据、闭环治理、公开交付边界和不可伪造的运行证明;也适用于清理冗余参考、拆分人读模板与机器结构数据、补齐首次公开前的验收记录、记录运行反馈、生成写回或不写回决定。当用户提到"做一个 skill / 改 skill / 优化 skill / 评审 skill / 加 trigger eval / 加 release gate / 加 baseline / 准备开源 / 做闭环 / 写回改进"时,必须使用本技能;不要用普通提示词改写 SKILL.md。一旦涉及 skill 设计、改写、评审、对比、验收、量化打分、冗余清理、frontmatter 加字段、加 license、加 compatibility、闭环复盘,立刻调用本 skill。

  • Claude review

    sandover/agent-skills/skills/claude-review Skill

    no license4★ repo

    codex and claude skills repo

  • Cross model handoff

    ntaffzii/Skill-Agents/Skill.md/cross-model-handoff Skill

    4★ repo

    Create continuation notes that another model, provider, or agent can resume without relying on hidden context or exact tool names. Use when the user asks to hand off work between Claude, ChatGPT, Gemini, Codex, local agents, or another MCP-enabled assistant.

  • Kimi skill

    cilidinezy-commits/doc-harness/kimi-skill Skill

    4★ repo

    Document-based project control that lets any AI agent or human resume work from files alone — no external memory needed. Use this skill whenever the user wants to structure a long-running project, track progress across sessions, recover state after context loss, coordinate multiple agents on the same project, audit project documentation health, or stop forgetting what was done last session. Triggers include: 'help me set up this project', 'I keep losing track', 'my agent forgets between sessions', 'organize my project docs', 'audit this project', 'check the documentation', 'what did we do last time', 'update the status docs', 'sync the project state', 'save everything before context compresses', 'flush context', 'prepare for compact', 'register this new file', 'init doc-harness', 'recall', 'remember', 'find in docs', 'search project docs', 'where did we discuss', 'why did we decide', 'what is the current plan', 'summarize what we know about'; multi-week projects (theses, research, analyses, software modules) that span many sessions; cross-project coordination (inbox/outbox for file-based messages between projects); requests to create CLAUDE.md, CURRENT_STATUS.md, FILE_INDEX.md, WORKLOG.md, or DOC_HARNESS_SPEC.md.

  • MPort

    forkadarshp/MPort Skill

    4★

    Use when the user asks to migrate, upgrade, or port prompts, agents, tools, or codebases from one LLM model or provider version to another. Also use when auditing or continuing migration work started by another agent. Covers API calls, prompt assets, agent configs, tool definitions, tests, docs, runtime settings, rollout plans, and handoff coordination. Can also benchmark pre/post migration systems (old model and prompts vs new model and enhanced system) and report the stats as evidence.

  • Claude patch

    huybuidac/claude-code-patchkit/skills/claude-patch Skill

    4★ repo

    Patch Claude Code CLI binary to unlock hard-coded limitations. Use when the user wants to apply, revert, or check status of binary patches after upgrading Claude Code. Community-contributed patches for model restrictions, feature flags, and schema unlocks.

  • Claude code usage

    0xlayerghost/solidity-agent-kit/skills/claude-code-usage Skill

    4★ repo

    [AUTO-INVOKE] MUST be invoked at the START of each new coding session. Covers context management, task strategies, and Foundry-specific workflows. Trigger: beginning of any new conversation or coding session in a Solidity/Foundry project.

    The same file is in 1 other repository

  • Prompt engineering

    hardness1020/awesome-prompt-skill/skills/prompt-engineering Skill

    4★ repo

    Expert guidance for designing, optimizing, evaluating, and securing prompts and system prompt architectures for LLMs. Use when users need help with writing or improving prompts, designing system prompts or multi-section prompt architectures, building agent prompts with tool integration, prompt optimization and automated tuning, prompt security and injection defense, prompt evaluation and benchmarking, production prompt management, or understanding prompt engineering techniques like Chain of Thought, ReAct, Tree of Thoughts, few-shot learning, and Constitutional AI. Covers patterns derived from production agentic systems and the broader prompt engineering research landscape.

  • Handoff

    wassermanproductions/master-canvas-hermes-plugin/skills/handoff Skill

    4★ repo

    Work with Master Canvas AI video handoff packages. Use when a user provides a Master Canvas ZIP or project_manifest.json and wants Hermes to inspect assets, preserve scene and shot order, prepare ComfyUI/LTX 2.3 jobs, or hand off prompts to Kling, Veo, or another video generation operator. Also use when a user wants Hermes to autonomously create, update, and package a Master Canvas pre-production project from a brief, scenes, shots, prompts, references, and local assets.

  • Coding agents superpack

    frankxai/awesome-hermes-agent-skills/skills/coding-agents-superpack Skill

    no license4★ repo

    Use when orchestrating multiple coding agent CLIs (Claude Code, Codex, OpenCode, Grok CLI, Antigravity). Discovery, comparison, structured prompting, and multi-agent handoff patterns. Portable free pack — no host-specific secrets.

