automate-project-maintenance
Orchestrate repository maintenance. Use when Codex needs one entry point to refresh tests, docs, README, and GitHub metadata.
Works with
--- name: automate-project-maintenance description: Orchestrate repository maintenance. Use when Codex needs one entry point to refresh tests, docs, README, and GitHub metadata. license: MIT --- # Automate Project Maintenance Use this skill after the focused maintenance skills are available. Detect the repo type from local facts, not from naming guesses. ## Detection Inspect the repo before acting. - Python signals: - `pyproject.toml` - TypeScript signals: - `package.json` ## Workflow 1. Determine whether the repo is Python, TypeScript, or other. 2. Run only the applicable focused skills. 3. Keep remote GitHub updates preview-first. ## Python Branch 1. Use `$write-python-tests`. 2. Use `$rewrite-python-docs`. 3. Use `$write-root-readme`. 4. Run `rumdl fmt .` and treat findings as weak hints. 5. Run `mise run lint`. 6. Run `mise run docs:build`. 7. Run `nox`. 8. Use `$sync-github-repo-metadata` in preview mode. ## TypeScript Branch 1. Use `$write-root-readme`. 2. Run `rumdl fmt .` and treat findings as weak hints. 3. If TypeScript or JavaScript files were edited, run `biome check --write`. 4. Use `$sync-github-repo-metadata` in preview mode. ## Other Repos - Apply the appropriate maintenance steps based on the detected technology stack. - Do not assume both branches must edit files in the same run.
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.
