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.
它强调证据而非炒作,提供可配置的语言、风格和长度选项,并包含风险提示和替代钩子——将线程质量提升到通用 AI 输出之上。
Evidence-driven X/Twitter threads for developer tools: 5–8 posts, hook variants, proof beats, single CTA. For indie hackers and product builders.
中文简介: 开发者工具向 X/Twitter 线程(5–8 帖,证据驱动)。 — 详见 README.zh.md.
After this package is on GitHub:
npx skills add / --skill thread-devtools
Local monorepo: point your agent at skills/thread-devtools/ (this folder).
| Option | Values | Default |
|---|---|---|
lang | en · zh · bilingual | en |
length | 5 · 6 · 7 · 8 | 7 |
style | launch · tutorial · teardown · hot-take · changelog | tutorial |
platform | x · threads | x |
proof | strict · normal | strict |
Runtime output language follows lang (default en). Skill docs stay EN-primary.
| Use | Don't |
|---|---|
| (see bullets) | (see bullets) |
Use
Don't
Full thread + 2–3 hook alts + risk notes
Full workflow, hard rules, and QA: see SKILL.md.
Monorepo sample (if present): ../../output/samples/thread-devtools-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.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.