Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
agent-fetcher
by ForgePlanMethodology: Cross-marketplace agent/skill suggestion (suggest-only, NO auto-install). EN: When canonical 17 forgeplan-aware agents don't fit the task, searches installed marketplaces (~/.claude/plugins/marketplaces/) for matching agents/skills. Ranks by keyword overlap + trust tier + specificity. Surfaces top 3 with description + install command + security caveats. NEVER auto-installs — user runs the command manually. Falls back to external catalogs (VoltAgent awesome-*, DenisSergeevitch) when no local match. RU: Когда канонических 17 forgeplan-aware агентов не хватает, ищет среди установленных маркетплейсов подходящих агентов/скиллов. Ранжирует по ключевым словам + tier + специфичности. Показывает топ-3 с описанием + командой установки + предупреждениями. НЕ устанавливает автоматически. Fallback на external catalogs. Triggers: "find agent for", "fetch agent", "external agent", "cross-marketplace agent", "search marketplaces", "найди агента", "поищи в маркетплейсах", "/agent-fetcher"
fpl-init
by ForgePlanOne-command project bootstrap for the ForgePlan ecosystem. Probes the forgeplan CLI, runs `forgeplan init`, wires `.mcp.json` and `.claude/settings.json`, then chains `/bootstrap` (universal CLAUDE.md template) and `/setup` (docs/agents/ wizard) so a fresh repo is fully wired in one shot. Recommends — but does not install — companion plugins (fpf, laws-of-ux, agents-core, forgeplan-workflow, forgeplan-orchestra). v2.0: Adds optional `--canonize` step that scaffolds the canonical agent layer (project-agent-matrix.yaml + project-config.yaml + Hindsight mental models) for forgeplan-aware projects per PRD-026 Phase 5. Use on a brand-new project, or on an existing project that has none of `.forgeplan/`, `CLAUDE.md`, `docs/agents/`. Triggers (EN/RU) — "fpl init", "init project", "bootstrap forgeplan", "set up everything", "full project setup", "/fpl-init", "поставь всё", "разверни проект с нуля", "инициализируй проект", "fpl init canonize", "setup agent matrix", "v2 bootstrap".
project-agent-scaffold
by ForgePlanMethodology: Project-scoped agent generation via tech-stack detection. EN: Detects project tech stack from package manifests (package.json, Cargo.toml, go.mod, pyproject.toml, pom.xml, mix.exs, Gemfile, composer.json, Package.swift, pubspec.yaml) + secondary signals (tailwind.config.*, next.config.*, nuxt.config.*, docker-compose.yml). Classifies signals into a stack profile, proposes 1–3 project-scoped agents (project:<slug>-pro) baked from agent-template.md with stack-specific patterns. Asks approval per proposal before writing any file. Does NOT auto-create — user always confirms. Writes agent files to .claude/agents/ on approval and suggests project-agent-matrix.yaml entries for dispatch overrides. RU: Определяет технологический стек проекта по package-манифестам + вторичным сигналам. Классифицирует в stack profile, предлагает 1–3 project-scoped агента (project:<slug>-pro) на базе agent-template.md. Спрашивает подтверждения для каждого предложения. Записывает только после согласия пользователя. НЕ создаёт
cc-best
by ForgePlanClaude Code ecosystem best practices — opinionated reference for CLAUDE.md, plugins, agents, hooks, MCP, and anti-patterns. Synthesises real ForgePlan production experience (18 plugins, 47+ audit findings). Use when authoring CLAUDE.md, designing a plugin, writing an agent, configuring hooks, or asking what NOT to do. Sections load on demand via agentic RAG (≤300 lines per file). Triggers: "claude code best practices", "claude-md structure", "how to write CLAUDE.md", "plugin patterns", "agent frontmatter", "hook ordering", "mcp gotchas", "anti-patterns claude code", "common claude code mistakes", "лучшие практики Claude Code", "как писать CLAUDE.md"
canonical-reproducer
by ForgePlanProduces self-contained standalone documents (DDL, pseudo-code, SDL) with zero `file:line` references in final sections. Triggers — "extract canonical reproducer", "brownfield canonical reproducer", "/canonical-reproducer".
