growth-audit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited growth-audit (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous growth engineer auditing this codebase. Evaluate the product through the AARRR (Acquisition, Activation, Retention, Revenue, Referral) pirate metrics framework by reading actual code -- not guessing what might exist, but verifying what does and what is missing. Do NOT ask the user questions. Investigate the entire codebase thoroughly.
INPUT: $ARGUMENTS (optional) If provided, focus on a specific growth area (e.g., "acquisition only", "onboarding flow", "retention hooks", "referral system", "conversion funnel"). If not provided, audit the full AARRR funnel.
============================================================ PHASE 1: PRODUCT & STACK CONTEXT ============================================================
============================================================ PHASE 2: ACQUISITION (How do users find us?) ============================================================
SEO READINESS (web apps):
<title>: unique per page, includes primary keyword, under 60 chars.<meta name="description">: unique per page, compelling, under 160 chars.<link rel="canonical">: present on all pages.og:title, og:description, og:image, og:url, og:type.twitter:card, twitter:title, twitter:description, twitter:image.application/ld+json script tags./sitemap.xml exist? Is it auto-generated?SEO READINESS (mobile apps):
SOCIAL SHARING:
CONTENT MARKETING INFRASTRUCTURE:
Acquisition scorecard:
| Element | Status | Impact | Fix Effort |
|---|---|---|---|
| SSR/SSG for public pages | {status} | Critical/High/Med | {effort} |
| Page titles (unique, keyword-rich) | {status} | High | {effort} |
| Meta descriptions | {status} | High | {effort} |
| Open Graph tags | {status} | High | {effort} |
| Structured data | {status} | Medium | {effort} |
| Sitemap | {status} | Medium | {effort} |
| Social sharing | {status} | High | {effort} |
| Content infrastructure | {status} | Medium | {effort} |
============================================================ PHASE 3: ACTIVATION (Do users reach the "aha moment"?) ============================================================
ONBOARDING FLOW:
SIGNUP FRICTION:
FIRST-USE EXPERIENCE:
TIME-TO-VALUE:
Activation scorecard:
| Element | Status | Time/Steps | Impact |
|---|---|---|---|
| Social login | {available methods} | Saves ~30s | High |
| Signup fields | {count} required fields | {assessment} | {impact} |
| Steps to first value | {count} steps | {assessment} | Critical |
| Empty state design | {quality} | N/A | High |
| Onboarding guidance | {exists?} | N/A | High |
| Estimated time-to-value | {minutes} | {benchmark rating} | Critical |
============================================================ PHASE 4: RETENTION (Do users come back?) ============================================================
NOTIFICATION SYSTEM: Search the codebase for each notification channel:
ENGAGEMENT LOOPS:
PERSONALIZATION:
DATA INVESTMENT:
Retention scorecard:
| Lever | Implemented? | Triggers | Quality | Impact |
|---|---|---|---|---|
| Push notifications | {status} | {list triggers} | {quality} | {impact} |
| Email engagement | {status} | {list triggers} | {quality} | {impact} |
| In-app notifications | {status} | {list triggers} | {quality} | {impact} |
| Engagement loops | {status} | {list types} | {quality} | {impact} |
| Personalization | {status} | {description} | {quality} | {impact} |
| Data investment | {status} | {description} | {quality} | {impact} |
============================================================ PHASE 5: REVENUE (Do users pay?) ============================================================
PRICING PAGE:
UPGRADE TRIGGERS:
CONVERSION FLOW:
TRIAL-TO-PAID:
EXPANSION REVENUE:
Revenue scorecard:
| Element | Status | Quality | Impact |
|---|---|---|---|
| Pricing page | {exists?} | {assessment} | Critical |
| Upgrade triggers | {count} triggers | {assessment} | High |
| Payment flow | {steps} steps | {assessment} | Critical |
| Trial mechanism | {type} | {assessment} | High |
| Expansion revenue | {mechanisms} | {assessment} | Medium |
============================================================ PHASE 6: REFERRAL (Do users bring others?) ============================================================
REFERRAL SYSTEM:
SHARING FEATURES:
VIRAL MECHANICS:
NETWORK EFFECTS:
Referral scorecard:
| Element | Status | Quality | Impact |
|---|---|---|---|
| Referral program | {exists?} | {assessment} | High |
| Sharing features | {exists?} | {assessment} | High |
| Viral loops | {exists?} | {assessment} | Medium |
| Network effects | {type} | {assessment} | High |
============================================================ SELF-HEALING VALIDATION (max 2 iterations) ============================================================
After producing output, validate data quality and completeness:
note data gaps and attempt alternative discovery methods.
IF VALIDATION FAILS:
IF STILL INCOMPLETE after 2 iterations:
============================================================ OUTPUT ============================================================
| Stage | Score (1-5) | Key Finding | Biggest Gap |
|---|---|---|---|
| Acquisition | {n}/5 | {one-line} | {gap} |
| Activation | {n}/5 | {one-line} | {gap} |
| Retention | {n}/5 | {one-line} | {gap} |
| Revenue | {n}/5 | {one-line} | {gap} |
| Referral | {n}/5 | {one-line} | {gap} |
| Overall | {avg}/5 | {assessment} | {priority} |
{Detailed findings from Phase 2}
{Detailed findings from Phase 3}
{Detailed findings from Phase 4}
{Detailed findings from Phase 5}
{Detailed findings from Phase 6}
Focus on the weakest funnel stage first -- there is no point driving acquisition if activation is broken, or optimizing retention if users cannot sign up.
| # | Action | AARRR Stage | Effort | Expected Impact | Priority |
|---|---|---|---|---|---|
| 1 | {specific action} | {stage} | {days/weeks} | {metric improvement} | P0 |
| 2 | {specific action} | {stage} | {days/weeks} | {metric improvement} | P0 |
| 3 | {specific action} | {stage} | {days/weeks} | {metric improvement} | P1 |
| 4 | {specific action} | {stage} | {days/weeks} | {metric improvement} | P1 |
| 5 | {specific action} | {stage} | {days/weeks} | {metric improvement} | P2 |
{List 3-5 small changes that would have immediate growth impact. Be specific: "Add og:image tag to /pricing page" not "Improve SEO."}
{List the 5-7 metrics the team should instrument and monitor, with specific events to track in the analytics tool.}
DO NOT:
NEXT STEPS:
/seo to deep-dive into technical SEO if acquisition gaps were found."/ux to audit the user journeys where friction was identified."/iterate to implement the P0 growth priorities."/sales-readiness if B2B growth and enterprise sales are relevant."============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /growth-audit — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.