technical-writing
Use when writing documentation, READMEs, API docs, changelogs, ADRs, or user guides — ensures clarity, structure, and project consistency
Works with
--- name: technical-writing description: Use when writing documentation, READMEs, API docs, changelogs, ADRs, or user guides — ensures clarity, structure, and project consistency license: MIT --- # Technical Writing ## When to Use When creating or updating any documentation: README, API docs, architecture decision records, changelogs, user guides, onboarding docs. ## Process 1. **Read context** — scan existing docs, code, and conventions 2. **Identify audience** — developers, end users, or ops? 3. **Choose format** — README, ADR, API reference, tutorial, changelog 4. **Write draft** — structure first, content second 5. **Verify examples** — all code snippets must be runnable ## Documentation Formats ### README - Project name + one-line description - Install / quickstart (copy-pasteable) - Usage examples - Configuration reference - Contributing link ### API Reference - Endpoint, method, path - Request: headers, params, body (with types) - Response: status codes, body schema, examples - Error codes and meanings ### ADR (Architecture Decision Record) - **Status**: Proposed / Accepted / Deprecated - **Context**: What problem are we solving? - **Decision**: What did we choose? - **Consequences**: Trade-offs, risks, follow-ups ### Changelog (Keep a Changelog) - `Added` / `Changed` / `Deprecated` / `Removed` / `Fixed` / `Security` - Most recent version first - Link to diff between versions ## Rules - Match existing project tone and terminology - Prefer examples over explanations - Keep sentences under 25 words - Use active voice - One idea per paragraph - Use tables for structured data, lists for sequences
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.
