mcpbeat

Agent Workflow Claude Skills

4 082 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 830 tokens or less — that is what one costs your context window when the agent loads it. 769 ship runnable scripts rather than instructions alone. 5 of them cannot work without an MCP server, most often task. We also found 541 copies of these same skills sitting in other people's repositories — counted once here, not 541 times.

4 082 unique 665 authors 2 733 updated this month 466 from vendors

1 830
tokens, median
what a typical one costs in context
769
ship scripts
code that runs, not instructions alone
5
need a server
most often task
541
copies elsewhere
counted once here, not once per repository

961–1 008 of 4 082

page 21 of 86
Skill Creator
AIPexStudio

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 AIPex's capabilities with specialized knowledge, workflows, or tool integrations.

13k tokens scripts
Building With AI Agents
RefoundAI

Help users master the transition from manual coding to managing AI-driven development workflows by focusing on high-level direction, parallel tasking, and rigorous automated review.

17k tokens
Clinical Delegation vendor
NVIDIA

How to delegate clinical tasks to specialist agents. Always use sub-agent runtime with explicit agentId — never ACP. Never call FHIR via web_fetch.

660 tokens
Oma Orchestrator
first-fluke

Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress. Use for orchestration, parallel execution, and automated multi-agent workflows.

9k tokens scripts
Oma Skill Creator
first-fluke

> Create or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents/skills/{skill-name}/SKILL.md`, converting an existing skill to the standardized Scheduling / Structural Flow / Logical Operations / References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.

6k tokens
Oma Orchestrator
first-fluke

Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress. Use for orchestration, parallel execution, and automated multi-agent workflows.

7k tokens scripts
Oma Skill Creator
first-fluke

> Create or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents/skills/{skill-name}/SKILL.md`, converting an existing skill to the standardized Scheduling / Structural Flow / Logical Operations / References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.

4k tokens
Folded Desc Skill
first-fluke

> A fixture whose description uses a YAML folded scalar, which parses with an embedded trailing newline unless normalized before use in Markdown tables.

57 tokens
Oversized Skill
first-fluke

A skill whose body deliberately exceeds the 500-line recommendation.

4k tokens
Valid Skill
first-fluke

A minimal, fully spec-conformant fixture skill used to exercise the happy path.

51 tokens
Xcode Build Orchestrator
AvdLee

Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval, delegating approved fixes to xcode-build-fixer, and re-benchmarking after changes. Use when a developer wants an end-to-end build optimization workflow, asks to speed up Xcode builds, wants a full build audit, or needs a recommend-first optimization pass covering compilation, project settings, and packages.

20k tokens scripts
Add New Opc Skill
ReScienceLab

Checklist and automation guide for adding a new skill to the OPC Skills project. Ensures all required files, metadata, logos, and listings are created before release. Use when adding a new skill, publishing a skill, or preparing a skill for release.

2k tokens
Agent Team Design
agentlas-ai

Use when designing a new multi-agent team, visible agents folder, role boundaries, handoff flow, PM Soul, Memory Curator, Policy Gate, or evaluation role. Use for agent-team repo creation even when the user only says they want a meta-agent or agent operating system.

225 tokens
Agentlas Core Engine Meta Agent
agentlas-ai

Use when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into Agentlas architecture. Make sure to use this for /meta-agent requests.

383 tokens
Agentlas Packaging
agentlas-ai

Use when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local install, Agentlas import, Codex plugin use, Claude adapter use, or open-source release.

460 tokens
Hephaestus Network
agentlas-ai

Use when the user types $hephaestus-network or /hep-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.

4k tokens
Install Verification
agentlas-ai

Use when verifying that a generated agent package can be installed, discovered by runtimes, and checked without private dependencies.

125 tokens
LLM Runtime Architecture
agentlas-ai

Use when designing how one canonical agent core runs across Codex, Claude Code, Gemini CLI, Cursor, and AGENTS.md-compatible tools.

196 tokens
Mode Classification
agentlas-ai

Use before routing a /meta-agent request to choose single-agent-creator, team-builder, or agentlas-packager from the user's wording and available files.

750 tokens
Public Plugin Packaging
agentlas-ai

Use when packaging an Agentlas agent repo for public GitHub release, Codex plugin submission, Claude adapter distribution, or one-line terminal installation.

206 tokens
Routing Card Authoring
agentlas-ai

Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.

3k tokens
Runtime Adapters
agentlas-ai

Use when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. Use whenever a generated repo needs multiple AI runtimes without duplicating instructions.

241 tokens
Self Evolving Single Agent
agentlas-ai

Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or improve itself over time without becoming a multi-agent team.

423 tokens
Sitemap Task Bias
agentlas-ai

Use when creating or auditing an agent-team sitemap, Task Bias ledger, concept coverage, product surface map, validation chain, or missing-concept check.

