builder-growth
CLAUDE.md2 starsChanged 5 months agoMITView on GitHub
builder-growth — AI Growth Skills Pack v1.1.0 This is the full lifecycle order. Not every skill is required on every project — trigger the ones that match the work in front of you. A pure copy review on an already-launched product does not need growth-strategy-design re-run; a brand-new initiative does. Standard growth frameworks optimise. This pack diagnoses and plans before optimising: - Every growth initiative starts with a named stage, segment, goal, and constraint — not a default channel -…
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-messaging-reviewSkill
- campaign-brief-generatorSkill
- channel-selection-auditSkill
- copy-quality-gateSkill
- experiment-designSkill
- funnel-analysisSkill
- growth-metrics-designSkill
- growth-strategy-designSkill
- launch-plan-designSkill
- offer-quality-gateSkill
- positioning-auditSkill
- pricing-page-reviewSkill
- retention-designSkill
- social-proof-reviewSkill
The file
We split this CLAUDE.md into the rules it gives an agent
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 59
Every growth initiative starts with a named stage, segment, goal, and constraint — not a default channel
- Distinctive: line 60
Every channel is scored against the same eight criteria before budget is committed
- Distinctive: line 61
Every offer has risk reversal and a single CTA before copy is written
- Distinctive: line 62
Every funnel optimisation starts with a diagnosed root cause
- Distinctive: line 63
Every experiment has a calculated sample size and a pre-specified stopping rule
- Distinctive: line 64
Every launch has a named rollback or pause criterion, decided before launch day
- Distinctive: line 65
Every AI capability claim has a source or is removed
- Distinctive: line 66
Every retention initiative defines the activation moment before launch
- Distinctive: line 67
Every pricing page and proof asset is reviewed for clarity and source before it ships
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
builder-growth — Claude Configuration
Pack Version
builder-growth — AI Growth Skills Pack v1.1.0
File Conventions
| Artifact | Path |
| Growth strategies | growth/strategy/<project>-<date>.md |
| Channel audits | growth/channels/<project>-channel-audit-<date>.md |
| Offer quality gates | growth/offers/<offer>-quality-gate-<date>.md |
| Positioning documents | growth/positioning/<product>-<date>.md |
| Campaign briefs | growth/campaigns/<campaign>-brief-<date>.md |
| Copy reviews | growth/copy-reviews/<campaign>-<date>.md |
| Launch plans | growth/launches/<project>-launch-plan-<date>.md |
| Growth metrics designs | growth/metrics/<project>-metrics-<date>.md |
| Funnel analyses | growth/funnel-analysis/<funnel>-<date>.md |
| Experiment designs | growth/experiments/<experiment>-design-<date>.md |
| Retention designs | growth/retention/<feature>-design-<date>.md |
| Social proof reviews | growth/social-proof/<campaign>-proof-review-<date>.md |
| Pricing page reviews | growth/pricing/<page>-review-<date>.md |
| Messaging reviews | growth/messaging-reviews/<campaign>-<date>.md |
| Growth critiques | growth/reviews/<work>/<date>-critique.md |
Skill Trigger Sequence
This is the full lifecycle order. Not every skill is required on every project — trigger the ones that match the work in front of you. A pure copy review on an already-launched product does not need growth-strategy-design re-run; a brand-new initiative does.
growth-strategy-design→ before any channel, offer, or campaign decision is madechannel-selection-audit→ before any campaign, content plan, or outbound motion is builtoffer-quality-gate→ before any copy or campaign is built around an offerpositioning-audit→ before any copy is writtencampaign-brief-generator→ before a campaign moves from strategy to creative productioncopy-quality-gate→ before any external copy shipslaunch-plan-design→ before any approved project, product, or campaign launchesgrowth-metrics-design→ before any growth initiative executesfunnel-analysis→ before any CRO effort startsexperiment-design→ before any A/B test runsretention-design→ before any feature launchessocial-proof-review→ before any testimonial, logo, case study, or quantified result shipspricing-page-review→ before any pricing or packaging page shipsai-messaging-review→ before any AI product claim ships externally
Agent Usage
| Agent | When to Use |
growth-critic | After positioning, copy, or experiment designs are drafted, before they ship |
experiment-designer | When designing any growth experiment |
messaging-reviewer | Before any external AI capability claim ships |
growth-strategist | When a project needs growth strategy, channel selection, offer validation, or a launch plan defined |
campaign-reviewer | When a campaign brief, metrics design, social proof, or pricing page needs to be built or reviewed before it ships |
What Makes This Pack Different From Generic Growth Frameworks
Standard growth frameworks optimise. This pack diagnoses and plans before optimising:
- Every growth initiative starts with a named stage, segment, goal, and constraint — not a default channel
- Every channel is scored against the same eight criteria before budget is committed
- Every offer has risk reversal and a single CTA before copy is written
- Every funnel optimisation starts with a diagnosed root cause
- Every experiment has a calculated sample size and a pre-specified stopping rule
- Every launch has a named rollback or pause criterion, decided before launch day
- Every AI capability claim has a source or is removed
- Every retention initiative defines the activation moment before launch
- Every pricing page and proof asset is reviewed for clarity and source before it ships
Optimising without diagnosing — and executing without a strategy — is the most expensive growth mistake. This pack blocks it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.