ericrisco/rsc-harness / skills/customer-research
customer-research
VerifiedUse when buyer interviews, reviews or lost deals need to become sourced needs, objections and language for an offer, or when that evidence is missing. Separates segments, repeated sources and inference. NOT market sizing (that is `market-research`) or page copy (that is `landing-copy`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.3 KB |
| evals/README.md | markdown | 2.4 KB |
| evals/cases.yaml | config | 4.5 KB |
evals/cases.yaml
View on GitHubskill: customer-research
should_trigger:
- prompt: "Find the objections we should answer using these customer interviews."
why: "Extracts buyer evidence before writing copy."
- prompt: "Our landing sounds like us, but nothing like the reviews. What are buyers actually asking for?"
why: "A language mismatch calls for sourced customer understanding."
- prompt: "Compara las llamadas de quienes compraron y quienes se fueron sin comprar."
why: "Spanish symptom asks for segmented decision evidence."
- prompt: "Build a quote bank from these support tickets without treating repeat tickets as different customers."
why: "Needs provenance and unit-of-analysis discipline."
- prompt: "We have no interviews yet. Plan how to learn why people postpone buying this course."
why: "Defines a decision-focused research plan when evidence is absent."
should_not_trigger:
- prompt: "Estimate the addressable market for bookkeeping software in Spain."
route_to: market-research
why: "Market size and segmentation are not buyer-language synthesis."
- prompt: "Rewrite this landing headline using the approved customer quote bank."
route_to: landing-copy
why: "Research is already supplied; this asks for page copy."
- prompt: "Track the prices of these three competitors every month."
route_to: competitor-watch
why: "Recurring rival monitoring has its own owner."
- prompt: "Find twenty named companies and contacts to sell this service to."
route_to: lead-gen
why: "Prospecting produces an outreach list rather than research findings."
capability:
- scenario: |
Produce a buyer-research brief for a new landing for LedgerBridge, a bookkeeping migration service. Work only from the material below; no browsing or outreach. Identify which message to test first, show the evidence behind it, and propose the smallest follow-up that could change your recommendation. This is a draft for the copywriter, not public copy.
Sources (all collected in October 2026):
A: Interview with an owner at firm O1 (4 staff, bought): "I didn't need more charts. I needed Friday back." They switched after spending their weekend correcting an import. Private interview; publication permission not requested.
B: Support ticket from the same owner at O1: "We spent another Saturday fixing mappings." Same migration as A. Internal use only.
C: Public review by O1's owner reposting A verbatim on a review site. No permission to use their name or logo in marketing has been obtained.
D: Interview with O2 (6 staff, bought): "Show me the exceptions before anything goes live." They chose the service after a preview of records needing review. Private; internal analysis permitted, public quotation not permitted.
E: Lost-deal note for O3 (90 staff): buyer said "Our security team needs a self-hosted option." They declined the cloud-only service. Salesperson wrote "too expensive" in the CRM category, but recorded no price objection in the call notes.
F: Interview with O4 (120 staff, bought): "The approval trail mattered more than speed." Procurement required an audit trail; the product included one.
G: Anonymous forum comment, organization and date unknown: "All migrations destroy your history." No product named.
Founder assertion: "Everyone wants the fastest migration; three customers already said so."
must_include:
- "Counts A/B/C as one organization and one related episode, not three independent customer confirmations; states the four identifiable organizations and unknown G separately."
- "Keeps small firms O1/O2 separate from larger O3/O4 and avoids presenting one universal persona or market-wide frequency."
- "Treats the O3 price category as an unsupported interpretation conflicting with the recorded self-hosting objection, preserving both provenance and uncertainty."
- "Preserves exact buyer wording with source identifiers and distinguishes observed statements from inferred themes; does not turn Friday back into a measured time-saving claim."
- "Makes a bounded initial message hypothesis for a named segment and cites both supporting and limiting evidence rather than accepting the founder's speed consensus."
- "Keeps private/internal quotations out of publishable proof and marks public review reuse permissions as unconfirmed rather than assuming public visibility grants promotional consent."
- "Proposes a small, decision-changing follow-up comparing the competing explanations with relevant buyers, without sending outreach or treating absent evidence as a positive finding."
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |