agentsclimarketplace

Context & AI engineering

25,729 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

  • Figma create design system rules

    michelve/hugin-v0/skills/figma-create-design-system-rules Skill

    0★ repo

    Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.

  • Miro mcp

    michelve/hugin-v0/skills/miro-mcp Skill

    0★ repo

    This skill teaches how to use Miro MCP tools effectively for creating diagrams, documents, tables, and extracting context from Miro boards. Use when the user asks about Miro capabilities, wants to create content on Miro boards, or needs to work with Miro board data.

  • Skill creator

    michelve/hugin-v0/skills/skill-creator Skill

    0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

  • Skill creator

    woyxiang/skills/skills/skill-creator Skill

    0★ repo

    Create new skills for AI agents. Use when: (1) User asks to create a skill for a language, tool, or framework, (2) A new skill needs to be bootstrapped from scratch, (3) An existing skill needs a new capability (doc, script, agent), (4) You need to understand the skill authoring workflow

  • Context audit

    mifunedev/skills/skills/context-audit Skill

    0★ repo

    Score the default-loaded context budget across 4 dimensions and emit KEEP/TRIM/DEMOTE/CUT verdicts per file. Optional Tier-2 ablation harness removes a target file, runs a fixed probe suite, and measures behavior degradation — the only provably safe gate for cutting load-bearing content. TRIGGER when: asked to audit context window, check default context load, "what's in my context", evaluate rules for signal vs noise, or before/after any change to context/rules/ or CLAUDE.md.

  • Skill creator

    jeffchen006/skills/.agent/skills/skill-creator Skill

    no license0★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 19 other repositories

  • Skill creator

    jeffchen006/skills/.claude/skills/skill-creator Skill

    no license0★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 19 other repositories

  • Skill creator

    jeffchen006/skills/selected/skill-creator Skill

    no license0★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 19 other repositories

  • Session handoff

    LoogacyStudio/skills/.agents/skills/session-handoff Skill

    0★ repo

    Use when work must continue in a fresh AI agent or later session and a continuation-ready handoff document is needed to preserve goals, decisions, evidence, and exact next steps without ambiguity.

  • Benchmark author item

    LoogacyStudio/skills/.github/skills/benchmark-author-item Skill

    0★ repo

    Use when a new benchmark item, seed draft, or ad hoc eval case needs to be turned into the repository's canonical benchmark-item format with clear task family, route expectation, artifact contract, scoring focus, and variant hooks.

  • Benchmark author rerun manifest

    LoogacyStudio/skills/.github/skills/benchmark-author-rerun-manifest Skill

    0★ repo

    Use when a bounded candidate revision needs a concrete rerun manifest with target suites, protected suites, benchmark anchors, execution paths, judging focus, and conditional follow-up checks before promotion review.

  • Benchmark author skill evals

    LoogacyStudio/skills/.github/skills/benchmark-author-skill-evals Skill

    0★ repo

    Use when a reusable agent skill needs a small, scoreable eval pack with explicit success criteria, trigger prompts, deterministic checks, rubric-based qualitative grading, and extension hooks for regressions, thrashing, or permission drift.

  • Benchmark author variants

    LoogacyStudio/skills/.github/skills/benchmark-author-variants Skill

    0★ repo

    Use when a benchmark item or judged run needs a reusable variant pack from the repository's canonical metamorphic and adversarial families, with explicit invariants, drift budget, safe-failure rules, and execution-ready transformed input packages.

  • Benchmark cluster failures

    LoogacyStudio/skills/.github/skills/benchmark-cluster-failures Skill

    0★ repo

    Use when multiple judged benchmark runs need to be grouped into reusable failure-pattern records with taxonomy-aligned tags, root-weakness hypotheses, severity and regression framing, and bounded next-action guidance for downstream proposal or gate work.

  • Benchmark core

    LoogacyStudio/skills/.github/skills/benchmark-core Skill

    0★ repo

    Use when a benchmark agent or skill needs the shared benchmark framework rules — capability map, corpus discovery, corpus adapter contract, lifecycle boundaries, or run-record finalization guidance — rather than one benchmark artifact like a judged run or rerun manifest.

  • Benchmark judge run

    LoogacyStudio/skills/.github/skills/benchmark-judge-run Skill

    0★ repo

    Use when a benchmark execution record or variant run needs a canonical judged record with route-first classification, five-dimension rubric scoring, post-score failure tags, separate invariance or robustness notes, and optional scaffold-to-completed finalization.

  • Benchmark review candidate

    LoogacyStudio/skills/.github/skills/benchmark-review-candidate Skill

    0★ repo

    Use when a wording, routing-policy, rubric, template, or other candidate revision needs a formal promotion review against target-suite gain, protected-suite regressions, invariance, robustness, mutation-surface rules, and official-adoption governance requirements.

  • Skill authoring

    LoogacyStudio/skills/.github/skills/skill-authoring Skill

    0★ repo

    Use when a repo customization or governance artifact needs a controlled update, review, or new scaffold, especially for skills, prompts, agents, hooks, instructions, learning notes, or change-log discipline.

  • Proactive agent

    muhammadrivaldy/agent-skills/proactive-agent Skill

    no license0★ repo

    Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞

  • My web search kagi

    alexleekt/agents/skills/my-web-search-kagi Skill

    no license0★ repo

    **ALWAYS use when user asks for:** searching the web, looking up information online, finding docs, checking prices, researching a topic, verifying facts. Also use when no dedicated web search MCP server is available. Triggers on phrases like "search the web", "look up", "find online", "google", "kagi search", "web search", "search for", or when current/real-time information is needed. **DO NOT use for:** questions answerable from training data alone, tasks where the user explicitly says "don't search", or when a dedicated MCP search server is available and preferred.

  • Worktree safety

    yangshu2087/Codex/.agents/skills/worktree-safety Skill

    no license0★ repo

    Safely operate in repositories that use Git worktrees or live inside a meta-workspace with multiple repos. Use when a task involves git roots, linked worktrees, pointer directories, or avoiding the wrong repository context.

  • Stitch ui prompt architect

    yangshu2087/Codex/vendor/skills/skilltrust-curated/stitch-kit/stitch-ui-prompt-architect Skill

    no license0★ repo

    Use when the user explicitly mentions Google Stitch and wants a structured Stitch-ready UI prompt or prompt refinement from rough product/design ideas.

  • Lf design system

    twinfo-io/lifters-skills/skills/lf-design-system Skill

    no license0★ repo

    Connects to Figma via MCP Server, extracts typography, colors, spacing, border radius, shadows and all design token definitions, and generates specs/design-system.md — the official design system source of truth for the project. Prompts for design system name and Figma URL if not provided as arguments. Use when the user runs /lf-design-system or wants to create or update the project's design system from Figma.

  • Crawlio mcp

    Crawlio-app/crawlio-plugin/skills/crawlio-mcp Skill

    0★ repo

    Complete reference for the Crawlio MCP server — 37 tools, 6 code-mode tools, 4 resources, 4 prompts. Use this skill when orchestrating website crawling, export, enrichment, or analysis via Crawlio MCP.

  • Memory forge

    javicasper/memory-forge Skill

    0★

    Continuous learning system that forges knowledge from work sessions into permanent memory. Use when: (1) after completing non-trivial debugging or investigation, (2) discovering patterns not obvious from documentation, (3) finding workarounds worth preserving, (4) "what did we learn?", (5) "save this pattern", (6) "extract a skill". Supports monorepos with distributed context files. CLI-agnostic (works with Claude Code, OpenCode, Codex, Cursor, and any tool supporting the Agent Skills standard).

  • Obsidian

    lx-wnk/skills/skills/obsidian Skill

    0★ repo

    Obsidian vault access via Local REST API using curl — read, search, create, or update notes in the knowledge base. Trigger on ANY of these: user mentions "obsidian", "vault", "knowledge base", "my notes", or "note" in a save/lookup context; user asks to "save", "persist", "document", "note down", or "look up" information; phrases like "note this down", "add this to my knowledge base", "search my notes", "check if I have notes on X", "create a note"; CLAUDE.md says to search or store in Obsidian before/after tasks — do it proactively; starting a task where prior context might exist → search first; mid-task discovery of a non-obvious insight, gotcha, root cause, or workaround → save it; finishing a task with decisions or learnings worth remembering → persist it; something written to CLAUDE.md or project docs → also save it for cross-project search.

