Growth Lab is an open-source growth system that uses coding agents to understand a product, research markets, execute growth activities, and learn from the results. It is designed for teams that want to manage growth work across channels such as SEO and Xiaohongshu through natural-language collaboration, persistent product context, and recorded outcomes. Catalogue add-ons define parts of its product models, research methods, execution workflows, and agent operation.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tsingyuai/growth-labnpx agentmods add skills/tsingyuai/growth-lab/wechat-article-composeWrote 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/tsingyuai/growth-lab/wechat-article-compose)<a href="https://agentmods.dev/skills/tsingyuai/growth-lab/wechat-article-compose"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/wechat-article-compose/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/tsingyuai/growth-lab/wechat-article-compose"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/wechat-article-compose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00081 | $0.01693 |
| Opus 5.5 | $0.00032 | $0.00677 |
| Sonnet 5.5 | $0.00016 | $0.00339 |
| Haiku 4.5 | $0.00008 | $0.00169 |
Grade A, and why
wechat-article-compose 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 18d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
公众号长文创作 SOP
公众号读者愿意读完长文，前提是标题让他点开、首屏说中他的卡点、每一节都给他一个可带走的结果。本 SOP 的重心在“完整解释 + 真实产品能力 + 可转发价值”。
严格按顺序执行。source-review.md 未经用户确认前，不写正文。
0. 确定生产单元
必须具备：选题、目标读者、文章类型（教程 / 案例 / 观点 / 更新）、账号角色（官号 / 个人号）、调用方 Model 的 Memory 输出目录，以及来自 SOUL.md、产品代码、页面或用户明确提供资料的可验证产品事实。
生产单元目录由调用方决定，默认 memory/<model-name>/outputs/<YYYYMMDD-slug>/：
| 文件 | 作用 |
|---|---|
source-review.md |
阶段一 brief：写什么、参考哪 1-2 篇、为什么读者需要、证据与能力边界 |
article.md |
正文源文件，模板见 templates/article.md |
wechat.yml |
标题、摘要、作者、封面、评论、发布审批，模板见 templates/wechat.yml |
_review.md |
复刻锚、价值三问、标题候选、合规与发布自检，模板见 templates/_review.md |
cover.png / assets/ |
封面与正文图片；正文图片只用本地相对路径 |
1. 阶段一 brief
先读：
然后写 source-review.md：文章类型；1-2 篇复刻锚（已发布公众号长文、本产品已验证的小红书爆款或真实产品工作流）及复刻了什么；读者问题与可量化证据；产品能力边界（哪些已上线可验证、哪些只能作为探索写出边界）。交给用户确认后再进入下一步。
2. 大纲与标题
按“读者问题 → 先给结论 → 方法/案例 → 产品能力 → 截图证据 → 下一步”编排大纲，每个小标题都能单独被扫读。
写 5 个标题候选，每个标注钩子类型：痛点 / 反差 / 结果 / 数字 / 物证。
3. 写正文
-
逐节回答用户价值三问，把“产品有某功能”改写成“读者因此能做到什么”。
-
产品能力只写已上线、可验证的内容；来源不明确就停下询问，禁止补写。
-
对标题、摘要和正文执行 xhs-render-cards 的 DAI SOP 的第一、二遍（恢复真实说话者、删除模型腔），语气按 editorial-voice.md 校准；不套小红书口吻。
-
卡片、表格、步骤、数据对比等结构化内容直接用排版块写进正文，不截取网页卡片当配图（公众号不渲染 Markdown 表格）：
::: card [accent|soft|dark] #### 眉题 / ### 标题 / 段落 / --- 分隔 / - 列表项 [| 标签] ::: steps - 标题 | 说明 | 补充 ::: stats - 数值 | 说明 ::: bars 系列A | 系列B - 指标 | A 百分比 | B 百分比 ::: -
配图只承担排版做不到的事：第一印象、真实产品与成果物证、转化入口。先写
image-plan.md（位置、要传达什么、构图、素材来源、制作路线），正文用::: figure配图位占位（首行图题，其余为说明），图片生成后再替换；仍含配图位时发布 Executor 拒绝创建草稿。 -
产品界面图必须来自 screenshot-assets 的真实截图；概念图、封面可以走 generate-image。不得让 AI 伪造产品 UI。
-
封面建议 2.35:1（如 900×383）；正文图片放在生产单元的
assets/下并以相对路径引用。 -
标题只写在
wechat.yml，正文不写 H1；article.md中不留>说明行或{…}占位符，渲染器会把它们原样输出到正文。 -
小标题用
## 01 标题形式，两位编号显示为主题强调色。 -
品牌色通过
wechat.yml的theme设置，只作点缀色（编号、线条、标记、强调字），底色保持白色。 -
需要可点击入口时使用
[](https://...)，alt 会显示为图片下方的链接文字。
What ships with it
10 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.
- agents/openai.yaml 241 B
- references/article-structure.md 1.5 KB
- references/compliance.md 1.1 KB
- references/editorial-voice.md 902 B
- references/replicate-value-guide.md 2.5 KB
- references/templates/_review.md 1.2 KB
- references/templates/article.md 717 B
- references/templates/wechat.yml 272 B
- references/title-patterns.md 1.3 KB
- scripts/check-wechat-compliance.py 5.6 KB runs code
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.
- 18d ago First seen · 89 lines · 81 tokens per session scan A e0db7bc70134
wechat-article-compose is a skill published in the GitHub repository tsingyuai/growth-lab (1,992 stars, last pushed 19d ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,693 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
viral-marketing-playbook
Design viral loops into your product — referral programs, invite systems, and share mechanics that drive exponential growth. Includes K-factor calculations and real examples from Dropbox, Slack, and Notion. By @WeiYipei.
synthesis-explore
Synthesis EXPLORE stage for the Diffmode growth-tactics pipeline (fuses the blind-combination draw + emergent-mechanism derivation — formerly two separate synthesis steps — into ONE structural-check-only stage). Reads the per-run growth-factors.json (LIGHT vector DB) + synthesis-constraints.json + founder-input +…
diagnostics-intake
Fast founder-input capture for the Diffmode growth-tactics pipeline (the diagnostics stage). Produces WS/01-diagnostics/founder-input.md in the exact schema the enrichment + synthesis stages read. Two modes — (A) URL mode researches a product's website (homepage/pricing/about) plus a web-research pass to prefill the…
growth-factors-mining
Builds a per-run LIGHT growth-vector database for the Diffmode growth-tactics pipeline by mining public growth case studies fresh, every run, and distilling each into atomic "growth factors" (transferable mechanisms). Clean-room — NEVER reads the proprietary tacticsDB. Outputs growth-factors.json (20-40 vectors spread…
lite-constraints
Generates synthesis-constraints.json for the Diffmode growth-tactics pipeline by reasoning in-context over the per-run growth-factors.json (LIGHT vector DB) + founder context — the clean-room, no-Python replacement for the proprietary Python constraints generator. Emits the white-space pairs, mandatory…
cro-optimization
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze…