Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Gingiris-1031/gingiris-skills --skill gr-b2b-growthgit clone --depth 1 https://github.com/Gingiris-1031/gingiris-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gr-b2b-growth)<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gr-b2b-growth"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gr-b2b-growth/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gr-b2b-growth"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gr-b2b-growth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.01691 |
| Opus 5 | $0.00042 | $0.00846 |
| Sonnet 5 | $0.00017 | $0.00338 |
| Haiku 4.5 | $0.00008 | $0.00169 |
Grade A, and why
gr-b2b-growth scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gr-b2b-growth — B2B SaaS 增长
什么时候用
- "我的 B2B SaaS 怎么从 0 做到 PMF"
- "PLG 还是 SLG，我该选哪个"
- "怎么做 affiliate 营销"
- "渠道合作 / 集成伙伴怎么谈"
- "Enterprise sales 怎么起"
- "私有化部署怎么收款 / 尾款怎么要"
- "客户需求蔓延怎么管（SOW / 变更）"
增长飞轮（4 象限）
PLG（产品驱动）
↑
|
已有流量 + 短决策 ←→ 需要信任 + 长周期
|
↓
SLG（销售驱动）
选型判据：
- ACV < $1k/年 & 决策周期 < 1 周 → PLG（Vercel、Supabase 模式）
- ACV > $10k/年 & 决策周期 > 1 个月 → SLG（Snowflake、Databricks 模式）
- 中间 → PLG-to-SLG hybrid（HeyGen、Deel 模式）
5 阶段路径
| 阶段 | ARR | 关键动作 |
|---|---|---|
| Pre-PMF | $0-$100k | 10-30 次用户访谈（联动 gr-user-interview），确认 must-have |
| Early PMF | $100k-$1M | 投 1-2 个渠道做深（不要广撒网） |
| Growth | $1M-$5M | 引入 affiliate + 集成伙伴，PLG 加 sales-assist |
| Scale | $5M-$10M | Enterprise 团队、合规认证（SOC2）、channel 加码 |
| Ecosystem | $10M+ | 开放平台、investor / agency 分销 |
2B 打单与交付（私有化 & 定制实操）
来自某 Multi-Agent 开源商业化项目复盘。签合同只是一半，全额收回款才是另一半。
付款与尾款防御
| 规则 | 细节 |
|---|---|
| 分段付款 | 私有化 3:4:3 或 4:4:2（首批功能上线 / 全部部署完 / 运维 3–6 个月后尾款） |
| 签约即收款 | 签合同当天收 30% |
| 违约金 | 写进合同：拖一天多付 0.5% |
| 尾款筹码 | 留 1–2 个功能部署在自己服务器，尾款结清才迁（签前说清、条款写清） |
| 找谁要 | 尾款找对接的最高的人；推诿可问 1–2 次 CEO |
| 长期方向 | 预付款越来越高、尾款越来越少 |
需求边界：SOR / SOW / CCB
- SOR（客户原始输入）与 SOW（验收标准+交付节点+变更条款）分开，合同和 SOW 一起签
- 变更走 CCB：客户书面发起 → 双方 PM 评估金额/工期 → 签变更确认
- 一切留痕；合同指明"项目验收对接人"
- 客户口头承诺再多，只有 paperwork 有效
商务推拉与定价
- 客户提 50 个需求、能做 40 →"先答应 10 个、因为想帮你做到 15 个"，把让步做成人情
- 不想做的需求抬价过滤（人/天多标几天），不直接拒
- 私有化只有两个真需求：数据隐私 + 接内部权限系统，其他都该买 SaaS
- SaaS 二开直接卖 License；SSO 等集成开放 API + 标准手册让客户自己做
营收与渠道账
- $100 万 ARR 拆解：9 个 $10 万 2B 客户 或 每 $10 万 ≈ 500 个 $200/年订阅用户（$1M ≈ 5,000）
- 代理分层：reseller 10–20% 推荐费；年销 $10 万银牌 15%、$30 万金牌 20%
- 代理尽调三问：代理过什么产品？客户从哪来？Reseller 还是 Service Partner？
- 2B 内容公式：80% 讲自己如何帮客户成功 + 20% 讲客户；deck 先讲怎么痛、再说怎么好
深度参考
references/deal-execution.md— 2B 打单与交付框架（六步流程 / SOW+CCB / 付款结构与尾款防御 / 渠道分层 / $1M ARR 拆解）- 完整实操层（合同条款速查卡、签约前 12 问 Checklist、实战话术库）见 Gingiris 付费实操手册 → https://gingiris.tools/playbook/2b-deals/
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 143 lines · 83 tokens per session scan A 355e580b94db
gr-b2b-growth is a skill published in the GitHub repository Gingiris-1031/gingiris-skills (79 stars, last pushed 5d ago), licensed MIT. It adds 83 tokens to every session and 1,691 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gingiris-b2b-growth
A multilingual guide to growing a business-to-business software company, from finding product-market fit to reaching $10 million in annual recurring revenue. It covers product-led growth, sales-led growth, partnerships, contracts, sales materials, and measurement.
afrexai-startup-metrics-engine
Complete startup metrics command center — from raw data to investor-ready dashboards. Covers every stage (pre-seed to Series B+), every model (SaaS, marketplace, consumer, hardware), with diagnostic frameworks, benchmark databases, and board-ready reporting.
skill-catalog
Maintains the central registry of all skills with dependencies, trigger phrases, review gates, and chaining.
gbp-review-strategy
Analyzes review velocity, sentiment distribution, and competitor review patterns, then produces branded response.
design-incident-response
Triage decision tree for design incidents flagged by /design-reviewer.
design-reviewer
Reviews implemented React/Tailwind/CSS output for design quality across 5 dimensions scored 0-4: anti-patterns.