agentsclimarketplace

Context & AI engineering

25,864 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

  • Talend ans agent

    asin553/EscAlert-Ops/.agents/skills/talend-ans-agent Skill

    no license0★ repo

    Work on this Talend Alert Noise Suppression Azure Functions app, including Talend task/plan parsing, retry classification, alert storage, digest email, and optional OpenAI summaries.

  • Dock0

    cynsta/dock0-claude-skill/skills/dock0 Skill

    no license0★ repo

    Guide for deploying and monetizing MCP servers on Dock0. Use when the user wants to deploy an MCP server, monetize an existing MCP server, set up per-call pricing, manage API keys, configure Claude Desktop or Cursor to use a Dock0 endpoint, manage wallet balance, view earnings, or use the dock0 CLI. Also use when the user mentions Dock0, dock0, or MCP server deployment/monetization.

  • Mac secrets

    Vasallo94/skill-issue/skills/general/mac-secrets Skill

    no license0★ repo

    Securely store and manage secrets (API tokens, PATs, passwords, credentials) in macOS Keychain for local development tools — MCP servers, CLI tools, wrapper scripts, .env files, and more. Use this skill whenever the user asks to "secure a token", "store a secret", "set up keychain", "remove plaintext credentials", "secure my .env", or mentions wanting to avoid secrets in plaintext on their Mac. Also trigger when discussing MCP server configuration that involves tokens or credentials on macOS, or when the user asks how to safely manage API keys locally. Trigger PROACTIVELY when you detect a secret being passed as plaintext in a command, env var, or config file — don't wait for the user to ask.

  • Claude complex tasks

    echohello-dev/skillet/skills/claude-complex-tasks Skill

    0★ repo

    Guide Claude on complex, multi-step tasks by enforcing structured discovery, scoped planning, and verification before delivery.

  • Evm copilot researcher

    0xYudhishthra/evm-copilot-skills/evm-copilot-researcher Skill

    no license0★ repo

    Research the EVM/Ethereum competitive landscape using the EVM Copilot MCP server. Search 18,000+ projects (launched protocols, hackathon submissions, dead/rugged projects), 1,500+ research documents (EIPs, ethresear.ch, Vitalik blog), and 54 VC investment theses. Use when user asks about EVM/DeFi projects, wants to vet or validate a project idea, check competitors, find dead protocols, research Ethereum topics, or analyze VC funding. NOT for smart contract auditing or security analysis.

  • Smart router

    c0nSpIc0uS7uRk3r/smart-router Skill

    0★

    Expertise-aware model router with semantic domain scoring, context-overflow protection, and security redaction. Automatically selects the optimal AI model using weighted expertise scoring (Feb 2026 benchmarks). Supports Claude, GPT, Gemini, Grok with automatic fallback chains, HITL gates, and cost optimization.

  • Gh aw workflow authoring

    deyil/gh-aw-skills/skills/gh-aw-workflow-authoring Skill

    0★ repo

    Create new GitHub Agentic Workflows, shared gh-aw components, and safe edits to workflow prompts or frontmatter with the right compile, security, tool patterns, and Peli's Agent Factory reuse rules.

  • Bug fix lifecycle

    jovd83/bug-fix-lifecycle Skill

    0★

    Use when Codex must report a newly discovered defect, implement an approved bug fix, or harden regression coverage and documentation around a known bug. This skill enforces repository-aware bug intake, failing confirmation tests before fixes, scoped verification, documentation updates when warranted, and a structured resolution report.

  • Agentic bdd test case mentor

    jovd83/agentic-bdd-test-case-mentor Skill

    0★

    Review, rewrite, generate, and assess BDD or Gherkin feature files, scenarios, and outlines from user stories, acceptance criteria, business rules, or example maps. Use to identify BDD anti-patterns, traceability or coverage gaps, weak Given-When-Then structure, overloaded scenarios, missing rule branches, or coaching-oriented improvements without framework-specific automation design.

