readme-generator

Solid

Generate or refactor project README.md files using repository evidence. Use when the user asks to create/rewrite/standardize README, improve documentation structure, or produce maintainable README templates for different project types (service/library/CLI/monorepo).

AI & Automation 30 stars 5 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
50
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# README Generator Generate high-quality README documents from codebase evidence, with clear structure, runnable commands, and maintenance rules. ## Core Rules - Base every statement on repository evidence (files, code, scripts, workflows, configs). - Keep internal workflow reporting out of the README body. Evidence maps, scorecards, and verification state belong in the assistant response — see §Command Verifiability Gate. - Exclude local/private tooling folders by default (for example `.codex/`) unless asked. - Keep naming and paths consistent with the real repository layout. - Treat top-level `README.md` as a user-facing homepage first, a maintainer reference second. ### Evidence Precedence (resolves "omit or mark?") One rule, applied by section class — there is no third case: | Section class | Evidence present | Evidence missing | |---|---|---| | **Required** for the project type (§Structure Policy) | Write it | Keep the heading, write `Not found in repo` | | **Optional** (§Optional Sections) | Write it | Omit entirely and list it in `sections_omitted` | ### Facts vs Results (resolves "is this command fabricated?") A manifest proves a **toolchain**; only an artifact proves a **result**. - Evidence-backed: `go test ./...` when `go.mod` exists, `pytest` when `pyproject.toml` exists, `make <target>` when that exact target is in the Makefile. - Not evidence-backed: coverage percentages, test counts, benchmark numbers, throughput, latency, or a response body — un...

Details

Author
johnqtcg
Repository
johnqtcg/awesome-skills
Created
6 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category