Install any skill in seconds. Free to start, no credit card required.
Get Started Free →coco-research/pmstudio-dr
Generate a Disaster Recovery plan with RTO/RPO targets.
Passed 17 of 20 test cases with the skill, and 9 of 20 without it.
and 6 more in the full report
9 fixed10 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
What final item must be appended to each recovery scenario in section 5 to confirm systems are fully restored to normal operations?
| Checked | Without skill | With skill |
|---|---|---|
| Requires a verification checklist at the end of each recovery scenario. | Missed | Passed |
The instructions your model reads when the skill loads.
Generates a Disaster Recovery plan scoped to a specific product. For SaaS products (where the vendor owns infrastructure), this plan focuses on what Coco Inc controls: data exports, integration failover, access recovery, communication, and business continuity.
Read all that exist:
CLAUDE.local.md — architecture, integrations, vendor info, data strategyPRD/*.html or PRD/*.md — NFRs, technical considerations, integrations, data architectureArchitecture/ — system diagrams, data flowsOperational/IRP-*.html — incident response plan (if exists, reference for communication)From context, classify the product:
| Type | DR Focus | Example |
|---|---|---|
| SaaS (customer) | Vendor dependency, data portability, alternative workflows | (third-party SaaS) |
| Self-hosted | Infrastructure recovery, backup/restore, failover | Custom app on EKS |
| Hybrid | Both vendor and self-hosted components | SaaS + custom middleware |
Adjust the plan scope accordingly. For SaaS, skip infrastructure sections (that's the vendor's problem). Add vendor SLA and data portability sections.
Only ask what can't be inferred:
test cases passed, vs 9 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.