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 screenshot-assetsgit 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/screenshot-assets)<a href="https://agentmods.dev/skills/tsingyuai/growth-lab/screenshot-assets"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/screenshot-assets/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/screenshot-assets"><img src="https://agentmods.dev/badge/skills/tsingyuai/growth-lab/screenshot-assets.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 | $0.00077 | $0.00487 |
| Opus 5 | $0.00039 | $0.00244 |
| Sonnet 5 | $0.00015 | $0.00097 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
screenshot-assets 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 11d 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.
What it actually says
Screenshot assets
Use scripts/capture.py. It connects to the user's already-running Chrome through CDP, so the user completes login in their own browser and retains control of authentication.
Preconditions
If uv, Chrome, CDP, or the target login is unavailable, invoke onboard-growth-lab. Do not look for credentials in another repository and do not inject copied tokens or cookies.
Ask for the target URL, what UI fact the screenshot must prove, output path under the invoking Model's Memory, viewport, and optional CSS selector. Never infer a staging URL or test account.
Capture
Start Chrome with remote debugging as directed by onboarding, let the user log in, then run:
uv run --with playwright python executors/screenshot-assets/scripts/capture.py \
--cdp http://127.0.0.1:9222 \
--url "https://product.example/workspace/..." \
--out memory/<loop>/assets/screenshots/<descriptive-name>.png \
--width 1440 --height 900
For one stable component, add --selector '<css-selector>'. Add --wait-selector for a loading boundary and --delay-ms only when the application needs a short settling interval.
Quality and privacy
- Capture only the minimum region needed to support the claim.
- Inspect the output at full size. Reject loading, error, stale, clipped, blurred, or wrong-account states.
- Redact personal data before distribution; do not capture secrets, cookies, tokens, admin panels, or unrelated user content.
- Record source URL, capture time, viewport, selector, product version/environment, and what the screenshot demonstrates in a neighboring metadata file.
- Do not use AI-generated UI as product evidence.
- Store reusable screenshots once in the loop's Memory; outputs may reference them without duplicating the source asset.
What ships with it
2 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.
- 11d ago First seen · 38 lines · 77 tokens per session scan A 4e4008103dbc
screenshot-assets is a skill published in the GitHub repository tsingyuai/growth-lab (2,000 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 487 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.
screenshot-automation
Automatically captures, crops, and beautifies screenshots from URLs for your portfolio or docs.