How-To Guides

repo-readme-generator: README and Docs Skill for Codex

Install repo-readme-generator for Codex to create or update README.md and documentation suites, including AGENTS.md, from verified repository evidence.

  • Builds README and optional docs suite with AGENTS.md
  • Evidence-only writing with explicit TBD for unknowns
  • Includes quick prompts for README-only or full docs generation
By Rejith Krishnan3 min read
repo-readme-generator: README and Docs Skill for Codex

What it is

repo-readme-generator creates or updates project documentation from files it has actually read. If a fact cannot be verified, it is marked TBD instead of guessed, which helps teams avoid polished but inaccurate documentation.

What it does

  • Creates or updates project documentation from files the skill has actually read.
  • Two scopes: a single architecture-focused README.md, or a full suite with AGENTS.md and a docs/ folder.
  • Four modes: create, create as a starter skeleton, incremental update, and audit-only health check.
  • Asks which scope you want when the request does not say, and confirms the branch before changing any file.
  • Marks anything it cannot verify as TBD, and documented-but-unbuilt items as Planned.
  • Labels design rationale inferred from code as Source: inferred from code, never as the authors' intent.
  • Runs discover.py to collect manifests, scripts, compose services, env vars, entry points, routes, data models, CI and tests from real files.
  • README follows a 17-section template with a clickable table of contents and fenced commands.
  • Suite documents cover architecture, stack, data, API, configuration, development, testing, deployment, security and troubleshooting.
  • Renders diagrams as Mermaid or SVG, drawing an edge only where it saw an import, call or connection.
  • Validates output with validate_readme.py and validate_docs.py, checking anchors, links, paths, commands, secrets and AGENTS.md size.
  • Re-opens the source for every version, port, variable and command it stated, and downgrades anything unconfirmed.
  • Never edits application code, dependencies or infrastructure, and never writes real secret values.
  • Adds a note that commit messages and PR descriptions must be descriptive, not one line.
  • In update mode, keeps accurate existing text and preserves existing AGENTS.md rules.
  • Ends with a report of files changed, commands run versus only read from files, and open TBD items.

Install and usage

Codex CLI prerequisite: PowerShell setup or WSL setup.

Install, then restart Codex:

$skill-installer install https://github.com/lowtouch-ai/krithi-skills/tree/main/skills/repo-readme-generator

Usage examples from the repository README:

$repo-readme-generator create the README for this repo
$repo-readme-generator document this repo fully

For update and uninstall steps, see the krithi-skills README.

Install all the skills together

If you want the whole set instead of one skill, point the installer at the repository root:

$skill-installer install all the skills in the https://github.com/lowtouch-ai/krithi-skills/

This asks Codex to install every skill in the krithi-skills repository in one step, so you do not repeat the install for each one. Restart Codex afterwards so the new skills are picked up.

The set currently covers five skills:

  • migration-estimate: turns a codebase into PRDs, stories and a sprint estimate with human-team and Krithi timelines.
  • plan-builder: turns a ticket into a Plan Mode prompt that changes no code.
  • repo-readme-generator: creates or updates a README and documentation suite from verified repository evidence.
  • appsec-static-audit: runs a source-code-only security audit with compliance mapping.
  • wave-a11y-scan: runs a WAVE-style accessibility scan mapped to WCAG 2.x.

Prefer to install one at a time? Use the single-skill command in the install section above.

About the Author

Rejith Krishnan

Rejith Krishnan

Founder and CEO

Rejith Krishnan is the Founder and CEO of lowtouch.ai, a platform dedicated to empowering enterprises with private, no-code AI agents. With expertise in Site Reliability Engineering (SRE), Kubernetes, and AI systems architecture, he is passionate about simplifying the adoption of AI-driven automation to transform business operations.

Rejith specializes in deploying Large Language Models (LLMs) and building intelligent agents that automate workflows, enhance customer experiences, and optimize IT processes, all while ensuring data privacy and security. His mission is to help businesses unlock the full potential of enterprise AI with seamless, scalable, and secure solutions that fit their unique needs.

LinkedIn →