Files
skills/reference/templates/reports/cro-report-template.md
zeekayandHanzo Dev 65c3b27843 160 marketing, growth and PM skills, on our own connectors
Four MIT collections ported — growthOS, openclaw-marketing-skills,
Marketing-Skills and pm-skills — as 160 skills, 12 agents and 45
commands, each naming its origin in its own frontmatter so the tree can
be checked against THIRD_PARTY_NOTICES rather than trusted. Sixteen names
appeared in more than one collection and none of the copies were
identical; the longest wins, which lands on the more developed text where
they genuinely diverge.

A fifth collection is deliberately absent. awesome-growth-hacking-skills
carries NO licence, which leaves its author every right by default — and
it is a list of links rather than a collection of skills, so there is
nothing in it to port and no permission to port it with. It is cited as a
directory to read.

THE CONNECTOR SKILLS ARE REWRITTEN, not ported. They arrived installing
vendor SDKs, running OAuth flows of their own, and ending with long-lived
credentials in JSON files under .agents/ and ~/.growthos/ at mode 600.
That is a secret on a disk with no rotation path, protected from other
users and not from the agent — and one auth implementation per skill.
Hanzo holds these connectors in Go, per user, sealed in KMS, so `connect`
is the one home for the flow and the platform skills defer to it by
provider id: google_ads, meta_ads, x. It is reachable as HTTP or as MCP
tools at api.hanzo.ai/v1/mcp — the same routes, typed once in Go, so a
tool and a curl cannot disagree.

Two had nothing real behind them and now say so. There is no
search_console provider, so that skill names what does answer the same
questions (google_analytics, google_bigquery) and states that the remedy
is a provider in hanzoai/cloud rather than a vendor SDK here. And
getxapi-connect was a wrapper around a paid reseller of X's public data
with the vendor's key in an env var; it is `listen` now, on our own x
connector — a skill named after a vendor makes the vendor the capability
and dies with it.

The skills referenced paths that only existed inside the source repo, so
the shared material they read is ported to reference/ and the paths
rewritten. Three skills need the growthOS APPLICATION rather than its
data; per the estate's own split an application belongs in hanzoai/ads,
social, email or sms as a cloud plugin, so those three say what they need
instead of carrying an import that resolves to nothing.

Third-party product names are out of our prose and kept in the notices,
which is where the licence requires them and the only place they belong.
A skill's persona names a role, not somebody else's product.


Co-authored-by: Hanzo Dev <[email protected]>
2026-09-15 01:27:26 -07:00

6.4 KiB

CRO Report: [Page/Funnel Name]

Metadata

Field Value
Report ID CRO-[NNN]
Analysis Date [ISO 8601]
Analyst Growth Engineer
Page/Funnel [URL or funnel name]
Funnel Goal [Ultimate conversion action]
Baseline Conversion Rate [current rate or unknown]

Executive Summary

[2-3 sentences: what was analyzed, key findings, and the expected impact of top recommendations]


Funnel Definition

Stages

# Stage Description URL Pattern Success Action
1 [name] [description] [url] [action to proceed]
2 [name] [description] [url] [action to proceed]
3 [name] [description] [url] [action to proceed]
4 [name] [description] [url] [final conversion]

Funnel Visualization

[Stage 1] ──── [Stage 2] ──── [Stage 3] ──── [Stage 4]
  100%           ??%            ??%            ??%
         -??%           -??%           -??%

Drop-Off Analysis

Stage Metrics

Stage Traffic Conv. to Next Drop-Off Rate Severity
[Stage 1] [n] [%] [%] [critical/high/medium/low]
[Stage 2] [n] [%] [%] [critical/high/medium/low]
[Stage 3] [n] [%] [%] [critical/high/medium/low]

Severity thresholds: >80% = Critical | 60-80% = High | 40-60% = Medium | <40% = Low

Identified Drop-Off Causes

[Stage A] to [Stage B] — [drop-off %] drop-off ([severity])

# Cause Evidence Affected Segment
1 [friction point] [data or heuristic] [all / mobile / new users]
2 [friction point] [data or heuristic] [segment]

[Stage B] to [Stage C] — [drop-off %] drop-off ([severity])

