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

  • General

    jajupmochi/agent-harness/skills/general Skill

    1★ repo

    Audit the source agent-harness general skill catalog. Use only when maintaining or adapting this repository's original reusable skill set.

  • Init codex config

    jajupmochi/agent-harness/skills/init-codex-config Skill

    1★ repo

    Scaffold or migrate a project to use agent-harness from Codex. Use when applying agent-harness in Codex, converting Claude Code setup to AGENTS.md/.codex/.agents, or making a project ready for Codex skills and hooks without changing the original Claude setup.

  • Memory flywheel

    jajupmochi/agent-harness/skills/memory-flywheel Skill

    1★ repo

    Use to persist and recall per-project cross-session working memory so long or multi-project sessions don't lose detail to context compaction. Record each round of progress (verbatim I/O + reasoning + metadata) into a project memory dir, read a coarse INDEX first, then open only what keyword recall points at. Deterministic, grep-native, LLM-as-component.

  • Prompt library

    jajupmochi/agent-harness/skills/prompt-library Skill

    1★ repo

    Use to save and reuse good prompts across projects and agents, and to MINE past prompts out of local Claude Code / Codex / Copilot / opencode history. Many prompts recur (a detailed feature spec, a "design the whole thing" brief, a manual/onboarding prompt) and are worth reusing verbatim or as a reference. This curates them as browsable, greppable Markdown — each with the original, an optimized rewrite, and when to use / when NOT to use it — behind a PRIVACY GATE that refuses to store anything still containing paths/emails/tokens/usernames/codenames, so the library stays publishable.

  • Task orchestrator

    jajupmochi/agent-harness/skills/task-orchestrator Skill

    1★ repo

    Meta-skill that enforces a structured Research-Design-Plan-Execute-Verify pipeline for every atomic task. Compensates for model/agent weaknesses (especially DeepSeek, non-native models) by adapting plan template strictness based on detected capabilities. Self-improving: records better approaches back into templates.

  • Tui installer

    jajupmochi/agent-harness/skills/tui-installer Skill

    1★ repo

    Use to install (or just plan) the recommended terminal/TUI stack for driving multiple AI coding agents on Ubuntu — zellij + claude-squad + lazygit + delta. Dry-run by default (prints the plan, installs nothing); --apply asks y/N per tool. When onboarding agent-harness, offer to run --check and ask before installing anything.

  • Verify visual

    jajupmochi/agent-harness/skills/verify-visual Skill

    1★ repo

    Visual verification for UI changes using Playwright screenshots and native model vision (GPT-5.5, Claude). For models without vision (DeepSeek), uses Playwright screenshot capture with pixel comparison for regression detection. BackstopJS available as optional regression tool.

  • Browser ops agent developer

    guorunjie/skillpack-forge/examples/.claude/skills/browser-ops-agent-developer Skill

    1★ repo

    Use when changing browser automation workflows.

  • Browser ops agent developer

    guorunjie/skillpack-forge/examples/.codex/skills/browser-ops-agent-developer Skill

    1★ repo

    Use when changing browser automation workflows.

  • Figma plugin orchestration

    royvergara/design-team-os/skills/figma-plugin-orchestration Skill

    1★ repo

    Use when a design task spans multiple Figma plugins or steps and needs to be sequenced from one instruction. Triggers on a request to coordinate, sequence, or automate plugin work in Figma. Always names which steps stay human.

  • Customer support agent

    Marine-softdrink524/claude-skills/skills/customer-support-agent Skill

    no license1★ repo

    Build AI-powered customer support systems with knowledge base access, ticket routing, and empathetic responses. Adapted from Anthropic's Claude Quickstarts.

    The same file is in 1 other repository

  • Prompt engineer

    Marine-softdrink524/claude-skills/skills/prompt-engineer Skill

    no license1★ repo

    Master prompt engineering with classification, summarization, and advanced techniques. Based on Anthropic's Claude Cookbooks and Courses.

    The same file is in 1 other repository

  • Rag specialist

    Marine-softdrink524/claude-skills/skills/rag-specialist Skill

    no license1★ repo

    Build Retrieval Augmented Generation (RAG) pipelines with vector databases, embeddings, and context-aware responses. Adapted from Anthropic's Claude Cookbooks.

    The same file is in 1 other repository

  • Tool use architect

    Marine-softdrink524/claude-skills/skills/tool-use-architect Skill

    no license1★ repo

    Design and implement Claude tool/function calling patterns with error handling, parallel execution, and validation. Based on Anthropic's Claude Cookbooks.

    The same file is in 1 other repository

  • Firecrawl agent

    arch3rPro/ark-space/plugins/ark-space/skills/firecrawl-agent Skill

    1★ repo

    Use when running Firecrawl Agent for structured extraction, schema-guided web data collection, or ArkSpace structured_extract routing that selects Firecrawl.

  • Orchestrator

    arch3rPro/ark-space/plugins/ark-space/skills/orchestrator Skill

    1★ repo

    Use when a user invokes ArkSpace, asks for general help, a cross-domain task, role selection, skill selection, provider routing, web search/fetch through ArkSpace, or when task scope is unclear.

  • Firecrawl agent

    arch3rPro/ark-space/skills/firecrawl-agent Skill

    1★ repo

    Use when running Firecrawl Agent for structured extraction, schema-guided web data collection, or ArkSpace structured_extract routing that selects Firecrawl.

  • Orchestrator

    arch3rPro/ark-space/skills/orchestrator Skill

    1★ repo

    Use when a user invokes ArkSpace, asks for general help, a cross-domain task, role selection, skill selection, provider routing, web search/fetch through ArkSpace, or when task scope is unclear.

  • Cavecrew

    Shivam990q/better-than-claude-skills/caveman/cavecrew Skill

    1★ repo

    Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

    The same file is in 7 other repositories

  • Caveman compress

    Shivam990q/better-than-claude-skills/caveman/caveman-compress Skill

    1★ repo

    Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"

    The same file is in 4 other repositories

  • Claude api

    Shivam990q/better-than-claude-skills/claude-api Skill

    1★ repo

    Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.

  • Mcp builder

    Shivam990q/better-than-claude-skills/mcp-builder Skill

    1★ 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

    Shivam990q/better-than-claude-skills/skill-creator Skill

    1★ repo

    Behavioral guidelines to reduce common LLM coding mistakes AND a complete system for creating, testing, and optimizing skills. Use this skill WHENEVER the user asks you to write, review, debug, refactor, or discuss code — or whenever you are about to generate any code yourself. Also use when the user wants 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. Apply to every coding task including fixing bugs, adding features, creating new files, refactoring, code reviews, architecture discussions, writing tests, and skill development.

  • Microsoft skill creator

    The-Biomechanist/Windows-Toolchain-Forensics/mcp-main/skills/microsoft-skill-creator Skill

    1★ repo

    Create agent skills for Microsoft technologies using Learn MCP tools. Use when users want to create a skill that teaches agents about any Microsoft technology, library, framework, or service (Azure, .NET, M365, VS Code, Bicep, etc.). Investigates topics deeply, then generates a hybrid skill storing essential knowledge locally while enabling dynamic deeper investigation.

  • Humanizer

    svyatov/agent-toolkit/plugins/humanizer/skills/humanizer Skill

    1★ repo

    Remove signs of AI-generated writing from prose that carries a personal voice, tuned for Claude output. Use when the user asks to humanize, de-AI, clean up, or improve the tone of blog posts, essays, opinion pieces, launch announcements, newsletters, emails, or long-form articles that read like an LLM wrote them. Also use to judge whether a given text was AI-generated. Triggers on AI patterns like markdown overuse, AI vocabulary, sycophantic openers, post action summaries, standalone caveat lines, unsolicited safety disclaimers, vague attributions, significance inflation, em dash overuse, or manufactured drama. Not for prose that lives in a repository or on a forge: commits, PRs, reviews, issues, READMEs, docs, changelogs, code comments, error messages.

  • Llms visibility

    svyatov/agent-toolkit/plugins/llms-visibility/skills/llms-visibility Skill

    1★ repo

    Make websites, docs, blogs, or landing pages visible and readable to LLMs and AI agents — ChatGPT, Claude, Perplexity, Cursor, Claude Code, and other coding agents that fetch URLs. Use this for any request involving llms.txt, llms-full.txt, serving .md/Markdown versions of pages, Accept text/markdown content negotiation, Link rel="alternate" headers, Cloudflare Content-Signal in robots.txt, GEO (generative engine optimization), AI-friendly / AI-readable / LLM-discoverable sites, getting cited in ChatGPT or Perplexity answers, or fixing pages where AI tools fetch JavaScript bundles or empty React roots instead of content. Also use to push back on debunked patterns: ai.txt, AI meta tags, hidden HTML comments, AI toggle buttons, User-Agent sniffing, JSON-LD aimed at LLMs. Do NOT use for traditional Google SEO, sitemap.xml, schema.org rich snippets for search engines, WCAG/accessibility audits, or CSP/security headers.