  • Claude desktop manual

    ThanhNguyxnOrg/blendops/bundles/claude-desktop-manual Skill

    4★ repo

    Claude Desktop-facing BlendOps router skill for planning, runtime readiness, evidence truth, and non-Blender-user outputs using bundled references.

  • Ab scripting feature dev

    mumez/pharo-agentic-browser/skills/ab-scripting-feature-dev Skill

    no license4★ repo

    Generates an AgenticBrowser Scripting DSL orchestration that implements a feature end-to-end — plan (if needed), TDD implementation, tests, and a lint/style-guide review pass — previews it as docs/scripting-features/feature-<name>.scripting.md, and on user approval runs it via st-eval. Use this whenever the user wants to build or automate a feature "using the scripting DSL", asks to orchestrate coding agents (claude/codex/etc.) to implement something in an AgenticBrowser-based repo, or asks for a multi-agent orchestration script (`AgenticBrowser runBy:` / `scriptBy:` / `groupRunBy:`) for feature development. Trigger on phrases like “Implement it using the scripting DSL,” “Create an orchestration script,” “Create a feature-xxx.scripting.md file”, "scripting DSLで実装して", "オーケストレーションスクリプトを作って", "feature-xxx.scripting.mdを作って", even if the user doesn't say "skill" explicitly.

  • Osmedeus expert

    osmedeus/osmedeus-skills/osmedeus-expert Skill

    no license4★ repo

    Expert guide for the Osmedeus security automation workflow engine. Use when: (1) writing or editing YAML workflows (modules and flows), (2) running osmedeus CLI commands (scan, workflow management, installation, server), (3) configuring steps, runners, triggers, or template variables, (4) debugging workflow execution issues, (5) building security scanning pipelines, (6) working with agent/LLM step types, or (7) any question about osmedeus features, architecture, or best practices.

  • Auditing agent config

    keshavjoglekar/auditing-agent-config Skill

    4★

    Audits a Claude Code and/or Claude.ai configuration for redundancy, misplacement, and conflicts — across global (~/.claude) and project (.claude/) scopes, skills, plugins, CLAUDE.md/rules, subagents, hooks, and MCP/connector setup. Use this whenever the user wants to audit, review, clean up, reorganize, or sanity-check their Claude setup; mentions having "too many skills/plugins"; asks whether something should be global or project-level; suspects duplicate, conflicting, or overlapping skills; wants to know if their CLAUDE.md is too long or bloated; asks "why isn't skill X triggering"; or asks things like "audit my claude setup," "check my skills for overlaps," or "help me organize my Claude Code config." Trigger proactively any time the user is actively managing a nontrivial skill/plugin library (roughly 10+ skills or 3+ plugins) and starts talking about adding more.

  • Gpt pro

    scasella/codex-gpt-pro/gpt-pro Skill

    4★ repo

    Operate ChatGPT Pro through Browser Use/Playwright or Computer Use. Use when the user asks Codex to ask GPT Pro, prompt GPT Pro, use ChatGPT Pro, send a prompt to ChatGPT Pro/GPT Pro, or wait for a GPT Pro result. Checks whether Browser Use/Playwright and/or Computer Use are available, asks for a first-run default route when both are available, selects Pro, submits prompts, waits through long reasoning or streaming, and returns the completed answer while pausing for login, MFA, CAPTCHA, account-security prompts, and never exporting or saving cookies, session tokens, or auth credentials.

  • Skill agent session handover

    oguzkr/skill-agent-session-handover Skill

    4★

    Use this skill when the user asks one local AI agent to inspect, continue from, hand off, summarize, or compare another local agent session, especially Cursor agent transcripts under ~/.cursor/projects, Codex sessions under ~/.codex/sessions, and Claude Code transcripts under ~/.claude/projects.

  • Ruledoctor

    syf2211/ruledoctor/plugin/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.

  • Mcp

    fouradata/mcp/ai.foura/mcp MCP server

    4★ repo

    Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.

  • Mcp

    megberts/mcp-websitepublisher-ai/ai.websitepublisher/mcp MCP server

    no license4★ repo

    Build and publish websites through AI conversation.

  • Windsor.ai MCP

    windsor-ai/windsor_mcp/ai.windsor/windsor-mcp MCP server

    4★ repo

    Query and analyze marketing, sales, and business data from 325+ platforms via Windsor.ai.

  • Jooq mcp

    martinellich/jooq-mcp/ch.martinelli/jooq-mcp MCP server

    4★ repo

    An MCP server that provides access to the jOOQ documentation

  • APIVerve

    apiverve/mcp-server/com.apiverve/mcp-server MCP server

    4★ repo

    350+ production-ready APIs through one MCP server — weather, geocoding, validation, financial data.

  • Mcp

    lusha-oss/lusha-mcp-plugin/com.lusha.mcp/mcp MCP server

    4★ repo

    Lusha MCP server for authorized business profile, usage, and buying-signal insights.