convez.ai
MCP Server
agentskillexchange

agent-skills-resources

agentskillexchange/agent-skills-resources

Ver no GitHub
BomPluginScore · de 0 a 100

Source-backed companion guide for agent skills, AI agent workflows, framework resources, evaluation templates, and rollout playbooks.

Instalação

$npx convez-ai agentskillexchange/agent-skills-resources

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
1
Acompanhando
0
Saúde
75%
Último commit
há 2 dias
Versão
—
Issues abertas
1
Contribuidores
1

README

A tradução para o português deste README ainda está na fila.

Agent Skills Resources

A source-backed companion resource hub for agent skills, AI agents, coding agents, and skill-based agent workflows.

Use this repo to learn the ecosystem, compare frameworks, evaluate skills, and run pilots. Use agentskillexchange/skills as the canonical catalog, and use Agent Skill Exchange to browse the live marketplace.

Source labels Companion repo

Start with the Overview or the generated Repo Stats.

Start Here In 60 Seconds

  1. Read the Awesome Agent Skills front door.
  2. Compare surfaces in Framework Comparison.
  3. Pick a practical path from Starter Kits.
  4. Browse real skills in the canonical ASE skills repo.

About This Repo

This is a source-backed companion guide for agent skills and AI agent workflows. It provides framework resources, visual maps, examples, rollout playbooks, evaluation templates, and source-labeling guidance. The installable skill source of truth remains agentskillexchange/skills.

What You'll Find Here

NeedStart here
Learn the agent skills ecosystemOverview
Compare Codex, Claude Code, GitHub Copilot, OpenClaw, Hermes, Cursor, Gemini CLI, LangChain, LangGraph, MCP, and OpenAI Agents SDKFramework pages
Review source-backed resourcesResource Index
Evaluate skill quality and agent safetyQuality Checklist
Run a bounded rolloutPlaybooks and Templates

I Want To

GoalGo here
Understand agent skillsAwesome Agent Skills
Compare frameworksFramework Comparison
Find official resourcesResource Index
Evaluate a skillQuality Checklist
Build a skillSkill Author Starter Kit
Run a team pilotTeam Evaluation Starter Kit
Browse the canonical catalogAgent Skill Exchange

Use This Repo When

  • You want to understand where agent skills fit across AI agents, coding agents, MCP, Model Context Protocol, Codex, Claude Code, GitHub Copilot, OpenClaw, Hermes Agent, Cursor, Gemini CLI, LangChain, LangGraph, and OpenAI Agents SDK.
  • You need source-backed framework resources, visual maps, examples, skill evaluation templates, agent safety checks, verification guidance, or rollout playbooks.
  • You want representative examples without copying the full catalog.

Do Not Use This Repo For

  • The full skill catalog.
  • The installable skill source of truth.
  • Official vendor claims unless the claim is source-backed.
  • Catalog-wide generated skill dumps.

What This Is

Agent skills are reusable instructions, workflows, and tool-usage patterns that help agents perform repeatable work. A good skill explains when to use a tool, how to set it up, what safety checks matter, and how to verify the result.

This repo helps developers answer four questions:

  • Where do skills fit in the agent stack?
  • Which labs, frameworks, and runtimes support skill-like workflows?
  • How should teams evaluate, write, and verify skills?
  • Where can I find source-backed examples without confusing them for the main ASE catalog?

It covers MCP and the Model Context Protocol, verification, skill evaluation, rollout playbooks, and practical adoption evidence for teams working with agentic development and operations.

How This Differs From agentskillexchange/skills

RepoPurposeUse it for
agent-skills-resourcesCompanion guideLearning, diagrams, framework links, best practices, and curated examples
agentskillexchange/skillsCanonical catalogActual skill files, generated indexes, categories, verification, and installable entries
agentskillexchange.comLive marketplaceBrowsing, search, skill pages, industry collections, and creation workflows

Skill Ecosystem Layers

LayerExamplesWhat skills add
Model/providerOpenAI, Anthropic, GoogleModel-specific setup and constraints
RuntimeCodex, Claude Code, GitHub Copilot, OpenClaw, Hermes, Cursor, Gemini CLIRepeatable agent workflows
FrameworkLangGraph, OpenAI Agents SDK, ADKOrchestration patterns and state
Protocol/toolingMCP, CLIs, APIs, browser toolsTool setup, permissions, and usage recipes
Verificationtests, scans, traces, approvalsEvidence that the workflow worked

Ecosystem Map

flowchart LR
  User["User or team"] --> Runtime["Agent runtime"]
  Runtime --> Framework["Agent framework or coding agent"]
  Framework --> Skills["Skills layer"]
  Skills --> Tools["Tools, APIs, CLIs, MCP servers"]
  Skills --> Context["Memory and context"]
  Skills --> Safety["Verification and guardrails"]
  Skills --> Ops["Schedules, crons, deployments"]
  Safety --> Evidence["Tests, scans, logs, citations"]
  Tools --> Outcome["Repeatable workflow outcome"]
  Evidence --> Outcome

Quick Paths

PathStart hereWhat to read next
New to skillsGetting StartedEcosystem Map
Skimming the ecosystemAwesome Agent SkillsFramework Comparison
Building a skillBest PracticesASE skills repo
Comparing frameworksFramework pagesresources.json
Choosing a starter pathStarter KitsAdoption Matrix
Exploring workflowsWorkflow pagesASE skill mapping
Applying skills to scenariosCase StudiesGenerated skill mapping index
Planning adoptionPlaybooksAdoption Matrix
Running a pilotEvaluation TemplatesTemplate Index
Reviewing qualityAnnotated ExamplesQuality Checklist
Maintaining resourcesFreshness AuditSource Labeling
Evaluating trustBest PracticesASE verification
ContributingCONTRIBUTINGASE Create Skill

Framework And Resource Guide

AreaRole in the ecosystemGuide
CodexCoding agent and terminal workflow runtimeCodex
Claude CodeCoding agent with project workflows, tools, and automationClaude Code
GitHub CopilotGitHub-native coding assistant, cloud agent, CLI, SDK, MCP, and skills surfaceGitHub Copilot
OpenClawAgent runtime for providers, crons, skills, tools, and channelsOpenClaw
HermesSelf-improving agent with skills, memory, and agent-managed workflowsHermes
CursorIDE agent environment with context, skills, and background agentsCursor
Gemini CLIOpen-source terminal agent from GoogleGemini
LangChain / LangGraphAgent orchestration and stateful workflow frameworkLangChain / LangGraph
MCPProtocol for connecting agents to tools and context providersMCP

Source Labels

Every resource in data/resources.json uses one of four labels:

  • Official: vendor or project-owned documentation or repository.
  • Lab: research lab, model provider, or frontier-lab material.
  • Community: useful third-party material that is not official.
  • ASE: Agent Skill Exchange site, repo, data, or documentation.

When a claim is not source-backed, leave it out.

Data Files

Quality Loop

Use the repo as a small maintenance loop:

  1. Add or revise source-backed resources.
  2. Map only existing ASE skill slugs.
  3. Review examples against the quality checklist.
  4. Run validation and freshness checks.
  5. Keep source labels honest when ownership changes.

Validation

python3 scripts/validate-resources.py
python3 scripts/validate-links.py
python3 scripts/audit-freshness.py
python3 scripts/generate-resource-index.py
python3 scripts/generate-skill-mapping-index.py
python3 scripts/generate-nav-index.py
python3 scripts/generate-template-index.py
python3 scripts/generate-repo-stats.py

Loop Roadmap

Future loops should expand one area at a time:

  1. Deepen Codex, Claude Code, GitHub Copilot, OpenClaw, Hermes, Cursor, Gemini, LangGraph, and MCP pages.
  2. Add more ASE skill mappings from the public catalog.
  3. Add visual workflow stacks for security, data, SRE, legal, GTM, and support.
  4. Add a freshness audit that flags moved docs, stale links, or unsupported claims.
  5. Add deeper case studies for teams evaluating adoption paths.
  6. Add adoption playbooks for team-specific rollout decisions.
  7. Add fillable pilot templates for recording evidence and go/no-go decisions.
  8. Add completed evaluation examples and repo stats for stronger first-read clarity.
Ver o original no GitHub

Bom para

Relacionados