  • Aieng

    javalenciacai/develop-skills/.agents/skills/aieng Skill

    0★ repo

    AI Engineer. AIEng develops AI/ML models, training, MLOps and LLM integration. Reports to DataLead. Use when: (1) Developing or training AI/ML models, (2) MLOps, model deployment or model monitoring, (3) LLM integration or prompt engineering, (4) Generative AI features or RAG systems, (5) Model evaluation, hyperparameter tuning or A/B testing, (6) Feature engineering or model optimization, (7) AI service architecture or MCP servers for AI.

  • Persistent memory claw

    2730554131/persistent-memory-claw Skill

    no license0★

    跨会话持久记忆系统:为 OpenClaw agent 提供持久记忆能力。使用 SQLite 存储,按日期保存,手动触发更可控。

  • Agent builder skill

    peanutsee/skills/skills/agent-builder-skill Skill

    0★ repo

    Guides design and implementation of new agentic systems (workflows, multi-agent orchestration, tool use). Use when the user asks to build a new agentic system or review/audit an existing one. Do not use for incremental changes, bug fixes, or refactors to an existing system unless the user explicitly asks to redesign, rearchitect, or replace it.

  • Write a skill

    antono/agent-skills/.agents/skills/write-a-skill Skill

    no license0★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    The same file is in 20 other repositories

  • Epitech pre eval

    epitech-toulouse/epitech-pre-eval Skill

    no license0★

    Pré-évalue automatiquement un projet étudiant Epitech à partir d'un barème JSON et du code source fourni (repo GitHub, archive ZIP, ou clone local). Génère un compte rendu rapide, un rapport détaillé critère par critère et un fichier Excel exportable. Utiliser ce skill dès que l'utilisateur mentionne : "pré-évaluation", "barème", "corriger un projet étudiant", "vérifier les critères", "noter un rendu", "EIP", "regarde si l'étudiant a bien fait X", "vérifie que le projet respecte le barème", "prépare mon évaluation", "analyse de code Epitech".

  • External requirements

    planifest/planifest-framework/plan/_archive/0000003-hook-based-enforcement-2026-04-20/external-requirements Skill

    0★ repo

    Phase 7 only — raises the PR, writes the changelog, handles skips, and archives plan/current/. Invoked by the orchestrator at the end of the feature pipeline.

  • Deepagents cli

    Gitmaxd/deepagents-cli-deepagents-skill/templates/skills/deepagents-cli Skill

    0★ repo

    Deep Agents CLI — the LangGraph-based terminal coding agent. Use this skill whenever the user mentions deepagents, deep agents, the deep agents CLI, terminal coding agent, LangGraph agent, or asks about agent memory, agent skills, AGENTS.md, coding assistants in the terminal, or building scripted/CI agent workflows. Covers: interactive and non-interactive sessions, 20+ LLM providers, model configuration, skills, persistent memory, sandboxed execution, subagents, streaming, and the Agent Client Protocol.

    The same file is in 3 other repositories

  • Prek agentic onboard

    zhutao100/prek-agentic-onboard-skill/prek-agentic-onboard Skill

    0★ repo

    Onboard or migrate repositories from pre-commit to prek, including workspace-mode polyglot setup and agent-friendly auto-format+auto-stage commit convergence (global shim or per-language wrapper hooks).

  • Claude web remote

    lunaticfluker/claude-web-remote Skill

    0★

    Set up remote browser access to Claude Code and dev site preview from any device (iPad, phone, another computer) with QR codes. Use when the user wants to access Claude Code remotely, work from a tablet or phone, or set up browser-based terminal access.

  • Repo setup

    avantika-msr/agent-skills/repo-setup Skill

    0★ repo

    Autonomous local development environment setup agent. Use this skill whenever a user wants to clone a repository and get it running locally, set up a dev environment for a project, install dependencies for a codebase, or run a project from a GitHub URL or repo name. Triggers on phrases like "set up this repo", "clone and run", "get this project running", "set up my dev environment", "help me run this locally", repo URLs (github.com/...), or org/repo-name patterns. Also use when a product manager, designer, or new team member wants to run a project locally and needs hand-holding through the process. This skill runs commands itself rather than listing them — it is an autonomous agent, not a tutorial. Even if the user just pastes a GitHub URL with no other context, use this skill.