# Cause Evidence Affected Segment
1 [friction point] [data or heuristic] [segment]

CRO Audit Checklist

Above the Fold

  • Clear value proposition visible immediately
  • Single primary CTA (no competing actions)
  • CTA visible without scrolling
  • Headline is benefit-focused

Trust & Proof

  • Social proof present and specific
  • Risk reversal stated
  • Trust badges or security indicators present

Content & Copy

  • Copy is scannable (short paragraphs, bullets)
  • Benefits > features ratio
  • Anti-slop compliant
  • Urgency/scarcity used appropriately

Technical Performance

  • Page loads in <2s (LCP)
  • No layout shifts (CLS < 0.1)
  • Mobile responsive and thumb-friendly
  • Images optimized

Conversion Architecture

  • Single clear conversion path
  • Form fields minimized
  • Error states are helpful
  • Success state confirms action

Recommendations (ICE-Scored)

ICE Scoring Reference

Score Impact Confidence Ease
10 Transforms the metric Proven by data/research Minutes to implement
7-9 Major improvement Strong evidence Hours to implement
4-6 Moderate improvement Some evidence Days to implement
1-3 Minor improvement Gut feeling Weeks to implement

Formula: ICE Total = Impact x Confidence x Ease (max 1000)

Priority Recommendations (Top 5, sorted by ICE)

#1: [Title] — ICE: [total]

Dimension Score Rationale
Impact [1-10] [why this score]
Confidence [1-10] [evidence level]
Ease [1-10] [implementation effort]
ICE Total [I x C x E]
  • Stage: [which funnel stage]
  • Drop-off cause: [which identified cause]
  • Change: [specific change to implement]
  • Expected improvement: [e.g., +15% conversion at this stage]
  • Test plan: [how to validate — usually A/B test]

#2: [Title] — ICE: [total]

Dimension Score Rationale
Impact [1-10] [why]
Confidence [1-10] [evidence]
Ease [1-10] [effort]
ICE Total [I x C x E]
  • Stage: [stage]
  • Drop-off cause: [cause]
  • Change: [change]
  • Expected improvement: [estimate]
  • Test plan: [validation approach]

#3-5: [Repeat pattern above]


Action Plan

Quick Wins (ICE Ease >= 8)

# Recommendation ICE Total Next Step Owner Deadline
1 [title] [score] [action] [who] [when]

Test Queue (requires A/B testing)

# Recommendation ICE Total Test Design Est. Duration
1 [title] [score] [control vs variant] [days]

Backlog (lower priority)

# Recommendation ICE Total Reason for Deferral
1 [title] [score] [why not now]

Success Metrics

Metric Baseline Target Measurement Period
Overall funnel conversion [current] [target] [timeframe]
[Stage X] conversion [current] [target] [timeframe]
[Key metric] [current] [target] [timeframe]

YAML Schema Reference

funnel_analysis:
  funnel_name: "[name]"
  analysis_date: "[ISO 8601]"
  total_entry_traffic: "[number]"
  stages:
    - name: "[stage name]"
      traffic: "[visitors]"
      conversion_to_next: "[percentage]"
      drop_off_rate: "[percentage]"
  drop_offs:
    - stage_transition: "[Stage A -> Stage B]"
      drop_off_rate: "[percentage]"
      severity: "[critical | high | medium | low]"
      identified_causes:
        - cause: "[friction point]"
          evidence: "[data or heuristic]"
          affected_segment: "[all | mobile | new_users]"
  recommendations:
    - id: "REC-001"
      title: "[title]"
      stage: "[funnel stage]"
      drop_off_cause: "[cause]"
      change_description: "[what to change]"
      ice_score:
        impact: "[1-10]"
        confidence: "[1-10]"
        ease: "[1-10]"
        total: "[I x C x E]"
      expected_improvement: "[estimate]"
      implementation_effort: "[hours/days]"
      test_plan: "[validation approach]"
  action_plan:
    quick_wins: []
    test_queue: []
    backlog: []
  success_metrics:
    - metric: "[name]"
      baseline: "[current]"
      target: "[goal]"
      measurement_period: "[timeframe]"