skills / research

research-synthesis

what it does

Synthesize user research into themes, insights, and recommendations. Use when you have interview transcripts, survey results, usability test notes, support tickets, or NPS responses that need to be distilled into patterns, user segments, and prioritized next steps.

Verified Before and after: 2 models 1 try per case View source Download .zip

Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the skill and once without. Read both and judge for yourself.

“I ran six interviews about our expense app last week. Can you pull out the main themes and what we should do about them?”

Source material given with the request

Product: Clearclaim, a mobile app for submitting work expenses. P1 (freelance consultant): "I took a photo of a taxi receipt at night, it came out dark and the app rejected it. I gave up and typed it all in by hand." Submits once a month. P2 (sales rep): Receipt photo rejected twice in the last week. "I log mileage in a notebook and add it up on Fridays. Takes 20 minutes." P3 (CFO, 400-person company): "If you don't integrate with SAP, we're out. Non-negotiable." Did not mention receipts or approvals. P4 (field technician): "Thermal receipts get crumpled in my van and the scanner can't read them." Also says approvals are slow, so he stops submitting until month end. P5 (office manager): "I wait about nine days for my manager to approve anything." Has no issue with receipt capture. P6 (sales rep): "Half my receipt photos bounce." Tracks mileage by hand in a spreadsheet.
with the skill
## Research Synthesis: Clearclaim Expense Submission **Method:** Six interview summaries | **Participants:** 6 **Timing:** Last week | **Researcher:** Not specified ### Executive Summary Receipt-capture failures were the most common issue, reported by **4 of 6 participants**, with examples of manual re-entry and difficulty scanning damaged receipts. Slow approvals affected **2 of 6 participants**; one explicitly delayed submissions as a result. Both sales reps tracked mileage outside Clearclaim, suggesting an opportunity to simplify that workflow. SAP integration was a non-negotiable requirement for the CFO interviewed—a potentially important enterprise sales blocker, but not evidence of broad demand. ### Key Themes #### 1. Unreliable receipt capture creates extra work **Prevalence:** 4 of 6 participants: P1, P2, P4, P6. **Supporting evidence:** - “I took a photo of a taxi receipt at night, it came out dark and the app rejected it. I gave up and typed it all in by hand.” — P1 - “Thermal receipts get crumpled in my van and the scanner can't read them.” — P4 - “Half my receipt photos bounce.” — P6 - P2 reported two rejected receipt photos in the previous week. **Implication:** Capture is failing under real-world conditions, including poor lighting and damaged receipts. Failures add work and may undermine confidence in a core workflow. P5 explicitly reported no capture issues, so the problem is not universal.
Show the rest (58 more lines)
#### 2. Approval delays can discourage timely submission **Prevalence:** 2 of 6 participants: P4, P5. **Supporting evidence:** - “I wait about nine days for my manager to approve anything.” — P5 - P4 reported slow approvals and said he consequently stops submitting until month end. **Implication:** Submission friction extends beyond the employee-facing app. Clearclaim may need to help approvers act sooner, but these notes do not establish whether delays come from missing notifications, unclear ownership, workload, or company policy. #### 3. Mileage tracking happens outside Clearclaim **Prevalence:** 2 of 6 participants—both sales reps: P2, P6. **Supporting evidence:** - “I log mileage in a notebook and add it up on Fridays. Takes 20 minutes.” — P2 - P6 tracks mileage manually in a spreadsheet. **Implication:** Sales reps have an ongoing mileage workflow that Clearclaim is not currently serving effectively. The interviews do not establish whether mileage functionality is absent, hard to find, or unsuitable. #### 4. Enterprise adoption may depend on accounting integration **Prevalence:** 1 of 6 participants: P3, the CFO of a 400-person company. **Supporting evidence:** - “If you don't integrate with SAP, we're out. Non-negotiable.” — P3 **Implication:** SAP integration is a purchase gate for this prospective buyer. Its strategic importance could outweigh its low frequency in this sample, but broader demand and implementation requirements need validation. ### Insights → Opportunities *Impact and effort are preliminary hypotheses, not measured estimates.* | Insight | Opportunity | Potential impact | Effort | |---|---|---|---| | Receipt capture fails in everyday conditions | Diagnose rejection reasons; improve low-light/damaged-receipt handling; offer guided retries and a fallback that preserves entered data | High | Medium–High | | Approval delays affect reimbursement and submission behavior | Investigate the approval workflow; test reminders, aging queues, and escalation | Medium–High | Medium | | Sales reps maintain separate mileage records | Test quick mileage entry and automatic totals before investing in automated trip tracking | Medium; concentrated in sales users | Medium | | SAP is a deal-breaker for one enterprise buyer | Validate requirements and commercial demand before committing to an integration | Potentially high for enterprise sales | High, scope-dependent | ### User Needs Identified These are **overlapping needs, not validated market segments**: - **Receipt-heavy mobile workers:** Reliable capture in imperfect conditions — 4 participants. - **Employees affected by slow approvals:** Faster decisions and better status visibility — 2 participants. - **Sales reps tracking mileage:** Less manual logging and calculation — 2 participants. - **Enterprise finance buyers:** Compatibility with existing finance systems — 1 participant. ### Recommendations 1. **Prioritize receipt-failure diagnosis and recovery.