
Startup Metrics Framework
Guides the agent to define, calculate and benchmark startup KPIs like CAC, LTV and burn multiple
- Repository
- wshobson/agents
- Stars
- 42,095
- Licence
- MIT
- Files
- 2 files
What it does
Once installed, the agent answers startup metrics questions using a built-in reference of formulas and rough benchmarks for marketplace, consumer, B2B and SaaS businesses from seed through Series A. It can explain how to calculate metrics such as CAC, LTV, burn multiple, retention, take rate and pipeline coverage, suggest which 5-7 metrics to track at a given stage, and format a metrics dashboard for investors or a board update. It works from written guidance and the numbers you give it; it does not connect to your data.
Great for
- Founders at pre-seed to Series A who want a starting set of metrics and benchmarks
- Analysts or operators preparing an investor or board metrics dashboard
- Students learning SaaS and startup unit economics
Skip it if
- Final investor-grade financials or valuation: the benchmarks are generic rules of thumb and may not fit your market, and the agent does not verify your inputs
- Regulated or audited reporting, where a qualified accountant should review the numbers
Try asking
- “Define a metrics framework for my seed-stage B2B SaaS startup”
- “Calculate our CAC, LTV and burn multiple from these figures and tell me how we compare to benchmarks”
- “Build a monthly investor dashboard from our MRR, churn and runway numbers”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 2 original files, the MIT licence and an attribution note.
startup-metrics-framework.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip startup-metrics-framework.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip startup-metrics-framework.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Give the agent your actual figures (MRR, customer counts, spend, churn) so it calculates rather than guesses
- Ask which metrics matter for your business model and stage, since the skill says not to over-track early on
- Treat the benchmark ranges as starting points and check them against your sector's data
What's inside
- references/universal-and-saas-metrics.md
- SKILL.md
Redistributed unmodified from wshobson/agents under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.