kg-curator
by ForgePlanBuilds and maintains the knowledge graph connecting glossary terms, use-cases, invariants, scenarios, hypotheses, domain-models. Detects contradictions. Triggers — "extract kg curator", "brownfield kg curator", "/kg-curator".
supersede
by ForgePlanWalk the complete supersede-ADR workflow with mandatory OpenSpec delta-spec discipline. Reads the old ADR, verifies it is active, computes the user's intended delta, creates the new ADR using the adr-supersede.md template (all four delta sections: ADDED / MODIFIED / REMOVED / UNCHANGED), links supersedes, and marks the predecessor superseded. Triggers: "supersede", "supersede ADR", "замени ADR", "обнови решение", "supersede decision", "evolve ADR", "replace ADR", "/supersede" Sprint Z8 PRD-058 — EPIC-001 S12 OpenSpec layer.
tdd
by ForgePlanEnforced-TDD entry point. Runs the C1-C6 sub-cycle the tdd-orchestrator drives: precondition check (PRD + SPEC active with #### Scenarios) → tdd-planner (scenarios → test plan) → coder-tdd (RED: plan → failing tests) → tdd-test-validator (C4: certify tests, freeze the SPEC oracle on PASS via a normalized full-file hash) → coder (GREEN: code to pass the frozen tests, cannot edit tests) → lint → EVIDENCE-out into the forgeplan Audit. Each tier is a separate isolated dispatch (generator≠verifier). Test immutability during GREEN is enforced by a fail-closed PreToolUse gate, not by prompt. Use when a feature has an active SPEC with #### Scenarios and you want tests-frozen-before-code with structural enforcement. Triggers: "tdd", "/tdd", "test-driven", "test driven development", "write tests first", "RED GREEN", "frozen oracle", "enforced tdd", "tests before code", "напиши тесты сначала", "TDD цикл", "красный зелёный"
ubiquitous-language
by ForgePlanExtracts business terms, definitions, aliases, and synonyms from a codebase to build a domain glossary. Triggers — "extract ubiquitous language", "brownfield ubiquitous language", "/ubiquitous-language".
decay-watch
by ForgePlanScan all active ADR artifacts for fired Revisit Triggers (Evidence Decay). Reports which triggers fired, which need human verification, which are stale because the ADR uses pre-Sprint-Z2 prose format. Use periodically (weekly + at session start) — keeps decisions from quietly going stale. Triggers: "decay watch", "/decay-watch", "проверь триггеры пересмотра", "stale ADR", "revisit trigger check", "evidence decay scan"
conformance-vectors
by ForgePlanThe OPTIONAL `## Conformance Vectors` enrichment for spec-driven development (ADR-008): a frozen, hash-pinned, language-neutral conformance corpus that is the SOLE behavioral oracle for an implementation, plus a per-language harness and a cross-language equivalence gate. Use when a SPEC targets MORE THAN ONE implementation language (REQUIRED — prose scenarios alone diverge across languages) or for a pure algorithmic core where prose under-specifies. Do NOT use for ordinary single-language features — the SPEC's `#### Scenario` blocks are the oracle there. Proven across 4 languages (TS/Py/Go/Rust) in `reference/semver/` (EVID-119). Triggers: "conformance vectors", "conformance corpus", "cross-language equivalence", "multi-language spec", "frozen oracle", "language-neutral corpus", "spec conformance harness", "конформанс-вектора", "кросс-языковая эквивалентность"
sparc
by ForgePlanEntry point for the SPARC feature pipeline — the master-coordinated five-phase walk that drives a SINGLE feature in an EXISTING active system from specification to a completed, independently-verified feature (Specification → Pseudocode → Architecture → Refinement → Completion), the THIRD instance of the AD/AID-PDLC sub-cycle contract (ADR-010 / RFC-016). Dispatches the `sparc-orchestrator` master, which walks the five phases as separate isolated-context agents with a blocking INDEPENDENT quality-gate between each. hook-gate=No: there is NO fail-closed hook — C5 is harness phase-ordering + delegating Refinement to the existing TDD hook-gate (RFC-012) when test-immutability matters. EN: Run SPARC on a single feature in an existing active system — spec → pseudocode → architecture (RFC) → code+tests → completion, with a MANDATORY independent reviewer at every phase gate. Use for one well-scoped feature in an active codebase, NOT a brand-new product from scratch (that is BMAD) or brownfield modernisation (that is
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.