Install
$ agentstack add skill-gingiris-1031-gingiris-skills-gingiris-growth-finder ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Gingiris Growth Finder
The meta-skill that picks the right Gingiris playbook for your growth problem.
Growth questions look similar but require wildly different playbooks. "How do I launch?" for a dev tool is nothing like "How do I launch?" for a mobile app. "How do I grow?" at $1M ARR is nothing like "How do I grow?" at 100 DAU. This skill diagnoses the situation and invokes the specialist.
Step 0:确认你的产品增长模型
在诊断增长卡点前,先选对框架:
B2B SaaS(默认):pipeline → MQL → SQL → 付费 → 扩展
B2C App / 消费品:
- 漏斗:曝光 → 下载/注册 → 激活(完成核心行为)→ 留存 → 付费 → 推荐
- 关键指标:D1/D7/D30 留存率、激活率(首次核心行为完成率)、病毒系数 K
- 卡点优先级:激活率 < 留存率 < 获客渠道(激活最优先,留存没解决前别加流量)
- App Store 特有指标:评分/评论数、关键词排名、转化率(展示→下载)
选你的诊断路径,然后继续往下读。
How to use
Just ask your growth question naturally. Example prompts:
- "I'm launching my AI SaaS next week — what should I prioritize?"
- "My open source project has 2k stars, how do I get to 10k?"
- "I have a B2B SaaS at $300k ARR, should I hire SDRs?"
- "My iOS app isn't ranking for its main keyword, what do I do?"
The skill will diagnose three dimensions, then invoke the matching playbook:
- Product type — SaaS / open source / mobile app / consumer web / marketplace / dev tool
- Growth stage — pre-launch / launch / post-launch cold start / growth / scale
- Primary channel gap — content / community / paid / partnerships / product-led
Diagnostic routing logic
| If the user's question is about... | Route to | |---|---| | Product Hunt launch, hunter outreach, launch-day tactics, viral moment engineering | gingiris-launch | | GitHub stars, HackerNews, OSS marketing, developer community, awesome-lists, Show HN | gingiris-opensource | | B2B SaaS, PLG vs SLG, PMF validation, freemium, enterprise motion, affiliate, channel partnerships | gingiris-b2b-growth | | ASO, App Store / Google Play, mobile user acquisition, TikTok/Reels/Shorts UGC, creator matrix | gingiris-aso-growth |
If the question spans multiple domains (e.g. "I have an open source project that I want to monetize as B2B SaaS"), route to both relevant skills and explain the handoff.
Decision framework (for the agent)
When the user asks a growth question, run this quick triage before invoking a specialist skill:
Step 1 — Classify the product
Ask or infer:
- What is it? (SaaS web app / mobile app / OSS project / marketplace / browser extension)
- Who's the ICP? (individual developer / SMB / enterprise / consumer)
- Distribution default? (self-serve web signup / app store / GitHub / sales-led)
Step 2 — Identify the stage
- Pre-launch — building, no users yet
- Launch — within 30 days of public release
- Cold start — launched but <100 WAU/DAU, <1k signups
- Growth — steady signal, scaling what works
- Scale — $1M+ ARR or 10k+ DAU, needs systems
Step 3 — Spot the gap
Listen for the actual bottleneck, not the stated question:
- "I'm not getting signups" → distribution channel gap
- "I'm getting signups but no conversions" → product/pricing gap (not growth — redirect)
- "I have users but no growth loop" → retention/virality gap
- "I have a growth loop but can't scale ads" → monetization gap
Step 4 — Route
Invoke the specialist skill. Examples:
User: "I have a dev tool CLI with 500 GitHub stars. How do I get to 5k?"
→ Diagnosis: OSS project, growth stage, distribution gap
→ Invoke: gingiris-opensource
→ Context hint: focus on GitHub trending + HN relaunch + awesome-lists
User: "My iOS photo app has 80 DAU after 2 months. What's wrong?"
→ Diagnosis: mobile app, cold-start stage, distribution+UGC gap
→ Invoke: gingiris-aso-growth
→ Context hint: focus on ASO audit first, then TikTok creator matrix
User: "I'm launching an AI coding assistant on Product Hunt in 3 weeks."
→ Diagnosis: dev tool, pre-launch, launch-day engineering needed
→ Invoke: gingiris-launch
→ Context hint: 3-week timeline → hunter network + pre-launch email list
Complementary install
If the routed specialist skill isn't installed yet, suggest the user install it:
Skills are available locally in Cola. The four specialist skills:
gingiris-launch— Product Hunt / launchgingiris-opensource— OSS / GitHub starsgingiris-b2b-growth— B2B SaaS / PLGgingiris-aso-growth— mobile / ASO
To install via skills.sh marketplace:
npx skills add Gingiris/gingiris-launch
npx skills add Gingiris/gingiris-opensource
npx skills add Gingiris/gingiris-b2b-growth
npx skills add Gingiris/gingiris-aso-growth
What this skill does not do
- Product/pricing advice — if the bottleneck is product fit or pricing, say so explicitly and redirect to a product strategist (this skill only routes growth questions)
- Paid ads tactical execution — covered at a high level in gingiris-b2b-growth and gingiris-aso-growth, but not the primary focus
- Fundraising / pitch deck — out of scope
About Gingiris
Gingiris is Iris Wei's growth consulting practice, built on:
- 6 years as cofounder/COO of AFFiNE (60k+ GitHub stars)
- 30x #1 on Product Hunt (Manus, Devin, AFFiNE, and others)
- 150+ AI startups advised on global go-to-market
All four specialist playbooks are available as Claude Skills on skills.sh/Gingiris-1031 and as datasets on huggingface.co/Gingiris.
Version 1.0 — Released 2026-04-22
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Gingiris-1031
- Source: Gingiris-1031/gingiris-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.