  • Agent browser

    mifunedev/skills/skills/agent-browser Skill

    0★ repo

    Open a URL in the headless agent-browser, with a preflight health check. Verifies agent-browser is installed and Chromium launches before navigating. Errors out with a diagnostic trace if anything fails. TRIGGER when: asked to open a page, browse a URL, take a screenshot, or test a site with agent-browser.

  • Long running agent skill

    bowen31337/long-running-agent-skill Skill

    0★

    Build autonomous, long-running AI agents that parse PRDs/specifications into structured task lists and execute them autonomously with state persistence, error recovery, and cross-session resumption. Works with any agent framework (Cursor, OpenCode, etc.).

    The same file is in 1 other repository

  • Prompt inspector

    aunicall/prompt-inspector-integration/skills/prompt-inspector Skill

    0★ repo

    Detect prompt injection attacks and adversarial inputs in user text before passing it to your LLM. Use when you need to validate or screen user-provided text for jailbreak attempts, instruction overrides, role-play escapes, or other prompt manipulation techniques. Returns a safety verdict, risk score (0–1), and threat categories. Ideal for guarding AI pipelines, chatbots, and any application that feeds user input into a language model.

  • Agent protocols

    BartWaardenburg/isagentready-skills/agent-protocols Skill

    0★ repo

    Implements AI agent interaction protocols — adds WebMCP declarative tool annotations, WebMCP manifests, Google A2A Agent Cards, MCP discovery documents, OpenAPI specifications, and agents.json so AI agents can directly interact with website functionality. Use when asked to "add WebMCP", "implement A2A", "create agent card", "add MCP discovery", "create OpenAPI spec", "add agents.json", "improve agent protocols score", "make site agent-interactive", or any WebMCP, A2A, MCP, or OpenAPI task.

  • Agent handoff governor

    yangshu2087/Codex/.agents/skills/agent-handoff-governor Skill

    no license0★ repo

    Use when handing work between Codex, Cursor, or other agents, before pausing or switching tools, to refresh docs/agent-handoff.md with branch, changed files, verification evidence, and an explicit next step.

  • Claude agent teams

    cskwork/claude-agent-teams Skill

    0★

    When the user wants to coordinate multiple Claude Code agents to work on a complex task in parallel. Also use when the user mentions "agent team," "parallel agents," "multi-agent," "team of agents," "worktree agents," "split this into agents," "divide and conquer with agents," or "orchestrate agents." For single-agent sequential work, standard Agent tool usage suffices.

  • Msa claude md

    cskwork/msa-claude-md Skill

    0★

    Generate minimal (<100 line) root CLAUDE.md + per-service CLAUDE.md files for MSA projects. Auto-detects tech stacks, uses See (not @) for zero-cost context loading, domain grouping for 10+ services. Use when setting up or auditing CLAUDE.md in microservice architectures.

  • Codex agent

    ninjaproger/skills/skills/codex-agent Skill

    no license0★ repo

    Delegate complex, multi-step coding tasks to the OpenAI Codex CLI agent running in the background. Use when the user wants to offload autonomous coding work to codex — including TCA feature development (new reducer/view/tests in a modular iOS app) and iOS Simulator automation (build, install, navigate, inspect). Codex runs non-interactively via `codex exec`, handles tool calls and file edits autonomously, and returns a final summary. Use for tasks that benefit from background execution: "implement X feature using codex", "have codex add tests for Y", "use codex to navigate the simulator and verify Z", "run codex in the background to build this".

  • Memory forge

    javicasper/memory-forge/.claude/skills/memory-forge Skill

    0★ repo

    CLI-agnostic continuous learning for AI coding agents. Supports Claude Code, OpenCode, Codex, Cursor. Monorepo-ready with distributed docs and skills.