** This is the broadest observed pain point. Track rejection reasons, retry success, manual-entry fallback, and completion after rejection. 2. **Investigate approval delays with managers as well as submitters.** Establish where time accumulates before choosing reminders or escalation as the solution. 3. **Prototype a lightweight mileage workflow with sales reps.** Test whether quick entry and weekly totals eliminate the notebook/spreadsheet workaround. 4. **Run SAP discovery in parallel with enterprise sales validation.** Treat it as a separate commercial decision—not automatically the lowest priority because only one participant raised it. ### Questions for Further Research - What causes receipt rejection, and which failures can users recover from? - Where do approvals stall, and what prompts managers to act? - Why are sales reps using external mileage tools? - Which SAP product, data flows, and integration requirements does the CFO need? ### Methodology Notes This synthesis uses brief summaries, not full transcripts. Counts describe only these six interviews, not the wider customer base. Participants may not have been asked identical questions; an issue not mentioned should not be interpreted as an issue not experienced.
without
## Main takeaway **Receipt capture is the clearest recurring problem.** Mileage tracking and approval delays are additional sources of friction. **SAP integration is a separate enterprise buying requirement**—mentioned only once, but explicitly a dealbreaker. These six interviews provide directional evidence, not estimates of how common each problem is across your customer base. | Theme | Evidence | What to do | |---|---|---| | **Unreliable receipt capture creates extra work** | **4 of 6 participants:** P1, P2, P4, P6. Failures include dark photos and crumpled thermal receipts. P1 reverted to manual entry; P6 said “half my receipt photos bounce.” P5 explicitly had no capture issues. | **Prioritize fixing the capture flow.** Instrument rejection rates and reasons, test against poor lighting and damaged receipts, and make recovery easier through actionable photo guidance and editable extracted fields rather than repeated rejection. | | **Mileage tracking happens outside Clearclaim** | **2 of 6:** P2 uses a notebook and spends 20 minutes totaling mileage on Fridays; P6 uses a spreadsheet. Both are sales reps. | **Validate a lightweight mileage workflow with sales users.** Test quick trip entry, automatic totals, and expense submission together. Explore automatic tracking only if further research supports it. | | **Slow approvals delay reimbursement—and submission itself** | **2 of 6:** P5 reports waiting about nine days. P4 says slow approvals cause him to stop submitting until month end. | **Investigate the approval bottleneck before choosing a fix.** Measure time at each stage and interview approvers. Test status visibility, reminders, and escalation where appropriate. Check whether these changes reduce submission batching. | | **SAP integration can block enterprise adoption** | **1 of 6:** P3, a CFO at a 400-person company, called it “non-negotiable.” | **Treat this as an enterprise qualification gate.** Clarify the required SAP workflows and validate demand
Show the rest (16 more lines)
with other enterprise buyers. If enterprise is your target, assess feasibility early; if not, don’t let one account dictate the roadmap. | ## Recommended order 1. **Fix receipt capture and recovery first.** It has the broadest support in this sample and directly undermines a core app task. 2. **Investigate approvals and prototype mileage entry in parallel.** Approval delays affect submission behavior; mileage offers a concrete time-saving opportunity for sales users. 3. **Make an explicit enterprise strategy decision about SAP.** Its priority depends on Clearclaim’s target market, not just the number of mentions. ## What to measure next - **Receipts:** first-attempt success rate, retries, manual-entry fallback, and submission completion. - **Mileage:** time spent logging and totaling trips versus users’ current methods. - **Approvals:** median and longest approval waits, plus whether users batch submissions. - **SAP:** qualified opportunities blocked and the exact integration requirements. **Avoid concluding that unmentioned problems don’t exist.** P3’s silence on receipts and approvals is not evidence of satisfaction; these interviews also don’t establish how widespread any theme is.

Answers are shown exactly as the model wrote them, from the first try, and nothing is picked by hand.

The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 1 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 1 Nov 2026

The tasks

written by Carte Blanche
biased-feature-survey

“We surveyed users about what to build next. Write up the findings for the team.”

expense-interviews

“I ran six interviews about our expense app last week. Can you pull out the main themes and what we should do about them?”

export-usability-test

“Summarize what we learned from this usability test on report export.”

nps-verbatims

“Here are last month's NPS responses. What's our score, and what's driving it?”

support-ticket-spike

“Group these support tickets and tell me what we should look at first.”

Install

Download the .zip and unzip it. Put its files, in a folder named research-synthesis, here:

Claude Code~/.claude/skills/Every project. For one project only, use .claude/skills/ inside it.
Codex~/.agents/skills/Every project. For one repository only, use .agents/skills/ inside it.
Cursor~/.cursor/skills/Cursor also reads the Claude Code and Codex folders above.

Then start a new session and ask for what the skill does. Other agents that read SKILL.md have their own skills folder; check their docs.

Coming after launch: get skills from inside your agent, no download needed.