agentleFS
Sign inStart free
Google CloudKnown publisherGoogleCloudPlatform/cloud-solutions/projects/build-with-gemini-demo/build-with-antigravity/.agents/skills/documentation/SKILL.md

documentation

Skill138 starsChanged 5 months agoApache-2.0View on GitHub

Generates and updates project README documentation based on codebase changes. Use when generating or updating application documentation. Don't use for inline code comments or docstring-only refactoring.

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 94 edited versions we read keep these.

  • 6

    Distinctive

    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:

    Failure handling: If no application source files exist in the target directory, inform the user before creating placeholder documentation.

    line 30
  2. Distinctive:

    Check git status and git diff (if inside a Git repository) to identify newly added features, modified endpoints, or updated configuration …

    line 40
  3. Distinctive:

    Read the existing README.md file in the application directory (if present) to preserve valid custom sections and project context.

    line 42
  4. Distinctive:

    Create a new README.md file in the application directory (or update the existing file) with the following structured sections:

    line 47
  5. Distinctive:

    Verify that all file paths, shell commands, environment variables, and port numbers in README.md match the actual codebase.

    line 64
  6. Distinctive:

    Ensure Markdown formatting uses proper heading hierarchy, language-tagged fenced code blocks, and valid relative links.

    line 66

“Common” is measured: kept by at least 6 in 10 of the 94 edited versions of this file we could read. “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

Update documentation

<!-- Disabling markdownlint MD029 to provide explicit ordering to avoid confusing the LLM. --><!-- markdownlint-disable MD029 --><!-- Disabling markdownlint MD030 to allow the list overflowing to numbers >=10. --><!-- markdownlint-disable MD030 -->

Prerequisites

  • Application source files: Project source code, configuration files, and dependency manifests (requirements.in and requirements.txt) present in the workspace.
  • Development standards: Workspace rules defined in .agents/rules/dev-rules.md.
  • Failure handling: If no application source files exist in the target directory, inform the user before creating placeholder documentation.

Workflow

1. Analyze codebase and recent changes

  1. Inspect the application directory structure, entry points, data models, routes or CLI commands, and dependency manifests (requirements.in and requirements.txt).
  2. Check git status and git diff (if inside a Git repository) to identify newly added features, modified endpoints, or updated configuration options.
  3. Read the existing README.md file in the application directory (if present) to preserve valid custom sections and project context.

2. Draft or update README.md

Create a new README.md file in the application directory (or update the existing file) with the following structured sections:

  1. Project overview: Concise summary of the application's purpose, key features, and technology stack.
  2. Project structure: Overview of the main directories and source files.
  3. Prerequisites and setup: Required Python runtime version, virtual environment setup, dependency compilation and installation, and environment variable configuration following .agents/rules/dev-rules.md.
  4. Running the application: Exact commands to start the application locally and the local URL/port to access it.
  5. API reference and usage: Summary of available HTTP endpoints (method, path, request parameters, and response behavior) or user workflows.
  6. Running tests: Commands to execute the unit test suite.

3. Verify accuracy and formatting

  1. Verify that all file paths, shell commands, environment variables, and port numbers in README.md match the actual codebase.
  2. Ensure Markdown formatting uses proper heading hierarchy, language-tagged fenced code blocks, and valid relative links.
  3. Summarize the documentation updates for the user.

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.

Reviews can't be read right now.

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.

Check your setup, free