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
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 tsingyuai/growth-lab --skill xhs-replicategit clone --depth 1 https://github.com/tsingyuai/growth-labWrote 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/xhs-replicate)<a href="https://agentmods.dev/skills/tsingyuai/growth-lab/xhs-replicate"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/xhs-replicate/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/xhs-replicate"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/xhs-replicate.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 | $0.00082 | $0.02663 |
| Opus 5 | $0.00041 | $0.01332 |
| Sonnet 5 | $0.00016 | $0.00533 |
| Haiku 4.5 | $0.00008 | $0.00266 |
Grade A, and why
xhs-replicate 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 9d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xhs-replicate — 单一参考驱动的内容生产与复盘
源 Skill 元数据
when_to_use:用户说「出一篇 / 复刻这条爆款 / 做 X 主题的图文 / 找个爆款套一下 / 蹭这个热点出个内容」时。可独立触发,自带前置补全。arguments:"topic_or_viral_note role"argument-hint:"[主题或爆款note_id] [official|personal]"
这条流程的目标(项目核心目标,重定义)
- 高效 = 从「调研找 idea」到「发布就绪」的最短链路：锚一条用户确认的高质量参考，迁移可复用的信息层级，填入当前产品的真实内容并出图。产品事实必须来自用户当前 workspace 或明确提供的资料。
- 优质 = 两个指标驱动,重心全在内容:
- 曝光(阅读数)= 钩子:首页钩子照爆款实际编排,从用户痛点 / 热点出发,让人「看到标题封面就想点」。
- 赞藏(赞阅比 / 藏阅比)= 用户价值:内容有价值、不空、有序清晰、解决用户真实问题——让人「点进来觉得值,愿意赞/收藏」。
⚠️ 诚实边界:这条流程优化的是「单帖内容质量」。曝光量本身受账号权重 × 赛道体量限制(结构性天花板,靠养号/选赛道,内容架构够不到)。复刻让产出更快更稳,不等于保证爆。
5 步闭环
若执行时发现依赖缺失,触发统一的 onboard-growth-lab,由它在一次对话里审计全部能力并让用户选择配置或绕过;本 Skill 不自行维护 onboarding 流程。
产品认知贯穿整个闭环，不在开始时一次性补齐。首次执行或当前任务缺少产品事实时，调用 research-product，只把已确认的产品形态与能力增量写入 SOUL.md；用户、问题和价值继续作为待验证项。详细连接方式见 产品能力与内容机会映射。
① 找 idea → ② 选择参考并迁移结构 → ③ 填内容 → ④ 生图 + 检查 → ⑤ 结果回收与复盘
① 找 idea(调研驱动)
- 调研竞品 / 爆款 / 热点话题 / 热点事件,产出「有曝光潜力的 idea」。
- 来源：xiaohongshu-mcp 的 browser-first 只读采集 +
memory/xhs-replicate/libraries/xhs/中本 loop 运行时派生的通用候选样本 + 当下热点。仓库不附带私有对标库。 - 首次搜索默认采集 25 条。开始前必须告诉用户数量可调整，但建议 25 条；每批限定 20–30 条并在返回后立即落盘，不能等待无界的页面稳定判断。
- 产出 = 一句话 idea:挂哪个热点 / 戳哪个痛点 + 锚哪条爆款(note_id)。
- 先看可借鉴性，不用同类性做准入门槛：商业产品、课程、无源码项目、不同角色或不同宣传目的的内容都可以进入候选。找爆款不是寻找与当前产品、目标用户、产品类型、宣传目的和叙事角色完全相同的内容；只要它在钩子、叙事、信息组织、视觉编排或转化方式上有益，就可以参考。不得因为“不是开源项目”“没有源码”“是课程/商业产品”而直接剔除。
- 对 shortlist 中每条候选都做一份差异—迁移判断，至少记录：它卖什么、对谁说、希望读者做什么、由谁叙述；分别与当前任务有什么差异；这些差异会怎样改变可信度来源、利益承诺强度、销售感、技术细节密度和整体内容调性；最后明确哪些结构可以迁移、哪些表达不能照搬。格式见 产品能力与内容机会映射。
- 🔑 选品判断不可省：下载首批全部封面并检查联系表，只为 3–8 条视觉及内容均通过的候选补详情。直接向用户展示候选代表图、标题、评分和风险；无法确认图片内联展示时，在同一回复提供干净公开链接。若用户认为所有候选都一般，记录原因并换查询，不得强迫从弱批次中选择“最好的一条”。
② 选择参考并迁移结构
- 由用户确认恰好 1 条主要视觉学习样本，写入
visual-reference-selection.json并通过 Collector 验证器。其他候选只能作为被拒绝的研究证据，不能混入视觉规则或生图 reference。 - 只迁移抽象层级、证明区比例、阅读节奏、信息密度等通用规则。不得复制来源的品牌、文案、产品 UI、专有截图、独特装饰、精确构图或完整卡片顺序。
- 产出：
draft.md、image-plan.md、单一参考选择和不可复制边界；每张卡说明自身职责、真实素材和制作模式，不以参考图卡数决定成品卡数。 - 实操由 xhs-render-cards 总 SOP 负责，具体路线见其
references/rendering.md。
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.
- 9d ago First seen · 93 lines · 82 tokens per session scan A 23f497452caf
xhs-replicate is a skill published in the GitHub repository tsingyuai/growth-lab (1,994 stars, last pushed 28d ago), licensed Apache-2.0. It adds 82 tokens to every session and 2,663 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
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…
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.
ad-angles
Use this skill to brainstorm ad concepts across problem, solution, comparison, proof, and curiosity angles, formats, and visual styles. Trigger it when planning a campaign, refreshing stale creative, testing messaging, or preparing creative briefs.