  • Github ticket lifecycle orchestrator

    chf3198/megingjord-harness/skills/github-ticket-lifecycle-orchestrator Skill

    no license1★ repo

    Naming conventions and phase protocol for GitHub ticket lifecycle. Baton workflow in manager-ticket-lifecycle.

  • Llm wiki ops portable

    chf3198/megingjord-harness/skills/llm-wiki-ops-portable Skill

    no license1★ repo

    Operate an LLM Wiki knowledge system in any workspace using the Karpathy pattern

  • Llm wiki ops

    chf3198/megingjord-harness/skills/llm-wiki-ops Skill

    no license1★ repo

    Operate and maintain the LLM Wiki knowledge system in the Megingjord source workspace.

  • Openclaw universal system

    chf3198/megingjord-harness/skills/openclaw-universal-system Skill

    no license1★ repo

    Make OpenClaw a reusable machine-global execution system for all VS Code Copilot agent chats, regardless of repository, by standardizing routing, observability, and decision checkpoints.

  • Role baton orchestrator

    chf3198/megingjord-harness/skills/role-baton-orchestrator Skill

    no license1★ repo

    Orchestrate single-thread baton handoff across Manager -> Collaborator -> Admin -> Consultant with explicit entry/exit contracts.

  • Skill quality

    adhi-jp/agent-skills/skills/skill-quality Skill

    1★ repo

    Workflow-focused agent skills and evaluation suites for software development, skill maintenance, and Minecraft modding.

  • Vibe writing

    adhi-jp/agent-skills/skills/vibe-writing Skill

    1★ repo

    Workflow-focused agent skills and evaluation suites for software development, skill maintenance, and Minecraft modding.

  • Katana

    shane9coy/katana-agent/agent/skills/agents/katana Skill

    no license1★ repo

    Katana Sensei — life & business orchestrator powered by the 3 I's (Intelligence, Intuition, Initiative). Auto-loads memory on session start (soul.md, user.md, work.md, tasks.md). Runs morning briefings, evening check-ins, task daily iteration, inspirational quotes (Musashi, Stoic, Zen), profile management, and delegates to all agents. Use for any daily routine, task management, memory operations, quote requests, scheduling, or orchestration.

  • Obsidian memory

    shane9coy/katana-agent/agent/skills/memory/obsidian-memory Skill

    no license1★ repo

    Connect to Katana's centralized memory vault. Use when remembering, recalling, or referencing past sessions, projects, user preferences, or agent identity. Triggered by: /remember, /recall, session start, or any reference to past work.

  • Obsidian memory

    shane9coy/katana-agent/templates/claude/skills/obsidian-memory Skill

    no license1★ repo

    Connect to Katana's centralized memory vault. Use when remembering, recalling, or referencing past sessions, projects, user preferences, or agent identity. Triggered by: /remember, /recall, session start, or any reference to past work.

  • Obsidian memory

    shane9coy/katana-agent/templates/codex/skills/obsidian-memory Skill

    no license1★ repo

    Connect to Katana's centralized memory vault. Use when remembering, recalling, or referencing past sessions, projects, user preferences, or agent identity. Triggered by: /remember, /recall, session start, or any reference to past work.

  • Obsidian memory

    shane9coy/katana-agent/templates/generic/skills/obsidian-memory Skill

    no license1★ repo

    Connect to Katana's centralized memory vault. Use when remembering, recalling, or referencing past sessions, projects, user preferences, or agent identity. Triggered by: /remember, /recall, session start, or any reference to past work.

  • Obsidian memory

    shane9coy/katana-agent/templates/kilocode/skills/obsidian-memory Skill

    no license1★ repo

    Connect to Katana's centralized memory vault. Use when remembering, recalling, or referencing past sessions, projects, user preferences, or agent identity. Triggered by: /remember, /recall, session start, or any reference to past work.

  • Obsidian memory

    shane9coy/katana-agent/templates/universal/skills/obsidian-memory Skill

    no license1★ repo

    Connect to Katana's centralized memory vault. Use when remembering, recalling, or referencing past sessions, projects, user preferences, or agent identity. Triggered by: /remember, /recall, session start, or any reference to past work.

