asd-ste100-skill
A Claude Code skill that rewrites dense or ambiguous English for AI agents using ASD-STE100 principles. Use it to make tool descriptions, errors, and agent instructions easier to parse.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: MIT
Overview
This repository provides a Claude Code skill that rewrites dense or ambiguous English for AI agents using principles from ASD-STE100 Simplified Technical English. Use it on tool descriptions, error messages, instructions between agents, and explanatory text. It offers strict and STE-flavored modes, identifies sentence-level issues, and rewrites flagged text while aiming to retain facts, conditions, and scope. Structural checks are mechanical, but dictionary and style judgments can be advisory. The linter does not verify that a rewrite preserves meaning.
Key features
- Offers strict and STE-flavored rewriting modes.
- Flags sentence-level issues such as passive voice, long sentences, and ambiguous wording.
- Rewrites flagged sentences while aiming to retain facts, conditions, and scope.
- Can show a before-and-after table that names the rules broken.
Best for
Useful when preparing tool descriptions, errors, or instructions that one AI agent will pass to another. Do not treat a clean lint result as proof that a rewrite preserves the original meaning.
- Upstream
- danyuchn/asd-ste100-skill
- Fork on GitHub
- Guo-astro/asd-ste100-skill
- Upstream stars
- 6.1k
- Category
- AI agents and LLM tools
- Language
- Python
- License
- MIT
- Forked
- 2026-10-05
- Sync status
- In syncLast synced 2026-11-08
More in AI agents and LLM tools
/last30days is an AI-agent skill for researching recent discussions across social platforms, video, news, markets, and the web. It brings scattered signals together in a synthesized brief for trend research and preparation.
Forked 2026-10-22Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
A portable C99 inference engine for running Kimi K3 on a CPU without a GPU or machine-learning framework. It streams the large checkpoint from disk to support inference with limited RAM, for batch text generation or text chat.
Forked 2026-10-21Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub
LayerFS gives AI agents writable workspaces over shared history, so they can work in parallel without copying the base. Use it to checkpoint, branch, rewind, and merge agent changes.
Forked 2026-10-21Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
Magnitude runs open models locally and tunes kernels for your hardware. Use it to connect local models to supported agents or an OpenAI-compatible client.
Forked 2026-10-19Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub