Cro review
Skill sinhoneyy/master-skills/plugins/master-skills-ai-agent-builder/skills/cro-review
Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains
npx -y skills add sinhoneyy/master-skills --skill cro-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
/cs:cro-review <plan> — Pipeline-paranoid interrogation of revenue, win rate, NRR, and ramp time. Use when the forecast misses pipeline coverage, win rates drop, or before scaling the sales team.
SKILL.md
3.0 KB, as published. Nobody here has run it
/cs:cro-review — CRO Forcing Questions
Command: /cs:cro-review <plan>
The pipeline-paranoid operator pressure-tests revenue assumptions. Six questions that surface next-quarter pain this quarter.
When to Run
- Before committing to a quarterly revenue target
- Before changing sales motion (PLG ↔ sales-led, mid-market ↔ enterprise)
- Before hiring a batch of reps
- When pipeline coverage drops below 3x
- When NRR is trending down
The Six CRO Questions
1. Pipeline Coverage
What is pipeline coverage for the current quarter, by stage?
- Inbound-heavy: 3x. Outbound-heavy: 4x. Below either threshold = act now.
- Stage-weighted, not just total.
2. Win Rate Trajectory
What's win rate this quarter vs the last 4 — and what's the leak point?
- Stage-by-stage conversion.
- If a single stage softens, identify why before forecasting.
3. NRR Decomposition
What's gross retention, contraction, and expansion separately?
- NRR alone hides churn.
- A 110% NRR with 95% gross retention is different from 110% with 80%.
4. Ramp Time
For the last 4 hires, how many days to first deal and to quota?
- If ramp > 90 days at growth stage, hiring profile or enablement is broken.
- Forecasted hires must build in ramp.
5. Discount Discipline
What's the median discount this quarter vs last 4? Where is it creeping?
- Discount creep is the leading indicator of pricing or positioning weakness.
- Cap discounts by approver tier.
6. Pipeline Source Mix
What % of pipeline is marketing-sourced, sales-sourced, partner-sourced?
- If one source dominates > 80%, you have concentration risk.
- Cross-check with cs-cmo-advisor.
Workflow
python ../../../skills/cro-advisor/scripts/revenue_forecast_model.py
python ../../../skills/cro-advisor/scripts/churn_analyzer.py
Output Format
# CRO Review: <plan>
**Date:** YYYY-MM-DD
## Pipeline
- Coverage: X.Xx (target 3x+)
- Win rate: X% (4Q trend: ↑ / → / ↓)
- Top leaking stage: <name>
## Retention
- Gross retention: X%
- NRR: X%
- Expansion: X%
- Contraction: X%
## Ramp
- New hires last quarter: N
- Median days to first deal: X
- Median days to quota: X
## Discount
- Median discount this quarter: X%
- Trend vs 4Q ago: <delta>
## Source Mix
- Marketing: X% | Sales: X% | Partner: X%
## Verdict
🟢 ON PLAN | 🟡 GAP | 🔴 PIPELINE CRISIS
## Next Steps
[3 concrete actions]
Routing
/cs:cfo-review— does this hit the cash plan?/cs:cmo-review— is pipeline source-mix healthy?/cs:execute— quarterly plan if GREEN/cs:boardroom— if RED
Related
- Agent:
cs-cro-advisor - Skill:
cro-advisor - Execution:
../../../../business-growth/
Version: 1.0.0
Gives 0 of the 12 instructions most review quality skills give
Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-06
- ask questions one at a timein 82 of 1048, across 54 files
- provide a recommended answer for each questionin 73 of 1048, across 45 files
- explore the codebase instead of asking answerable questionsin 66 of 1048, across 37 files
- resolve dependencies between decisions one-by-onein 42 of 1048, across 15 files
- interview the user relentlessly about the planin 39 of 1048, across 12 files
- order findings by severityin 29 of 1048
- resolve each branch of the decision treein 28 of 1048, across 5 files
- run a grilling sessionin 26 of 1048, across 5 files
- update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 9 files
- propose precise canonical terms for vague languagein 25 of 1048, across 6 files
- create documentation files lazilyin 24 of 1048, across 5 files
- use the domain-modeling skillin 22 of 1048, across 3 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.