AGENTS.md and llms.txt Writer-Reviewer — Make Your Repo and Site Agent-Ready
Write and review the docs AI agents actually read — AGENTS.md for your repo and llms.txt for your site. Drafts them from scratch or audits existing ones for completeness, clarity, and wasted context, with a PASS or REVISE verdict.
- Draft a token-efficient AGENTS.md for any new or existing code repository.
- Audit documentation for "context waste" to save LLM tokens and costs.
- Create an llms.txt file to make your website easily indexable by AI agents.
$12
· or 60 creditsSecure checkout via Stripe
Included in download
- Draft a token-efficient AGENTS.md for any new or existing code repository.
- Audit documentation for "context waste" to save LLM tokens and costs.
- file_read, file_write automation included
- Ready for Cursor
Sample input
Review the AGENTS.md in this repo and tell me if it's ready for a coding agent. Then draft an llms.txt for our docs site at example.com. Give me a PASS or REVISE verdict with a prioritized fix list, and flag anything that wastes context.
Sample output
AGENTS.md — Verdict: REVISE
Priority fixes:
- Build/test commands missing. Add the exact commands an agent should run, e.g.
npm install,npm run build,npm test. - No code map. Add a short "where things live" section (e.g. app logic in src/, API routes in src/api/).
- Gotcha undocumented. Note that migrations must run before the test suite.
Context efficiency: removed ~180 tokens of filler ("This project is a wonderful...", "please be careful"). Keep instructions imperative.
llms.txt — drafted (ready to commit):
Example Docs
Documentation for the Example API and SDK.
Docs
- Quickstart: Install and first request
- API Reference: Endpoints and parameters
Optional
Verdict: PASS once the two AGENTS.md commands above are confirmed against your project.
AGENTS.md and llms.txt Writer-Reviewer — Make Your Repo and Site Agent-Ready
Write and review the docs AI agents actually read — AGENTS.md for your repo and llms.txt for your site. Drafts them from scratch or audits existing ones for completeness, clarity, and wasted context, with a PASS or REVISE verdict.
$12
· or 60 creditsSecure checkout via Stripe
Included in download
- Draft a token-efficient AGENTS.md for any new or existing code repository.
- Audit documentation for "context waste" to save LLM tokens and costs.
- file_read, file_write automation included
- Ready for Cursor
- Instant install
Sample input
Review the AGENTS.md in this repo and tell me if it's ready for a coding agent. Then draft an llms.txt for our docs site at example.com. Give me a PASS or REVISE verdict with a prioritized fix list, and flag anything that wastes context.
Sample output
AGENTS.md — Verdict: REVISE
Priority fixes:
- Build/test commands missing. Add the exact commands an agent should run, e.g.
npm install,npm run build,npm test. - No code map. Add a short "where things live" section (e.g. app logic in src/, API routes in src/api/).
- Gotcha undocumented. Note that migrations must run before the test suite.
Context efficiency: removed ~180 tokens of filler ("This project is a wonderful...", "please be careful"). Keep instructions imperative.
llms.txt — drafted (ready to commit):
Example Docs
Documentation for the Example API and SDK.
Docs
- Quickstart: Install and first request
- API Reference: Endpoints and parameters
Optional
Verdict: PASS once the two AGENTS.md commands above are confirmed against your project.
About This Skill
AI agents are now a primary reader of your documentation: a coding agent opens AGENTS.md before it touches your repo, and a browsing agent reads llms.txt before it uses your site. Both are young conventions, and most are missing, vague, or padded with words that waste the very context window they are meant to fill. This skill writes them properly and reviews existing ones against what an agent actually needs. For AGENTS.md it covers runnable build, test, and run commands, code conventions, a map of where logic lives, and the gotchas that trip agents up. For llms.txt it produces the correct structure — H1 name, summary, and curated, linked sections an agent can navigate. It has a write mode that drafts the file ready to commit, and a review mode that returns a PASS or REVISE verdict with a prioritized fix list, including a context-efficiency pass that cuts the filler tokens agentic engineers warn about. Works with Claude Code, Cursor, Codex CLI, Gemini CLI, and any SKILL.md agent.
Use Cases
- Draft a token-efficient AGENTS.md for any new or existing code repository.
- Audit documentation for "context waste" to save LLM tokens and costs.
- Create an llms.txt file to make your website easily indexable by AI agents.
- Improve agent accuracy by defining explicit project "laws" and gotchas.
Known Limitations
Generates and reviews documentation only — it does not run your build, execute tests, or verify that the commands it documents actually work, so you should confirm them against your project. Quality depends on the context you provide: for a private repo it can only work from the files and details you share. It is a one-time static download with no automatic or ongoing updates; you re-run the skill yourself whenever your project changes. It covers AGENTS.md, CLAUDE.md, and llms.txt and does not generate other formats (for example README.md or OpenAPI specs).
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/agents-md-and-llms-txt-writer-reviewer-make-your-repo-and-site-agent-ready -o /tmp/agents-md-and-llms-txt-writer-reviewer-make-your-repo-and-site-agent-ready.zip && unzip -o /tmp/agents-md-and-llms-txt-writer-reviewer-make-your-repo-and-site-agent-ready.zip -d ~/.claude/skills && rm /tmp/agents-md-and-llms-txt-writer-reviewer-make-your-repo-and-site-agent-ready.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
File Scopes
This skill only reads the documentation files you point it at (AGENTS.md, CLAUDE.md, llms.txt, and related Markdown) and writes the drafted or revised file back. It uses no terminal, browser, network access, or environment variables, and connects to no external hosts.
Tags
Works with any SKILL.md-compatible agent (Claude Code / Cursor / Codex CLI / Gemini CLI). No runtime or build step is required and it needs no network access — it operates only on the documentation files you point it at.
Creator
PubsProToolkit builds adversarial "gate" skills for AI agents — they catch problems before your output ships, instead of just generating more. From code, security, and infrastructure to content, hiring, contracts, and finance. Built by a CMPP-certified, PhD medical writer who brings regulated-industry rigor to every domain.
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
inline-comment
Best way to steer your agents, effortlessly.
skill-router-2
Automatically detect, load, and stack the perfect skills combo for any user request.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
ai-automation-qa-pack
Professional QA & UAT documentation generator for AI automation agencies and complex agent deployments.