zh-ste100-jev-skill
Chinese controlled-writing agent skill for technical reports with nine rules, using static checks plus a Jev semantic gate for certainty.
Overview
zh-ste100-jev-skill is an agent skill for controlled Chinese technical and reporting prose, documented in Chinese. It adapts ideas from ASD-STE100 Simplified Technical English and China's civil aviation simplified language rules, plus Chinese stylistic guidance, into nine rules across three layers: discourse (state firm conclusions, no hedging or disclaimers), sentence (short bamboo-joint sentences, at most two 的 per sentence, no Westernized prepositional shells) and word choice (strong verbs, no buzzwords, specific names and numbers, one term per concept).
Most rules are enforced by static checks. The discourse-level certainty rules add a Jev semantic gate that reviews text in about a hundred milliseconds to catch hedging and empty overclaims that static rules miss. It targets AI-generated Chinese reports that are hard to read and full of hedging.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does this text hedge instead of stating a firm conclusion?(inferred) | yes · no |
| Yes / no | Does this text contain empty overclaims or disclaimer tails?(inferred) | yes · no |
How it works
- The agent drafts a Chinese report or technical text.
- Static checks enforce sentence and word rules.
- A Jev semantic gate checks the certainty rules.
- The agent revises flagged passages.
Strengths
- Combines cheap static checks with a fast semantic gate.
- Targets common problems in AI-written Chinese reports.
Caveats
- Chinese only.
- Jev gate needs a key; exact questions are not detailed in the excerpt.
At a glance
- Type
- Agent skill
- Status
- beta
- Runtime
- agent skill
- Has code
- yes
Use cases and integrations
How curated lists describe it
中文受控技术与汇报写作技能（ASD-STE100 软硬双引擎 + Jev System-One 语义门禁：民机简化中文 + 汉语言文学竹节句）.
wh000wh000/awesome-jev-live
Frequently asked questions
What does Jev check?
The top-level certainty rules: hedging and empty overclaims.
What are the nine rules based on?
ASD-STE100, Chinese civil aviation simplified language and Chinese style guidance.
Who is it for?
Agents and people writing Chinese technical reports.
Related projects
CLI and agent commands auditing a git diff against YAML standards packs, scoring each hunk with Jev so agents fix only flags.
Agent skillbetaTypeScriptAgent skill where Jev flags 35 AI-writing patterns per paragraph and the model edits only the flagged spots.
ProjectbetaPythonRuff-style prose linter whose semantic rules each ask Jev a yes/no question about a paragraph, title or section, with tunable thresholds.
ProjectbetaPythonNode tool that crosschecks a folder of Markdown notes for contradictions and repeats, and ranks notes by any question, using Jev.
ProjectbetaJavaScriptProse linter for AI writing tells: regex handles 18, Jev judges 15 as Nouls in one call, shipped as a Claude Code Stop hook.
HookbetaPythonProse linter with local regex rules and Jev judgment rules per paragraph, as CLI, pre-commit hook, GitHub Action and Claude Code skill.
CLIbetaTypeScript