Saas spend optimizer
Skill sisodiabhumca/agent-skills/skills/saas-spend-optimizer
Production-Ready Agent Skills : product analytics, growth experiments, CRM, research synthesis, postmortems, data contracts, SaaS spend, compliance, architecture maps, and LLM eval and many more.
npx -y skills add sisodiabhumca/agent-skills --skill saas-spend-optimizerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 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
Use to analyze SaaS billing/usage exports (Zuora, Stripe, vendor invoices) and surface optimization opportunities — unused seats, duplicate tools, over-provisioned tiers, autorenewals coming up, and ARR-at-risk.
SKILL.md
1.5 KB, as published. Nobody here has run it
SaaS Spend Optimizer
When to invoke
- "Find waste in our SaaS stack."
- "Which renewals are coming up in the next 60 days?"
- "What seats are unused?"
Inputs needed
- Subscriptions CSV — vendor, plan, seats, cost_monthly, renewal_date.
- Usage CSV (optional but recommended) — vendor, user, last_active.
- Org headcount (for benchmarking).
Workflow
- Ingest subs + usage.
- Compute seat utilization, $/active user, autorenewal calendar.
- Classify waste types: unused seats, dead tools, duplicates by category.
- Estimate savings — annualized.
- Report with actions: cancel, downgrade, consolidate, renegotiate.
Output format
## Top savings opportunities
- $X/yr — vendor — action — owner
## Renewal calendar (next 90 days)
- date — vendor — amount — action by date
## Duplicates by category
- category — vendors — recommendation
Guardrails
- Always show the underlying counts, not just %.
- Flag low-confidence (no usage data) recommendations as such.
- Do NOT recommend cancellation of vendors with active integrations marked critical.
Reference code
optimize.py reads CSVs and emits a Markdown brief plus a JSON summary.