agentleFS
GstMirabalGstMirabal/Token-Optimized-Agent-Pipeline/skills/readme-standardizer/SKILL.md

readme-standardizer

Skill1 starsChanged 10 days agoMITView on GitHub

Use this Skill ALWAYS whenever you are asked to create, generate, standardize, or update a project's README.md. Never generate a README from scratch with an improvised structure.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the Director (user) asks to "create the readme", "update the readme", or "apply the template to the project":

    line 9
  2. Distinctive:

    Before blindly generating text, analyze the context of the current repository:

    line 16
  3. Distinctive:

    If the README.md does not exist in the local project root, create it using the processed content.

    line 30
  4. Distinctive:

    If the README.md already exists, OVERWRITE its content completely by applying the new template first and moving any useful old information …

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

📝 Skill: README Gold Standardizer

⚠️ When to Trigger this Skill?

If the Director (user) asks to "create the readme", "update the readme", or "apply the template to the project":

  1. You are PROHIBITED from inventing the Markdown structure.
  2. You MUST mandatory execute this process using the master architectural template hosted in this Submodule.

🛠️ How it Works (Instructions)

Step 1: Project Understanding (Brain Drain) Before blindly generating text, analyze the context of the current repository:

  • What languages does it use? (To fill in {{TECH_STACK_BADGES}}).
  • What are the execution steps? (Docker, npm, venv) for {{INSTALLATION_xx}}.
  • What is the project name and its actual GitHub URL? Infer it from the local git remote -v output, package.json/pyproject.toml repository fields, or equivalent project metadata. If it cannot be inferred with confidence, ASK the Director — never assume a default owner or organization.

Step 2: Read Master Template Open and read the static template file using your base tool: [submodule-root-directory]/.agents/skills/readme-standardizer/assets/template.md

Step 3: Fusion and Overwriting (Render) Mentally replace all {{UPPERCASE_VARIABLES}} delimiters in the template with the actual project information you extracted in Step 1. Keep the HTML structure, <p align="center">, shields (Shields.io), navigation anchors (<a name="readme-top"></a>), and the "Contact" section's Markdown/HTML structure intact. Fill the {{OWNER_NAME}}, {{OWNER_EMAIL}}, {{OWNER_LINKEDIN_URL}}, {{OWNER_X_URL}}, and {{OWNER_GITHUB_USERNAME}} placeholders in that section with the REAL owner data of the project you are currently standardizing — never assume they refer to the author of this Skill. If the owner's data cannot be inferred with confidence from repository context, ASK the Director for it before rendering.

Step 4: Injection

  • If the README.md does not exist in the local project root, create it using the processed content.
  • If the README.md already exists, OVERWRITE its content completely by applying the new template first and moving any useful old information to the "About the Project" or "Usage" sections.

Note for the Token-Saver: Writing the README with the write_to_file or replace_file_content tool is an approved and mandatory operation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.