Agent skill · Documentation

cet-skill

CET-4 and CET-6 exam preparation coach for original CET-style practice, diagnostic feedback, writing and translation correction, reading/listening drills, and study planning.

mingchen666157★ · +54/wk · 1 repos on radarProfile →
claude-code
Install
npx skills add mingchen666/Reviva --skill cet-skill --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 12
SKILL.md size: 25 KB
Bundled scripts: none
Path: electron/builtin-assets/skills/cet-skill/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 181 · +24 this week
Language: HTML
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Guides CET-4/6 learners through original CET-style practice, diagnostic feedback, writing and translation corrections, reading and listening drills, and study planning. It emphasizes non-reproduction of real CET content and uses copyright-safe patterns.

How it works

The skill presents a CET-focused coaching flow: initiate CET-4 or CET-6 training direction, offer original CET-style tasks rather than real items, and provide structured practice across writing, translation, reading, listening, and study planning. It gates interactions with copyright rules, ensuring no reproduction of real prompts or items. The system prompts user preferences in Chinese at session start and routes conversations into one of five modes (Writing, Translation, Reading, Listening, Study Plan) based on user input. It collects optional user profile data to tailor tasks and uses a default policy of delayed answer reveal for most tasks. Tasks are generated as original CET-style simulations with explicit labeling and structured feedback pathways.

When to use it

Use when a learner wants CET-4 or CET-6 preparation with original-style drills, diagnostic feedback, and a study plan. Triggered by user choice of target level and section, or by explicit request for study planning or practice in any of the five modes. The routing logic prefers the section named first if multiple are requested.

What it can touch

The skill relies on the claude-code tool for task generation and feedback. It specifies that tasks and feedback are produced within the constraints of original CET-style content, with labeling: “以下为原创 CET-style 仿真模拟训练。” and the actionable workflow embedded in mode-specific routines. It does not reproduce real CET content.

Caveats

It enforces copyright restrictions: no real prompts, passages, or answers from CET content; only abstracted patterns and original tasks. It uses Chinese as the default user-facing language unless requested otherwise. The policy includes a progressive answer reveal approach and structured feedback after user submissions in writing and translation modes.

From the SKILL.md

# CET Skill ## Purpose CET Skill helps Chinese learners prepare for CET-4 and CET-6 through original CET-style practice, diagnostic feedback, writing and translation correction, reading/listening drills, and study planning. This skill is built from copyright-safe distilled exam patterns. It must **never** reproduce, reconstruct, paraphrase, translate, complete, or compile real CET exam content. De

More from Reviva
All skills →
About this skill
What does the cet-skill skill do?

CET-4 and CET-6 exam preparation coach for original CET-style practice, diagnostic feedback, writing and translation correction, reading/listening drills, and study planning.

How do I install it?

Run `npx skills add mingchen666/Reviva --skill cet-skill --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From mingchen666/Reviva, a repository with 181 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going