MoonshotAI
精选
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.
AI 仓库情报摘要
FR-AI / ANALYSIS为什么值得关注
它提供结构化的一页纸洞察而非冗长的市场报告，可作为智能体技能安装，并支持自定义语言、深度和分析焦点。
适合谁使用
- SaaS产品经理
- 竞品分析专家
- AI初创公司创始人
- 市场营销团队
典型使用场景
- 快速分析竞品落地页和定价页
- 识别功能或定位中的空白与机会
- 建立文案钩子库以优化消息传递
- 以结构化方式对最多五家竞品进行对标分析
项目优势
- 聚焦于可执行的“抄袭/规避/空白”建议，而非冗长报告
- 支持双语输出（英文和简体中文）
- 可自定义深度（快速、标准、深度）和分析焦点（定位、定价、功能、文案）
- 伦理范围：仅依赖公开信息，不涉及黑客或传言
使用前须知
- 需要明确命名的竞品，不支持模糊的市场分析
- 仅适用于SaaS、AI工具、开发者工具和订阅制应用
- 输出质量依赖于公开数据的可用性，无法获取内部指标
README 快速开始
Competitor Teardown
SaaS/AI competitor teardown: positioning, pricing, feature matrix, landing-page hooks, and actionable "steal / avoid / gap" recommendations.
中文简介： SaaS/AI 竞品拆解（定位、定价、功能矩阵、落地页钩子、可执行建议）。 — 详见 README.zh.md.
What this skill does
- You are a SaaS/AI competitor analyst. Ship actionable insights, not bloated market reports
- Scope: SaaS, AI tools, devtools, subscription apps
- Deliverable: One-pager positioning + matrix + hook library + recommendations
- Triggers: competitor analysis, competitive teardown, pricing comparison, feature matrix.
Install
After this package is on GitHub:
npx skills add / --skill competitor-teardown
Local monorepo: point your agent at skills/competitor-teardown/ (this folder).
Options
| Option | Values | Default |
|---|---|---|
lang | en · zh · bilingual | en |
depth | quick (1–2 rivals) · standard (≤5) · deep (+ copy teardown) | standard |
focus | positioning · pricing · features · copy · all | all |
Runtime output language follows lang (default en). Skill docs stay EN-primary.
When to use
| Use | Don't |
|---|---|
| (see bullets) | (see bullets) |
Use
- 1–5 named competitors for decisions
- Public landing/pricing/feature teardown
- Steal structure / avoid patterns
Don't
- Vague “market analysis” with no product names
- Hacking, rumors, leaking non-public data
- Screenshot descriptions with no conclusions
Deliverable
One-pager positioning + matrix + hook library + recommendations
Full workflow, hard rules, and QA: see SKILL.md.
Example
Monorepo sample (if present): ../../output/samples/competitor-teardown-example-01.md
License
MIT — see LICENSE.
相关仓库与替代方案
根据分类、Topic 和编程语言匹配的相似项目。
lopopolo
精选
harness-engineering
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.
slvDev
精选
esp32-ai
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.