agent-ready-skills

Name: agent-ready-skills
Author: mlava

Verified

Installable skills for using Agent Ready (https://agent-ready.dev) — the agent-readability scanner. Two skills: agent-ready-api (REST) and agent-ready-mcp (MCP server).

0stars

0forks

Added 6/16/2026

View on GitHub Download ZIP Scan for vulnerabilities

30 days in the Featured rail · terms & refunds

AI Agents

Installation

# Add to your Claude Code skills
git clone https://github.com/mlava/agent-ready-skills

Getting Started

Guides for using ai agents skills like agent-ready-skills.

Security ReportVerified

Last scanned: 6/17/2026

{
  "issues": [
    {
      "file": "skills/agent-ready-api/SKILL.md",
      "line": 53,
      "type": "secret-exfiltration",
      "message": "Instruction appears to send credentials/secrets to an external endpoint",
      "severity": "medium"
    },
    {
      "file": "skills/agent-ready-api/SKILL.md",
      "line": 61,
      "type": "secret-exfiltration",
      "message": "Instruction appears to send credentials/secrets to an external endpoint",
      "severity": "medium"
    },
    {
      "file": "skills/agent-ready-mcp/SKILL.md",
      "line": 106,
      "type": "secret-exfiltration",
      "message": "Instruction appears to send credentials/secrets to an external endpoint",
      "severity": "medium"
    }
  ],
  "status": "PASSED",
  "scannedAt": "2026-06-17T09:04:51.777Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

agent-ready-skills

Agent Skills for using Agent Ready — the agent-readability scanner that scores any URL against the Vercel Agent Readability Spec, the llmstxt.org standard, and the agent-protocol manifests (MCP server cards, A2A, agents.json, agent-permissions.json, UCP, x402, NLWeb).

Install one of the skills below and your AI agent can run scans, fetch results, and search the Agent Ready docs without any further setup.

Or add all three at once with the whole-repo form:

npx skills add mlava/agent-ready-skills

Browse the rendered docs on skills.sh: https://www.skills.sh/mlava/agent-ready-skills

Skills

`agent-ready-api`

Use the REST API directly. Best when:

You don't have an MCP host (you're driving a curl / Node / Python script)
You want the leanest possible dependency surface
You need a one-shot scan from a CI step, a serverless function, or a notebook

Install:

npx skills add mlava/agent-ready-skills/skills/agent-ready-api

`agent-ready-mcp`

Use the MCP server (agent-ready-mcp on npm) inside Claude Desktop, Claude Code, Cursor, Cline, Continue, Goose, or any other MCP host. Best when:

You already have one of those clients running
You want tool-native invocation — no curl, no fetch wiring
You want the workflow prompts (scan, interpret_scan, remediation_plan)

Install:

npx skills add mlava/agent-ready-skills/skills/agent-ready-mcp

`agent-ready-cli`

Use the agent-ready command-line client (agent-ready-scanner on npm). Best when:

The agent can run shell commands and you want one command, zero wiring
You don't want to install an MCP server or write fetch/polling code
You're scripting — machine-readable --json to stdout, distinct exit codes

Install:

npx skills add mlava/agent-ready-skills/skills/agent-ready-cli

What is Agent Ready?

Agent Ready runs ~60 checks across four spec families:

Vercel Agent Readability Spec — 15 site-wide + 23 per-page checks (llms.txt, robots.txt, sitemap.xml, sitemap.md, AGENTS.md, JSON-LD, headings, markdown mirrors, content negotiation, code-block language tags, JS-rendering)
llmstxt.org — 10 checks against the llms.txt file format
Agent protocols — MCP server cards (SEP-1649), A2A agent cards, agents.json, agent-permissions.json, UCP, x402, NLWeb
Authentication discovery — RFC 9728 PRM + RFC 8414 AS metadata, WorkOS auth.md

Pricing:

Plan	Price	Pages/scan	Scans	API access
Free	$0 / month	25	10 / 30 days	No
Pro	$19 / month	250	50 / month	Yes (10 req/min, 200/day)

Issue a Pro API key at https://agent-ready.dev/dashboard/api-keys.

Authentication

All three skills expect the API key as the environment variable AGENT_READY_API_KEY (begins with ar_live_…).

For agent-ready-mcp, set it inside the MCP client's server config — not your shell — so the spawned npx process inherits it.
For agent-ready-api, set it in your shell, your .env, or wherever the agent picks up environment variables before running curl / fetch.
For agent-ready-cli, set it in your shell or .env; the CLI reads it automatically (prefer this over the --api-key flag, which leaks through shell history).

The ask tool/command (NLWeb-style search over Agent Ready's docs) is public and works without a key.

Reference

Browse on skills.sh: https://www.skills.sh/mlava/agent-ready-skills
Agent Ready homepage: https://agent-ready.dev
API quickstart: https://agent-ready.dev/quickstart
API docs: https://agent-ready.dev/docs/api
OpenAPI 3.1 spec: https://agent-ready.dev/api/v1/openapi.json
MCP server card: https://agent-ready.dev/.well-known/mcp/server-card.json
MCP server source: https://github.com/mlava/agent-ready-mcp
MCP npm: https://www.npmjs.com/package/agent-ready-mcp
CLI source: https://github.com/mlava/agent-ready-cli
CLI npm: https://www.npmjs.com/package/agent-ready-scanner
Auth walkthrough: https://agent-ready.dev/auth
Methodology: https://agent-ready.dev/methodology

License

MIT

Frequently Asked Questions

What is agent-ready-skills?

agent-ready-skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by mlava. Installable skills for using Agent Ready (https://agent-ready.dev) — the agent-readability scanner. Two skills: agent-ready-api (REST) and agent-ready-mcp (MCP server). It has 0 GitHub stars.

