agentsclimarketplace

Txtskills

Skill hk-vk/txtskills

Turn any llms.txt into skills installable with a single command for AI agents : works with Claude Code, Cursor, Windsurf, GitHub Copilot, Amp, Antigravity, and many more.

Install
npx -y skills add hk-vk/txtskills

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Convert docs base URLs, llms.txt, or llms-full.txt into installable Agent Skills with txtskills CLI. Use when a user asks to generate, publish, and optionally install a new skill from documentation.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.0 KB, 697 tokens by cl100k_base, as published. Nobody here has run it

txtskills: llms.txt → Agent Skills

Use this skill when you need to turn documentation into a reusable Agent Skill quickly.

What this skill does

  • Converts a docs URL into a published skill via txtskills convert
  • Supports base URLs and explicit files:
    • example.com
    • example.com/llms.txt
    • example.com/llms-full.txt
    • example.com/.well-known/llms.txt
    • example.com/.well-known/llms-full.txt
  • Can install immediately after conversion (interactive or auto)

Quick start

npx txtskills@latest convert github.com/llms.txt

npx txtskills@latest convert docs.anthropic.com

Recommended workflow

  1. Convert from a docs URL.
  2. Review generated skill name and GitHub URL.
  3. Install immediately when prompted.
  4. If content changed and skill exists, re-run with --force.

Agent execution workflow (important)

When the user gives only a product name (for example: "Google AI Studio"), do this:

  1. Discover candidate URLs by checking in this order:
    • <domain>/llms.txt
    • <domain>/.well-known/llms.txt
    • <domain>/llms-full.txt
    • <domain>/.well-known/llms-full.txt
  2. If domain is unknown, search web for "<product> llms.txt" and "<product> llms-full.txt".
  3. Run conversion:
    • npx txtskills@latest convert <best-url>
  4. If convert succeeds, offer immediate install.
  5. If multiple valid sources exist, ask user to choose before publishing.

Example user intent this skill should handle:

  • "Find Google AI Studio llms.txt and convert it to a txtskills skill"

Command reference

npx txtskills@latest convert <url>

Options:

  • -n, --name <skill-name>: set custom skill slug
  • -f, --force: regenerate when skill already exists
  • --install: auto-install after conversion
  • --skip-install: skip install prompt
  • -g, --global: install globally (when auto-installing)
  • -a, --agent <agents...>: target specific agents
  • -y, --yes: auto-confirm prompts
  • --json: machine-readable output
  • --api <url>: custom convert API base or full endpoint

Naming guidelines

Use lowercase, hyphenated names (Agent Skills standard):

  • ✅ payment-docs
  • ✅ ai-sdk
  • ❌ PaymentDocs
  • ❌ docs_skill

Troubleshooting

  • If conversion fails, verify the docs site exposes llms.txt or llms-full.txt.
  • If skill exists but docs changed, run with --force.
  • If install is skipped, run:
npx txtskills@latest add <skill-name>

Useful links

What ships with it: 129 files

2748.4 KB alongside SKILL.md, 37 of them executable

apps/

89 more files not listed here. See all 129 in the repository.

Keep looking

Skills are one crate of 327,167. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.