  • Llm app engineering

    SWEStash/swe-workflow-skills/plugins/ai/skills/llm-app-engineering Skill

    1★ repo

    Design and build LLM-powered applications — prompt and context engineering, RAG architecture (chunking, hybrid retrieval, reranking, grounded prompts), agent design (tool surfaces, planning, sub-agents), and memory. Triggers: build a chatbot, LLM app, AI assistant, prompt engineering, system prompt, RAG design, chunking, embeddings, vector database, semantic search, AI agent, tool calling, agent memory, context window, hallucinations. Measuring quality → ai-evaluation; model serving/inference infra → ml-model-deployment.

  • Ai evaluation

    SWEStash/swe-workflow-skills/plugins/data-scientist/skills/ai-evaluation Skill

    1★ repo

    Define how to evaluate ML models and GenAI/LLM apps — golden datasets, offline metrics, RAG evaluation (faithfulness, relevance, context precision/recall) with ragas/deepeval/promptfoo, LLM-as-judge design and calibration, eval regression gates in CI, online A/B and human feedback. Logging/comparing runs → ml-experiment-tracking; building the app → llm-app-engineering; general experiment statistics → statistical-analysis.

  • Ai evaluation

    SWEStash/swe-workflow-skills/plugins/ml/skills/ai-evaluation Skill

    1★ repo

    Define how to evaluate ML models and GenAI/LLM apps — golden datasets, offline metrics, RAG evaluation (faithfulness, relevance, context precision/recall) with ragas/deepeval/promptfoo, LLM-as-judge design and calibration, eval regression gates in CI, online A/B and human feedback. Logging/comparing runs → ml-experiment-tracking; building the app → llm-app-engineering; general experiment statistics → statistical-analysis.

  • Ai evaluation

    SWEStash/swe-workflow-skills/skills/ai-evaluation Skill

    1★ repo

    Define how to evaluate ML models and GenAI/LLM apps — golden datasets, offline metrics, RAG evaluation (faithfulness, relevance, context precision/recall) with ragas/deepeval/promptfoo, LLM-as-judge design and calibration, eval regression gates in CI, online A/B and human feedback. Logging/comparing runs → ml-experiment-tracking; building the app → llm-app-engineering; general experiment statistics → statistical-analysis.

  • Llm app engineering

    SWEStash/swe-workflow-skills/skills/llm-app-engineering Skill

    1★ repo

    Design and build LLM-powered applications — prompt and context engineering, RAG architecture (chunking, hybrid retrieval, reranking, grounded prompts), agent design (tool surfaces, planning, sub-agents), and memory. Triggers: build a chatbot, LLM app, AI assistant, prompt engineering, system prompt, RAG design, chunking, embeddings, vector database, semantic search, AI agent, tool calling, agent memory, context window, hallucinations. Measuring quality → ai-evaluation; model serving/inference infra → ml-model-deployment.

  • Subagent orchestration

    SWEStash/swe-workflow-skills/skills/subagent-orchestration Skill

    1★ repo

    Decompose big or parallelizable work across subagents — when to fan out vs stay solo, scoping self-contained sub-tasks, prompting agents that don't share your context, isolating parallel edits (git worktrees), skeptically verifying and synthesizing results you didn't produce. Triggers: use subagents, parallelize this, fan out, orchestrate agents, multi-agent, spawn agents, worktree, delegate to agents, split this across agents, agent team. Sequencing checkpoints of an approved plan → plan-execution (orchestration parallelizes within its batches).

  • Manage agent config

    Miyamura80/MCP-Template/.agents/skills/manage-agent-config Skill

    1★ repo

    Manage files under .claude/{skills,agents,rules}/, .agents/{skills,rules}/, or .codex/agents/. Covers dual-tool Claude/Codex layout and reminds to run make sync-agent-config.

  • New agent rule

    Miyamura80/MCP-Template/.agents/skills/new-agent-rule Skill

    1★ repo

    Guide for creating a new path-scoped .claude/rules/ file with proper globs frontmatter and structure.

  • Prek precommit hook

    Miyamura80/MCP-Template/.claude/skills/prek-precommit-hook Skill

    1★ repo

    Instructions for managing and running git hooks using `prek`. Use this skill for any mention of pre-commit hooks, as `prek` overrides pre-commit hooks.

  • Gmail mcp

    Miyamura80/MCP-Template/landing-page/public/.well-known/agent-skills/gmail-mcp Skill

    1★ repo

    Triage and curate a Gmail inbox by connecting to the GmailMCP server over MCP and calling its typed tools.

  • Gmail mcp

    Miyamura80/MCP-Template/skills/gmail-mcp Skill

    1★ repo

    Triage and curate a Gmail inbox by connecting to the GmailMCP server over MCP and calling its typed tools.