    The same file is in 5 other repositories

  • Agentic loop

    meharajM/agent-loop-mcp/skills/agentic-loop Skill

    no license0★ repo

    Run long-lived autonomous agent loops with persistent memory, context-window compaction, self-healing retries, and resumable state. Use when an AI coding agent must retain progress across sessions, recover from failures, or avoid context exhaustion.

  • Agent ready

    guygrigsby/claude-plugins/plugins/agent-ready/skills/agent-ready Skill

    0★ repo

    Use when making a repository easy for coding agents to work in, or keeping it that way, auditing a repo for agent ergonomics, bootstrapping or refreshing CLAUDE.md / AGENTS.md, when a session-start notice says context files are missing or stale, when a file has grown too large for an agent to hold in context, or when onboarding a codebase for agentic development. Not for writing application features.

  • Agent logger

    WhizZest/agent-logger/skills/agent-logger Skill

    no license0★ repo

    Records agent logs with structured markdown files. Invoke when completing complex tasks, learning new knowledge, making serious errors, being corrected by user, when no logs in recent 8 conversations, when self-deemed necessary, or when user requests logging.

  • Format evaluator

    danielrosehill/Agent-Skills/skills/format-evaluator Skill

    no license0★ repo

    Evaluate whether a capability idea is best deployed as a Claude Code plugin, slash command, skill, subagent, or agent workspace. Use when the user describes an idea and asks "should this be a skill / slash command / plugin / agent?" or wants a recommendation on packaging format before building.

  • Openclaw warden

    AtlasPA/openclaw-warden Skill

    no license0★

    Verify workspace file integrity and scan for prompt injection patterns in agent identity and memory files. Detects unauthorized modifications to SOUL.md, AGENTS.md, IDENTITY.md, memory files, and installed skills. Free detection layer — upgrade to openclaw-warden-pro for automated countermeasures.

  • Autonomous agent framework

    bowen31337/autonomous-agent-framework Skill

    0★

    Build autonomous, long-running AI agents that parse PRDs/specifications into structured task lists and execute them autonomously with state persistence, error recovery, and cross-session resumption. Works with any agent framework (Cursor, OpenCode, etc.).

    The same file is in 1 other repository

  • Agent context init

    lx-wnk/skills/skills/agent-context-init Skill

    0★ repo

    Initialize Agent-Context in the current project — sets up the layered context architecture with shared infrastructure, project-specific layers, memory stubs, and skill registry. Use this skill whenever the user asks to initialize Agent-Context, set up Agent-Context, bootstrap Agent-Context, or says things like "init agent-context", "set up context layers", "add agent-context to this project". Also use when the user wants to start using Agent-Context in a new or existing project.

  • Agents md audit

    neumie/almanac/skills/agents-md/agents-md-audit Skill

    0★ repo

    Use when auditing a CLAUDE.md or AGENTS.md file. Scores six metrics (0-100), cites issues, suggests fixes. Codebase scan first, falls back to file-only when no codebase available.

  • Agents do

    dot-do/skills/agents-do Skill

    0★ repo

    Expert guidance for agents.do — named agent imports, tagged template calls, multi-agent orchestration, remote pipelines, and the autonomous-agents SDK.

  • Test design orchestrator

    jovd83/test-design-orchestrator Skill

    0★

    Turn requirements, user stories, acceptance criteria, business rules, use cases, or state models into structured test artifacts. Selects the best black-box test design technique and routes work to the matching subskill. For format-only work, prefer test-artifact-export-skill.

  • Template

    verkyyi/ainbox-skills/_template Skill

    0★ repo

    One-sentence description of what this agent does when someone emails it.

  • Bootstrap agent

    stevesimpson418/ai-agent-template/.claude/skills/bootstrap-agent Skill

    0★ repo

    One-time interactive bootstrap wizard for setting up a new AI agent from the template. Trigger when: "bootstrap", "set up this agent", "initialise this agent", "/bootstrap-agent". This skill should only run once — it configures the repo for a specific agent. Do NOT trigger for: general questions about the template or how agents work.

