technical-writing
>-
Works with
--- name: technical-writing description: >- license: Apache-2.0 --- # Technical writing Use only authoritative context already present or explicitly supplied. Leave research, investigation, debugging, and fact-checking to the main agent. Produce a supportable partial result and identify material gaps instead of inventing facts, causes, requirements, risks, examples, or conclusions. Apply these invariants in order: 1. Preserve supported technical meaning and requirement strength. 2. Preserve terminology, certainty, conditions, exceptions, causality, commands, identifiers, paths, values, and units. 3. Follow explicit user instructions, then project guidance, nearby conventions, existing structure, and minimal generic organization. 4. Improve precision, concision, ambiguity, and information density. Apply grammar, punctuation, certain clarity improvements, terminology consistency, and removal of semantic duplication inline. Return additions, removal of distinct information, examples, analogies, major restructuring, changed emphasis, and ambiguous claims as author-judgment suggestions. Remove unnecessary throat-clearing, generic introductions or conclusions, unsupported significance claims, repetitive generic transitions, synonym cycling, immediate paraphrastic repetition, and empty generic sections. Retain useful repetition and predictable structure. Optimize for clear technical prose, not detector evasion or artificial humanization. For documentation, use `technical-docs`. For reader-oriented technical articles, use `tech-blog`.
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.
