write-root-readme
Write or rewrite the repo-root README.md.
Works with
--- name: write-root-readme description: Write or rewrite the repo-root README.md. license: MIT --- # Write Root README ## Guidelines - files to update: - `README.md` in the repo root - Read [example-readme.md](./references/example-readme.md) for a reference structure and style. - Badges are encouraged. See example README for useful badges. - Prefer badges in example README when applicable. - Prefer badges with live data over static badges. - Emojis are encouraged in headers. - Hero section is encouraged. Follow the format in example README strictly. - Use GitHub Socialify to generate a project image. The generated image already includes logo, title, description, badges for stars, forks, issues, pulls. - Include link to docs if exists. - Badges in hero section are encouraged. Limit hero section to 8 badges. - Limit hero section to 4 links. - Include a rule after hero section. - License section is encouraged. Follow the format in example README strictly. - DO NOT use relative links in README. - Favor bold, comprehensive rewrites over minor or incremental edits. - Keep README concise. ## Validation - Run `rumdl fmt .`. Treat its findings as weak hints, not strong constraints. - Spot-check commands, links, and tool names against the actual repo files before finishing.
More Writing & Documentation skills
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
repo-intake-and-plan
lllllllama/rigorpilot-skills
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