  • Agent mem

    lmaksym/agent-mem/.claude/skills/agent-mem Skill

    0★ repo

    Persistent, git-backed memory across sessions. Use at session start (snapshot), after decisions/fixes/mistakes (remember/lesson), to checkpoint work (commit), before risky exploration (branch), or to check prior context (search).

  • Ai knowledge base skill

    allenphant/ai-knowledge-base-skill Skill

    no license0★

    AI knowledge accumulation and research tool. Use this skill whenever the user shares a URL (article, tweet, thread, GitHub repo, product page), asks about an AI tool or service, wants to compare AI products/services, asks to research or summarize AI topics, mentions their knowledge base or Obsidian vault, or wants to update their understanding of a topic. Trigger on any AI-related learning, research, or knowledge management request — even if the user just pastes a link without explanation.

  • Kairo developer agent

    mattharbord/kairo-agents/skills/kairo-developer-agent Skill

    0★ repo

    Build and iterate Kairo-mode software with a PM using test-first delivery, explicit risk disclosure, and non-blocking warnings. Use when creating or modifying a Kairo-labeled tool, setting up PM/agent working contracts, building with snapshot-backed validation, maintaining known-gaps and decision logs, preparing a Kairo release README, or implementing write-path safety (dry-run then single-record canary). If scope is mission-critical or high-assurance, keep this skill active in severe-warning mode and explicitly state Kairo is a bad fit for that context.

  • Handoff

    thegeneralist01/claude-handoff-skills/handoff Skill

    no license0★ repo

    Prepare a context handoff for continuing work in a new thread. Use when asked to /handoff, create a handoff, or prepare context for continuation.

  • Skill packager

    yaniv-golan/skill-packager-skill/.agents/skills/skill-packager Skill

    0★ repo

    Package AI agent skills into deployment formats — .zip, .skill, Claude plugin, Claude marketplace, Cursor plugin, Cursor marketplace, native Codex/ChatGPT plugin, ChatGPT/Manus zip, Codex CLI, NanoClaw marketplace, OpenClaw/ClawHub, Agent Skills standard (.agents/), or a universal repo with all formats + CI/CD. Use when the user says "package this skill", "deploy my skill", "create a plugin from this skill", "make this work on Cursor/ChatGPT/Codex/NanoClaw/OpenClaw", "set up a repo for my skill", or wants to distribute a SKILL.md to any platform.

  • Agentic trust skill

    neo-daniil/agentic-trust-skill Skill

    0★

    Deterministic workflow for searching services in Agentic Trust, inspecting trust evidence, loading the active questionnaire, comparing with local review memory, and optionally submitting a valid structured review with integer answers (0..10).

    The same file is in 3 other repositories

  • Spaceship domains

    BartWaardenburg/spaceship-skills/spaceship-domains Skill

    0★ repo

    Manages domains via the Spaceship registrar API — registers domains, configures DNS records, manages contacts and WHOIS privacy, transfers domains, sets up nameservers, and sells domains on SellerHub. Use when asked to "manage domains", "register a domain", "configure DNS", "add DNS records", "set up nameservers", "check domain availability", "transfer a domain", "sell a domain", "set up email DNS", "manage WHOIS privacy", or any Spaceship domain registrar operation. Requires the Spaceship MCP server to be configured.

  • Bio agent

    master5d/claude-personal-skills/skills/bio-agent Skill

    no license0★ repo

    Design AI agents with emotional metabolism — dopamine (interest), cortisol (stress), ATP (energy) as internal state. Use when the user says "bio agent", "agent metabolism", "emotional AI", "biological computationalism", "agent with feelings", "agent personality", "affective agent", or wants to give an AI agent internal emotional dynamics that influence its behavior. Based on Milinkovic & Aru (2025).