205 tokens
Skill Lifecycle Promotion
agentlas-ai

Use when adding or auditing Agentlas skill lifecycle metadata, skill-registry.json, trial evidence, Curator promotion decisions, or first-class skill promotion gates.

299 tokens
Team Builder Packaging
agentlas-ai

Use when generating or auditing a multi-role agent team package with orchestrator, PM Soul, Memory Curator, Policy Gate, workers, eval, QA, handoffs, and runtime adapters.

406 tokens
Agentlas Core Engine Meta Agent
agentlas-ai

Use when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into Agentlas architecture. Make sure to use this for /meta-agent requests.

385 tokens
Hephaestus Build
agentlas-ai

Use when the user types /prompts:hep-build, mentions @Hephaestus for build work, asks to create a single Agentlas agent, create a multi-agent team, or package an existing local/external agent into Agentlas architecture.

1k tokens
Hephaestus Cloud
agentlas-ai

Use when the user types /hep-cloud or asks to find/route to one of THEIR OWN Agentlas cloud packages (보관함, 내 클라우드, 내 보관함, my cloud, my own agents). This is the owner-scoped leg of the three-scope model — it searches ONLY the signed-in user's own cloud packages, not the public marketplace (use hephaestus-network for that) and not local cards. The user's own cloud packages are restorable/owned by them and call-priced at a flat 1 credit.

1k tokens
Hephaestus Network
agentlas-ai

Use when the user asks OpenClaw to staff a durable goal from Agentlas Hub agents or teams. The active host LLM chooses the exact roster, which remains goal-bound until explicit completion.

718 tokens
Agentlas Packaging
agentlas-ai

Use when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local install, Agentlas import, Codex plugin use, Claude adapter use, or open-source release.

782 tokens
Public Plugin Packaging
agentlas-ai

Use when packaging this meta-agent for public Codex plugin registration, Claude Code installation, GitHub release, one-line terminal install, or open-source distribution.

292 tokens
Self Evolving Single Agent
agentlas-ai

Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or improve itself over time without becoming a multi-agent team.

466 tokens
Team Builder Packaging
agentlas-ai

Use when generating or auditing a multi-role agent team package with orchestrator, PM Soul, Memory Curator, Policy Gate, workers, eval, QA, handoffs, and runtime adapters.

640 tokens
Profile Test Skill vendor
microsoft

| **PROFILE TEST** - A skill for testing the profile command.

306 tokens
Waza vendor
microsoft

**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators. USE FOR: run waza, waza help, run eval, run benchmark, evaluate skill, test agent, generate eval suite, init eval, compare results, score agent, agent evaluation, skill testing, cross-model comparison. DO NOT USE FOR: improving skill frontmatter (use waza dev), creating new skills from scratch (use skill-creator), token counting or budget checks (use waza tokens). INVOKES: Copilot SDK executor, mock engine, code/regex validators. FOR SINGLE OPERATIONS: use waza run directly for a single benchmark.

2k tokens
Waza Interactive vendor
microsoft

Interactive workflow partner for creating, testing, and improving AI agent skills with waza. USE FOR: run my evals, check my skill, compare models, create eval suite, debug failing tests, is my skill ready, ship readiness, interpret results, improve score. DO NOT USE FOR: general coding, non-skill work, writing skill content (use skill-authoring), improving frontmatter only (use sensei).

2k tokens
Waza Runner vendor
microsoft

| Run evaluations on Agent Skills to measure their effectiveness. "check skill triggers", "skill compliance check", "measure skill performance", "run evals on [skill-name]", "grade skill execution". (use sensei), or general testing unrelated to skills.

1k tokens
Agent Context Audit
AI-Builder-Club

> Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.

2k tokens
Open Agent Teams
AI-Builder-Club

Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or when executor work should run in an observable background terminal instead of the Agent tool.

3k tokens scripts
Skillpack Creator
CreminiAI

Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with `skillpack.json`, local skills under `skills/`, starter prompts, start scripts, and an optional zip package.

3k tokens scripts
Audit Library Health
MoizIbnYousaf

Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.

518 tokens
Best Practices
MoizIbnYousaf

>- Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.

37k tokens
Browse And Evaluate
MoizIbnYousaf

Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.

452 tokens
Install From Remote Library
MoizIbnYousaf

Use when installing skills from a shared ai-agent-skills library repo. Inspect with `--list` first, prefer `--collection`, and preview with `--dry-run` before installing.

530 tokens
LLM Application Dev
MoizIbnYousaf

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

1k tokens
Migrate Skills Between Libraries
MoizIbnYousaf

Use when moving skills between library workspaces or upgrading from a personal library to a team library. Export from one workspace, import into another.

668 tokens
Review A Skill
MoizIbnYousaf

Use when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and decide whether to keep, curate, or remove.

577 tokens