  • Ascend memory

    Lukk17/agent-standards/.agents/skills/ascend-memory Skill

    1★ repo

    Long-term semantic memory for the user via the self-hosted AscendMemory service. Use this whenever the agent needs to remember something across conversations, recall a prior fact about the user, store a preference or note "for later", or pull back relevant context before answering. Trigger on phrases like "remember that…", "what did I tell you about…", "save this", "forget this", or any time persistent recall would obviously help.

  • Home assistant

    Lukk17/agent-standards/.agents/skills/home-assistant Skill

    1★ repo

    Home Assistant automation standards covering YAML conventions, entity naming, event-driven design, MCP server rules, backup, and notification routing.

  • Markdown writer

    Lukk17/agent-standards/.agents/skills/markdown-writer Skill

    1★ repo

    Use PROACTIVELY whenever the user wants to write, polish, audit, restructure, generate, or translate human-facing markdown such as README.md, docs landing pages, contributor guides, technical posts. Triggers on phrases like "fix my README", "write a README for this repo", "the README is messy", "add a diagram", "this looks AI-written", "translate the README to Spanish", "polish docs/INGESTION.md", or any portfolio-facing markdown work. Produces honest, human-sounding, structurally consistent docs with Mermaid diagrams, real comparisons, and a strict voice. Pulls source-of-truth from existing AGENTS.md or docs/ before guessing. Skips in-code docstrings, AGENTS.md / CLAUDE.md (machine-facing), ADRs, OpenSpec specs, CHANGELOG, and other format-specific files; those keep their own conventions.

  • Mongodb search and ai

    Lukk17/agent-standards/.agents/skills/mongodb-search-and-ai Skill

    1★ repo

    Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG applications), or combined approaches. Also use when users need text containment, substring matching ('contains', 'includes', 'appears in'), case-insensitive or multi-field text search, or filtering across many fields with variable combinations. Provides workflows for selecting the right search type, creating indexes, constructing queries, and optimizing performance using the MongoDB MCP server.

  • Session handoff

    andreab67/agent-skills/session-handoff Skill

    1★ repo

    Run manually before ending a session — `/clear`, `/compact`, switching repos, or any context wipe — to rescue critical context that would otherwise die with the conversation. Trigger phrases include "about to /clear", "before I clear", "wrap up this session", "checkpoint before clearing", "hand off this session", "save context first", "preserve what we just figured out", "I'm switching repos", "/session-handoff". Extracts goals, pending tasks, preferences, working rules, key background, and open questions into the project's auto-memory store, applying a rescue test (skip anything derivable from code/git/CLAUDE.md) with explicit per-entry user approval before writing. Do NOT use for ad-hoc single-fact saves (write the memory file directly — full extraction is overkill), for sessions already captured by a diff and commit, or after `/clear` has already run (context is gone — say so and offer the hook setup). (Six categories, rescue test, and workflow are detailed in the body.)

  • Npx skills

    petr-korobeinikov/skills/skills/npx-skills Skill

    1★ repo

    Documents the `npx skills` CLI for installing and updating agent skills, plus the project-level `skills-lock.json` lockfile. On start, detects a `skills-lock.json` without installed skills under `.claude/skills/` and proposes restoring them via `npx skills add … --copy -y` per the source recorded in the lockfile.

  • Setup

    Background-Craft/hydrant-skills/skills/setup Skill

    1★ repo

    First-run install for hydrant-skills — detect the active harness, configure the hosted Hydrant MCP server, write a fenced "Hydrant lifecycle workflow" section into AGENTS.md (and CLAUDE.md if Claude Code), and verify the connection by calling `mcp__hydrant__list_spaces`. Use when the user asks for `/setup`, says "set up hydrant-skills", "install Hydrant MCP", "wire up Hydrant", or runs the toolkit for the first time after `npx skills add`.

  • Canopy intelligence

    UniverLab/skills/canopy-intelligence Skill

    1★ repo

    Use this skill when the Canopy MCP server is available in the session and you need to pull workspace context or persist durable knowledge. It covers the Project Intelligence Layer (PIL): when to call get_tools and intelligence_get_context, and when to register facts and patterns with intelligence_upsert so future sessions inherit what you learned.

  • Canopy sync

    UniverLab/skills/canopy-sync Skill

    1★ repo

    Use this skill when the Canopy MCP server is available and you are about to act on a shared workspace: writing files, running builds or tests, installing dependencies, or committing. It defines the action-driven sync protocol (sync_get_context, sync_declare_intent, sync_broadcast, sync_report_status) that keeps solo history clean and multi-agent work conflict-free.