  • Llm knowledge base

    hey-dmitri/llm-knowledgebase/llm-knowledge-base Skill

    no license0★ repo

    Set up and maintain a local, file-based knowledge base with immutable raw sources, an agent-maintained Markdown wiki, and generated outputs. Use when a user asks to create an LLM wiki, personal knowledge base, AI-assisted second brain, Obsidian knowledge system, or a persistent alternative to reprocessing source files for every question.

  • Agents md authoring majo

    markjoshwel/skills/agents-md-authoring-majo Skill

    no license0★ repo

    Write effective AGENTS.md files for AI coding agents.

  • Agent security guard

    bensonmaxai/minis-security-skills/skills/agent-security-guard Skill

    no license0★ repo

    Use when planning, reviewing, or executing AI agent tasks that may involve shell commands, file operations, external services, secrets, personal data, automation, or potentially destructive changes. Applies an operational security review for Minis on iOS: risk tiering, least privilege, confirmation thresholds, secret handling, data minimization, safe tool usage, and audit-minded execution. Pair with prompt-injection-defense when handling untrusted content from the web, documents, OCR, or repositories.

  • Agent browser

    vijpatel7/favorite_skills_and_plugins/.agents/skills/agent-browser Skill

    0★ repo

    Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

  • Gemini skill creator

    grantmcd/skills/gemini-skill-creator Skill

    no license0★ repo

    Use this meta-skill to design, architect, and objectively evaluate high-quality specialized skills following the Agent Skills open standard. Activate whenever the user wants to 'create a skill', 'automate a workflow', or 'refine an agent capability', even if they don't explicitly mention 'Agent Skills' or 'SKILL.md'. Mandates sandboxed evaluation, objective metrics, and interactive review dashboards.

  • Shared memory

    jovd83/shared-memory Skill

    0★

    Manage persistent cross-agent knowledge across agents, skills, and repos. Trigger to assess, retrieve, validate, or deprecate shared conventions, prompts, and org defaults. ALWAYS trigger on "remember", "save", or "note" for cross-turn info.

  • Ai code review

    xPAlien/AI_code_review_skill/ai-code-review Skill

    0★ repo

    Systematic code review checklist for AI-generated code. Use this skill whenever reviewing code produced by AI assistants (ChatGPT, Copilot, Claude, Cursor, Codex, Gemini, etc.), or when the user asks to review, audit, or harden any code they did not write from scratch themselves. Also trigger when the user says "review this," "is this safe," "check my code," "audit this," "harden this," or pastes code they want evaluated before merging or deploying. If the user mentions vibe coding, shipping AI code, or debugging code they do not fully understand, use this skill.

  • Notebooklm experts skill

    khengyun/notebooklm-experts-skill Skill

    0★

    This skill connects GitHub Copilot to Google NotebookLM for explicit, source-grounded queries against notebooks the user has already prepared. The agent remains responsible for planning, follow-up, and synthesis.

  • Openclaw health

    LeoStehlik/openclaw-health Skill

    0★

    Audits an OpenClaw workspace for configuration health, signal quality, and security issues. Use when asked to run a health check, audit the workspace, review agent config quality, or check if AGENTS.md, SOUL.md, memory files, or skills are in good shape. Checks for: bloated bootstrap files, stale memory, skill description quality, prompt injection risks in skills, critical rules coverage, and context hygiene issues. OpenClaw equivalent of claude-health.

  • Agent registry

    srinandan/agent-registry-extension/skills/agent-registry Skill

    0★ 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.

  • Architect agent

    Mickos79/aria-skills/architect-agent Skill

    no license0★ repo

    Production AI agent skills for OpenClaw — extracted from a real personal AI OS. RAG memory, safety guards, cost tracking, architect agent and more.

  • Context os

    kaantaskentt/context-os Skill

    0★

    Memory operating system for AI agents. Activate when memory is near capacity, when stale or contradictory entries are detected, when the user's context has shifted significantly, or when the user requests memory optimization. Also trigger at the start of new projects or engagements where fresh context will accumulate. Handles triage, compaction, archival, and capacity planning. If you notice yourself applying outdated context to current situations, that is a trigger. Do not activate during casual conversation or when memory is healthy.