Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

ai-startup-skills

skill · huaxialucaicaizi/ai-startup-skillsNOASSERTION licenceAudited 12 Nov 2026 · source 44b2cb972f19

★ 924pushed 1 day ago
✓SAFEGrade B · 89/100 · 12 Nov 2026 · 44b2cb9
924repo stars · whole huaxialucaicaizi/ai-startup-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 44b2cb972f19 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Use when a founder or one-person company (一人公司/OPC) building an AI product in China needs end-to-end startup help and it is unclear which step they are on. Routes by stage through a 7-step journey - MVP validation,…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “ai-startup-skills (huaxialucaicaizi/ai-startup-skills)”. Retrieved 12 Nov 2026. https://modelsatlas.com/skills/huaxialucaicaizi/ai-startup-skills

Trust audit

Audit 0.4.1 · source read 12 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 low1 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS2
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (2)

LOWInventory / provenanceinv.hidden_file · .lycheeignore
F-13 Inventory / provenanceCWE-1104Layer L0
.lycheeignore
Why
hidden member outside the usual dotfiles
Fix
review its purpose
INFOInventory / provenanceinv.oversize · assets/promo/ai-startup-skills-promo.mp4
F-13 Inventory / provenanceCWE-1104Layer L0
assets/promo/ai-startup-skills-promo.mp4
Why
4483549 bytes not read
Fix
—

Audit 0.4.1 · source sha 44b2cb972f19 · 12 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherhuaxialucaicaizi GitHub userOwner of the repository this skill is read from
  • Source folderhuaxialucaicaizi/ai-startup-skillsThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdict44b2cb972f19A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Use when a founder or one-person company (一人公司/OPC) building an AI product in China needs end-to-end startup help and it is unclear which step they are on. Routes by stage through a 7-step journey - MVP validation,…

---
name: ai-startup-skills
description: Use when a founder or one-person company (一人公司/OPC) building an AI product in China needs end-to-end startup help and it is unclear which step they are on. Routes by stage through a 7-step journey - MVP validation, business plan, policy and subsidies, roadshow, growth, pricing and sales, registration and compliance - to the matching sub-skill in skills/.
---

# AI 创业 Skill 包 · Router

This is the entry skill for a 7-step toolkit. It does not do the work itself: it figures out which stage the user is at and hands off to the matching sub-skill under `skills/`.

## The 7 steps

| Step | Sub-skill | Use when the user... |
|---|---|---|
| 1 | `skills/ai-mvp-validation/SKILL.md` | has an AI product idea/MVP and does not yet know if anyone wants it |
| 2 | `skills/business-plan-skill/SKILL.md` | needs a business plan / BP, deck content or application materials |
| 3 | `skills/opc-policy-navigator/SKILL.md` | asks which policies, subsidies, vouchers or OPC community spaces they can apply for |
| 4 | `skills/ai-pitch-coach/SKILL.md` | prepares a live roadshow or defense for a park, incubator or competition |
| 5 | `skills/opc-growth-playbook/SKILL.md` | needs cold-start growth on Xiaohongshu, Douyin or WeChat Channels |
| 6 | `skills/opc-pricing-sales/SKILL.md` | needs prices, packages, quotes or a closing process |
| 7 | `skills/opc-registration-compliance/SKILL.md` | asks which entity to register or what ongoing compliance applies |

## Routing

1. If the request clearly matches one step, read that sub-skill's `SKILL.md` and follow it. Do not ask extra questions first.
2. If it is unclear, ask at most two short questions: what they are building, and what they have already done (validated? BP written? registered?). Then pick the earliest step not yet done.
3. Default order for a new founder is 1 → 2 → 3/7 → 4 → 5 → 6. Steps 3 and 7 can run in parallel; step 7 is often required before applying in step 3.
4. Pass outputs forward: validation evidence from step 1 feeds the BP in step 2; the BP feeds policy applications (3) and the roadshow (4); pricing (6) uses the funnel data from growth (5).
5. When a step finishes, say in one line which step is a sensible next one, and why.

## Rules

- Each sub-skill's own rules win inside that step (official links only, no invented benchmarks, compliance flags).
- Never invent numbers, policies, cases or testimonials. Mark any example as fictional.
- Policy, legal and tax content is information guidance, not professional advice; point to official sources.

Excerpt, first 2,567 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 44b2cb9

Download folder ↗
git clone https://github.com/huaxialucaicaizi/ai-startup-skills.git

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 44b2cb972f19 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 44b2cb972f19

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/huaxialucaicaizi/ai-startup-skills/badge.svg)](https://modelsatlas.com/skills/huaxialucaicaizi/ai-startup-skills/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Spec Driven Development✓SAFE

addyosmani/agent-skills

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when…

★ 100kGrade B
Test Driven Development!CAUTION

addyosmani/agent-skills

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when…

★ 100kGrade B
Using Agent Skills✓SAFE

addyosmani/agent-skills

Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are…

★ 100kGrade B
Api And Interface Design✓SAFE

addyosmani/agent-skills

Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing…

★ 100kGrade B
Ci Cd And Automation✓SAFE

addyosmani/agent-skills

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

★ 100kGrade B
Code Review And Quality✓SAFE

addyosmani/agent-skills

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it…

★ 100kGrade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/huaxialucaicaizi/ai-startup-skills/badge.svg)](https://modelsatlas.com/skills/huaxialucaicaizi/ai-startup-skills/)

Questions about ai-startup-skills

What does the ai-startup-skills skill do?
创业公司做 AI 产品的 7 步 Agent Skill 合集:验证 → BP → 政策 → 路演 → 获客 → 定价 → 注册。
Is ai-startup-skills safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can ai-startup-skills access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does ai-startup-skills work with?
Its documentation mentions claude-code, codex and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (44b2cb972f19), read on 2026-11-12. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.