  • Session handoff

    lx-wnk/skills/skills/session-handoff Skill

    0★ repo

    Generate a structured handoff document at the end of a work session — what was implemented, which decisions were made and why, open questions, and recommended next steps. The document is written to `outputs/handoffs/latest.md`, and the previous handoff is rotated to a dated, topic-named archive (repo convention, cf. `branch-review`). Use this skill whenever the user wants to end a session, create a handoff, or says: "session-handoff", "wrap up", "end of session", "session summary", "hand over to next session", "Handoff erstellen", "Session abschließen", "was haben wir heute gemacht", "Zusammenfassung der Session", "nächste Schritte dokumentieren", "übergib an nächste Session".

  • Handoff

    neumie/almanac/skills/productivity/handoff Skill

    0★ repo

    Use when compacting the current conversation into a handoff document for another agent to pick up.

  • Konecty meta

    konecty/skills/skills/konecty-meta Skill

    0★ repo

    All Konecty metadata operations through the Konecty admin MCP server: read/inspect MetaObjects, manage document schemas and fields, manage list/view/access/pivot metas, validate and generate hook code, manage Namespace config (SMTP/RabbitMQ/storage/MCP flags), validate metadata integrity, and sync metadata repo↔database. Use when: ler metadados, inspecionar esquema, gerenciar campos, adicionar campo, criar lista/view, configurar perfil de acesso, gerar hook, configurar Namespace/SMTP/fila RabbitMQ, habilitar MCP, validar integridade meta, sincronizar metas, remover módulo meta, read metadata, manage schema, add fields, manage list view access pivot, generate hook, configure namespace, enable MCP flags, validate metadata, sync metadata, remove meta module. Requires the konecty-admin MCP server connected and an admin user (admin: true). Do NOT use for data record ops (find/create/update/delete/upload) — use konecty-data; do NOT use for MCP server setup — use konecty-setup.

  • Skill creator

    Anoxxx/skillcache/examples/skill-creator Skill

    no license0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance, or optimize a skill's description for better triggering accuracy.

  • Handoff

    aylee/agent-os/.agents/skills/handoff Skill

    0★ repo

    Create a continuation brief for a real agent, runtime, machine, parallel-lane, or context-window boundary. Use when the user clearly asks to hand work to another agent or make it resumable across a named boundary. Do not infer handoff from casual closeout or use it as a substitute for current workstream state.

  • Agent patterns

    TheWatcher01/skills/.claude/skills/agent-patterns Skill

    0★ repo

    Design and implement autonomous AI agent architectures using SOTA patterns. USE when: building multi-agent systems, designing agent workflows, choosing between agent patterns (chaining vs routing vs parallelization), implementing orchestrator-worker pipelines, adding evaluator-optimizer loops, or when the user says "build an agent", "automate this workflow", "make agents work together", "design a multi-agent system". Based on Anthropic "Building Effective Agents" (Dec 2024).

  • Agentic actions auditor

    TheWatcher01/skills/.claude/skills/agentic-actions-auditor Skill

    0★ repo

    Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.

    The same file is in 1 other repository

  • Agentic workspace

    TheWatcher01/skills/.claude/skills/agentic-workspace Skill

    0★ repo

    Set up and maintain SOTA agentic architectures in VS Code workspaces with multiple projects. Use when: setting up agents, agentic architecture, multi-project workspace, agent hierarchy, context engineering, prompt engineering, skills ecosystem, AGENTS.md, copilot instructions, agent handoffs, orchestrator pattern, progressive disclosure, workspace agent structure. Teaches agent taxonomy design, skill ecosystems, instruction layering, handoff graphs following anthropics/skills, OpenAI Agents SDK, and GitHub Copilot custom agent standards (VS Code 1.106+).

