MoonshotAI
Featured
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 repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It delivers structured, one‑pager insights instead of bloated market reports, is installable as an agent skill, and offers customizable language, depth, and focus options.
Who it is for
- SaaS product managers
- competitive intelligence analysts
- AI startup founders
- marketing teams
Use cases
- Performing quick competitor analysis on landing pages and pricing pages
- Identifying gaps and opportunities in feature sets or positioning
- Creating a hook library for improving copy and messaging
- Benchmarking up to five competitors in a structured format
Strengths
- Focuses on actionable steal/avoid/gap recommendations rather than verbose reports
- Supports bilingual output (English and Simplified Chinese)
- Customizable depth (quick, standard, deep) and focus (positioning, pricing, features, copy)
- Ethical scope: relies only on public information, no hacking or rumors
Considerations
- Requires named competitors; vague market analysis is not supported
- Limited to SaaS, AI tools, devtools, and subscription apps
- Output quality depends on publicly available data; no access to internal metrics
README quick start
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.
Related repositories
Similar projects matched by category, topics, and programming language.
lopopolo
Featured
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
Featured
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.