Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
它将提示词质量变成可回归测试的流程,利用版本化金标输入、机器可检查约束和漂移表,让提示词编辑在发布前被安全地纳入检查。
Golden inputs, expected constraints, drift table, and CI pseudo-code — catch prompt regressions before ship.
中文简介: 提示词回归包(金标输入、期望约束、漂移检测表、CI 伪代码)。 — 详见 README.zh.md.
npx skills add / --skill prompt-regression-pack
Local monorepo: skills/prompt-regression-pack/.
| Option | Values | Default |
|---|---|---|
lang | en · zh · bilingual | en |
size | 12 · 25 · 50 | 25 |
check | constraints · exact · hybrid | constraints |
ci | none · pseudo · github-actions | pseudo |
depth | lite · standard · strict | standard |
| Use | Don't |
|---|---|
| Gate every system/template prompt edit | One-off creative chat |
CI on prompts/** changes | Full agent capability suite only |
| Track format/policy drift | Jailbreak exploit libraries |
Gold case set + constraint catalog + drift table + CI notes.
See SKILL.md.
../../output/samples/prompt-regression-pack-example-01.md
MIT — see LICENSE.
根据分类、Topic 和编程语言匹配的相似项目。
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.

A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.