Is agent-ready-skills safe to use?

Yes. agent-ready-skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install agent-ready-skills?

Clone the repository with "git clone https://github.com/mlava/agent-ready-skills" and add it to your Claude Code skills directory (see the Installation section above).

Are there alternatives to agent-ready-skills?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agent-ready-skills against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

20,863

Shell

AI Agentsaibrainstorming

View details

Compare

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

229,808

35,174

JavaScript

AI Agentsai-agentsanthropic

The agent that grows with you

214,982

40,020

Python

AI Agentsaiai-agent

View details

Compare

everything-claude-code

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,940

28,768

JavaScript

AI Agentsai-agentsanthropic

View details

Compare

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,031

19,897

Shell

AI Agents

View details

Compare

cc-switch

by farion1231

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

117,311

7,853

Rust

AI Agentsai-toolsclaude-code

View details

Compare

Browse all AI Agents skills

Developers Also Liked

Based on votes and bookmarks from developers who liked this skill

scholar-sidekick-skills

by mlava

Installable Agent Skills for Scholar Sidekick — turn DOI/PMID/ISBN/arXiv/ISSN/ADS/WHO IRIS into citations (10,000+ CSL styles), exports (BibTeX/RIS/EndNote/CSV), and retraction / open-access / fabrication checks. Zero-install REST skill + MCP skill.

AI Agentsagent-skillsbibliography

View details

agent-causal-decision-tool agenton

agent-ready-skills

Install one of the skills below and your AI agent can run scans, fetch results, and search the Agent Ready docs without any further setup.

Or add all three at once with the whole-repo form:

npx skills add mlava/agent-ready-skills

Browse the rendered docs on skills.sh: https://www.skills.sh/mlava/agent-ready-skills

Skills

`agent-ready-api`

Use the REST API directly. Best when:

You don't have an MCP host (you're driving a curl / Node / Python script)
You want the leanest possible dependency surface
You need a one-shot scan from a CI step, a serverless function, or a notebook

Install:

npx skills add mlava/agent-ready-skills/skills/agent-ready-api

`agent-ready-mcp`

Use the MCP server (agent-ready-mcp on npm) inside Claude Desktop, Claude Code, Cursor, Cline, Continue, Goose, or any other MCP host. Best when:

You already have one of those clients running
You want tool-native invocation — no curl, no fetch wiring
You want the workflow prompts (scan, interpret_scan, remediation_plan)

Install:

npx skills add mlava/agent-ready-skills/skills/agent-ready-mcp

`agent-ready-cli`

Use the agent-ready command-line client (agent-ready-scanner on npm). Best when:

The agent can run shell commands and you want one command, zero wiring
You don't want to install an MCP server or write fetch/polling code
You're scripting — machine-readable --json to stdout, distinct exit codes

Install:

npx skills add mlava/agent-ready-skills/skills/agent-ready-cli

What is Agent Ready?

Agent Ready runs ~60 checks across four spec families:

Vercel Agent Readability Spec — 15 site-wide + 23 per-page checks (llms.txt, robots.txt, sitemap.xml, sitemap.md, AGENTS.md, JSON-LD, headings, markdown mirrors, content negotiation, code-block language tags, JS-rendering)
llmstxt.org — 10 checks against the llms.txt file format
Agent protocols — MCP server cards (SEP-1649), A2A agent cards, agents.json, agent-permissions.json, UCP, x402, NLWeb
Authentication discovery — RFC 9728 PRM + RFC 8414 AS metadata, WorkOS auth.md

Pricing:

Plan	Price	Pages/scan	Scans	API access
Free	$0 / month	25	10 / 30 days	No
Pro	$19 / month	250	50 / month	Yes (10 req/min, 200/day)

Issue a Pro API key at https://agent-ready.dev/dashboard/api-keys.

Authentication

All three skills expect the API key as the environment variable AGENT_READY_API_KEY (begins with ar_live_…).

For agent-ready-mcp, set it inside the MCP client's server config — not your shell — so the spawned npx process inherits it.
For agent-ready-api, set it in your shell, your .env, or wherever the agent picks up environment variables before running curl / fetch.
For agent-ready-cli, set it in your shell or .env; the CLI reads it automatically (prefer this over the --api-key flag, which leaks through shell history).

The ask tool/command (NLWeb-style search over Agent Ready's docs) is public and works without a key.

Reference

Browse on skills.sh: https://www.skills.sh/mlava/agent-ready-skills
Agent Ready homepage: https://agent-ready.dev
API quickstart: https://agent-ready.dev/quickstart
API docs: https://agent-ready.dev/docs/api
OpenAPI 3.1 spec: https://agent-ready.dev/api/v1/openapi.json
MCP server card: https://agent-ready.dev/.well-known/mcp/server-card.json
MCP server source: https://github.com/mlava/agent-ready-mcp
MCP npm: https://www.npmjs.com/package/agent-ready-mcp
CLI source: https://github.com/mlava/agent-ready-cli
CLI npm: https://www.npmjs.com/package/agent-ready-scanner
Auth walkthrough: https://agent-ready.dev/auth
Methodology: https://agent-ready.dev/methodology

License

MIT