technical-writing
|
Works with
--- name: technical-writing description: | license: MIT --- # Technical Writing Owns meaning-preserving editing, translation, terminology, rhythm, and QA. ## 1. Workflow 1. Identify surface: English, Japanese, translation, skill text, or QA. 2. Preserve meaning. Do not rewrite commands, identifiers, product names, paths, code, links, versions, or APIs for style. 3. Keep glossary/terminology polish here when meanings are stable; use `clarify-concepts` first when they are not. 4. For generic/AI-like prose, read [Prose Review](references/prose-review.md). 5. For English checks, read [Vale And Harper](references/vale-and-harper.md). 6. For English-to-Japanese, clean English first, then read [English-to-Japanese Workflow](references/english-to-japanese-workflow.md) and [Japanese Writing Style](references/japanese-writing-style.md). 7. For Japanese editorial review, read [Japanese Writing Style](references/japanese-writing-style.md). 8. For flat explanatory prose, read [Cognitive Rhythm](references/cognitive-rhythm.md). Build rhythm from source material. 9. Apply only clarity changes; preserve facts and intent. ## 2. Boundaries Issue 225/226 boundaries: no automation, model/cost/privacy, external-sharing approval, derivative publication approval, or chunking. Do not add direct polished-Japanese drafting from scratch. Repair English first, then translate or QA Japanese. ## 3. References - [Vale And Harper](references/vale-and-harper.md) - [English-to-Japanese Workflow](references/english-to-japanese-workflow.md) - [Japanese Writing Style](references/japanese-writing-style.md) - [Prose Review](references/prose-review.md) - [Cognitive Rhythm](references/cognitive-rhythm.md)
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.

