grow-loop
Run a conversion loop — observe, hypothesise, smallest change, verify metric — for a live or soon-live site.
Skill by Alfred-Lau
Chalk Labs
Need help deploying grow-loop?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/alfred-lau-grow-loop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/grow-loop
What's inside
- Skill name
grow-loop- Description
- Run a conversion loop — observe, hypothesise, smallest change, verify metric — for a live or soon-live site.
- License
- MIT
- Instructions
- 36 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- log-template.md
SKILL.md (first lines)
# Grow Loop One **conversion loop** at a time. No big-bang redesigns disguised as growth. ## Process ### 1. Preconditions - Read `BRIEF.md`, `TRACKING.md`, `docs/agents/analytics.md` - If the metric you need isn't tracked and isn't explicitly qualitative, run **`/instrument`** first (or narrow to a qualitative loop the user accepts) ### 2. Observe Summarise what you know: funnel drop-offs, feedback, visual-qa leftovers, SEO smells. Prefer evidence over vibe. ### 3. Hypothesise (grill if needed) One hypothesis in the form: > If we **[smallest change]**, then **[metric]** will **[direction]** because **[reason]**. Confirm with the user. Reject bundled changes — split them. ### 4. Specify the change If UI: write or update a focused page-spec slice / issue, then **`/implement-ui`** (fresh context). If copy-only: edit copy against `BRAND.md`. If tracking-only: return to `/instrument`. ### 5. Verify Define the verification window and method (analytics, qualitative, or screenshot before/after). Append the loop entry to `docs/site/GROWTH.md` using [log-template.md](./log-template.md). **Completion criterion:** hypothesis recorded; change shipped or ticketed; verification method explicit.
From Alfred-Lau/skills, MIT.
More from Alfred-Lau/skills
- 0.547score
a11y-pass
Alfred-Lau
Accessibility smoke pass for a page — focus order, contrast, semantics, alts.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
responsive-pass
Alfred-Lau
Walk critical breakpoints for a page — no overflow, intact hero, readable CTA.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ui-prototype
Alfred-Lau
Build throwaway UI variants to answer one visual design question.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
design-critique
Alfred-Lau
Critique a design direction, mock, or live page against site composition hard rules and DIRECTION — before or beside code.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
perf-pass
Alfred-Lau
Performance smoke pass for a page — LCP/CLS risks on fonts, images, critical path.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
port-page
Alfred-Lau
Probe source and target stacks/conventions, write a port plan, then faithfully port a page with function, style, and responsive parity.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
instrument
Alfred-Lau
Write a tracking plan and land the events — named events, properties, funnel steps before growth work.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
visual-direction
Alfred-Lau
Lock a one-composition visual thesis into DIRECTION.md — type, color, material, atmosphere, reference boundaries.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
conversion-audit
Alfred-Lau
Audit funnel friction — CTA clarity, trust, drop-off hypotheses — and produce smallest-change recommendations.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
ship-checklist
Alfred-Lau
Run the launch gate — SEO basics, analytics, errors, OG, smoke a11y/perf — before a site or page goes live.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
design-system
Alfred-Lau
Freeze tokens-first design primitives into TOKENS.md and align code CSS variables.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
implement-ui
Alfred-Lau
Faithfully restore a page-spec into UI code using tokens — no improvisational redesign.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 29, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Alfred-Lau/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Alfred-Lau
- 0.547score
perf-pass
Alfred-Lau
Performance smoke pass for a page — LCP/CLS risks on fonts, images, critical path.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ui-prototype
Alfred-Lau
Build throwaway UI variants to answer one visual design question.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
responsive-pass
Alfred-Lau
Walk critical breakpoints for a page — no overflow, intact hero, readable CTA.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
a11y-pass
Alfred-Lau
Accessibility smoke pass for a page — focus order, contrast, semantics, alts.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
design-critique
Alfred-Lau
Critique a design direction, mock, or live page against site composition hard rules and DIRECTION — before or beside code.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
port-page
Alfred-Lau
Probe source and target stacks/conventions, write a port plan, then faithfully port a page with function, style, and responsive parity.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get grow-loop running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
grow-loop skill. Agent Mart. https://agentmart.dev/skills/alfred-lau-grow-loop (last updated 2026-10-24)