  • Claude in chrome troubleshooting

    TheWatcher01/skills/.claude/skills/claude-in-chrome-troubleshooting Skill

    0★ repo

    Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.

    The same file is in 3 other repositories

  • Claude memory

    TheWatcher01/skills/.claude/skills/claude-memory Skill

    0★ repo

    Create and optimize CLAUDE.md memory files or .claude/rules/ modular rules for Claude Code projects. Comprehensive guidance on file hierarchy, content structure, path-scoped rules, best practices, and anti-patterns. Use when working with CLAUDE.md files, .claude/rules directories, setting up new projects, or improving Claude Code's context awareness.

  • Code review agent

    TheWatcher01/skills/.claude/skills/code-review-agent Skill

    0★ repo

    Systematic AI-powered code review. USE when: reviewing PRs, auditing code quality, checking for security vulnerabilities, validating architecture, analyzing Rust/Python/JS/TS code, reviewing config files, or when the user says "review this code", "check this PR", "find bugs", "is this code safe". Covers: security (OWASP), performance, maintainability, correctness. Optimized for fast review with Haiku 4.5.

  • Context engineering

    TheWatcher01/skills/.claude/skills/context-engineering Skill

    0★ repo

    Optimize the AI context window for any task. USE when: agent has poor memory or forgets context, responses are imprecise, needing to compress long conversations, building RAG pipelines, designing multi-turn agent state, managing tool results in context, or when the user says "the AI doesn't remember" or "context too long". Implements Karpathy/Willison context engineering: right info, right time, right format, right size.

  • Designing workflow skills

    TheWatcher01/skills/.claude/skills/designing-workflow-skills Skill

    0★ repo

    Guides the design and structuring of workflow-based Claude Code skills with multi-step phases, decision trees, subagent delegation, and progressive disclosure. Use when creating skills that involve sequential pipelines, routing patterns, safety gates, task tracking, phased execution, or any multi-step workflow. Also applies when reviewing or refactoring existing workflow skills for quality.

    The same file is in 1 other repository

  • Devops agent

    TheWatcher01/skills/.claude/skills/devops-agent Skill

    0★ repo

    DevOps, CI/CD, Docker, systemd, and infrastructure automation. USE when: writing Dockerfiles, GitHub Actions workflows, systemd services, shell scripts, deploying services, troubleshooting service failures, writing CI pipelines, managing secrets in CI, setting up monitoring. Trigger: "write a Dockerfile", "create a CI pipeline", "fix this service", "automate deployment", "create systemd unit", "setup monitoring".

  • Dl mcp

    TheWatcher01/skills/.claude/skills/dl-mcp Skill

    0★ repo

    11 MCP tools + 3 resources du serveur datalake (search, dossier, leads, territory)

  • Free llm rotation

    TheWatcher01/skills/.claude/skills/free-llm-rotation Skill

    0★ repo

    Configure and use free LLM providers with intelligent rotation and fallback. USE when: setting up ZeroClaw with free tiers, hitting rate limits, switching providers dynamically, comparing free model quality, configuring Ollama local fallback, or when the user says "use a free model", "I hit the rate limit", "switch to a cheaper model", "configure Ollama". Covers OpenRouter (26+ free), Groq (free tier), Ollama (local), Cerebras.

  • Mcp builder

    TheWatcher01/skills/.claude/skills/mcp-builder Skill

    0★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

  • Prompt creator

    TheWatcher01/skills/.claude/skills/prompt-creator Skill

    0★ repo

    Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.

  • Prompt engineering sota

    TheWatcher01/skills/.claude/skills/prompt-engineering-sota Skill

    0★ repo

    Apply SOTA prompt engineering techniques to any task. USE when: improving AI responses, structuring complex instructions, debugging poor outputs, choosing between CoT/ToT/ReAct, writing system prompts, or any task needing optimal LLM interaction. Covers 40+ techniques from Zero-shot to Tree-of-Thought, ReAct, Reflexion, Self-Consistency. Optimized for fast models (Haiku 4.5, Llama 3.1 8B). Trigger: "improve this prompt", "the AI gives bad answers", "write a system prompt", "use chain of thought".

  • Research agent

    TheWatcher01/skills/.claude/skills/research-agent Skill

    0★ repo

    Systematic deep research methodology using multiple sources. USE when: researching SOTA techniques, comparing libraries/frameworks, finding best practices, verifying claims, investigating bugs via GitHub issues, technical due diligence, literature review. Trigger: "research X", "find the best way to Y", "what's the SOTA for Z", "compare A vs B", "is X still maintained". Combines web, GitHub, docs and codebase sources.

  • Security audit agent

    TheWatcher01/skills/.claude/skills/security-audit-agent Skill

    0★ repo

    Security audit for agentic systems, MCP servers, skills, hooks, workflows, and external tools. USE when: adding any external skill/MCP/plugin/tool, reviewing agent configs, checking hook code, auditing workflows, detecting prompt injection, validating secrets management, reviewing agent permissions. CRITICAL: "never reproduce the openclaw scandal". Covers OWASP Top 10 for AI agents + supply chain security. Trigger: "audit this skill", "is this MCP safe", "check agent security", "review this tool".

  • Skill creator

    TheWatcher01/skills/.claude/skills/skill-creator Skill

    0★ repo

    This skill should be used when the user asks to "create a skill", "build a skill", "write a skill", "improve skill structure", "understand skill creation", or mentions SKILL.md files, skill development, progressive disclosure, XML structure, or bundled resources (scripts, references, assets). Comprehensive guide for creating effective Claude Code skills.

  • Skill improver

    TheWatcher01/skills/.claude/skills/skill-improver Skill

    0★ repo

    Iteratively reviews and fixes Claude Code skill quality issues until they meet standards. Runs automated fix-review cycles using the skill-reviewer agent. Use to fix skill quality issues, improve skill descriptions, run automated skill review loops, or iteratively refine a skill. Triggers on 'fix my skill', 'improve skill quality', 'skill improvement loop'. NOT for one-time reviews—use /skill-reviewer directly.

    The same file is in 1 other repository

  • Subagent creator

    TheWatcher01/skills/.claude/skills/subagent-creator Skill

    0★ repo

    Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

  • Agent mail automation

    adryanmoldokkr32-pixel/awesome-claude-skills/composio-skills/agent-mail-automation Skill

    no license0★ repo

    Automate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.

    The same file is in 6 other repositories

  • Benchmark email automation

    adryanmoldokkr32-pixel/awesome-claude-skills/composio-skills/benchmark-email-automation Skill

    no license0★ repo

    Automate Benchmark Email tasks via Rube MCP (Composio). Always search tools first for current schemas.

    The same file is in 6 other repositories

  • Mcp builder

    adryanmoldokkr32-pixel/awesome-claude-skills/mcp-builder Skill

    no license0★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 18 other repositories

  • Skill creator

    adryanmoldokkr32-pixel/awesome-claude-skills/skill-creator Skill

    no license0★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 16 other repositories

  • N8n mcp tools expert

    pessini/aria/backend/agents/n8n_agent/skills/n8n-mcp-tools-expert Skill

    0★ repo

    Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

    The same file is in 2 other repositories

  • Mcp builder

    northseadl/skillwisp/skills/@anthropic/mcp-builder Skill

    0★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 42 other repositories

  • Skill creator

    northseadl/skillwisp/skills/@anthropic/skill-creator Skill

    0★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 19 other repositories

  • Context fundamentals

    northseadl/skillwisp/skills/@muratcankoylan/context-fundamentals Skill

    0★ repo

    This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

    The same file is in 5 other repositories

  • Evaluation

    northseadl/skillwisp/skills/@muratcankoylan/evaluation Skill

    0★ repo

    This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.

    The same file is in 4 other repositories

  • Filesystem context

    northseadl/skillwisp/skills/@muratcankoylan/filesystem-context Skill

    0★ repo

    This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.

    The same file is in 1 other repository