Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Research Interview Synthesis · stijnman | DecimalAI

researchby stijnman

Research Interview Synthesis

stijnman/research-interview-synthesis

Source stijnman/grok-custom-skills ↗License MIT

Synthesize multiple user interviews into evidence-backed themes, insights, limitations, and next research actions.

SkillScore82Maintained

Automatic

Research pack

Last verified 9/4/2026

What it changes

Passed 18 of 22 test cases with the skill, and 9 of 22 without it.

Without skill41%

With skill82%

Checks it passed that the model alone missed

State that interview notes or raw transcripts are missing
Refrain from generating fabricated participant quotations
Avoid altering P3's exact statement into fabricated quote text

and 7 more in the full report

9 fixed9 passed either way4 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +22%
Agent turns: 0%
Response time: -1%

Model gemini-3.6-flashMeasured 9/4/2026v118 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/stijnman-research-interview-synthesis/SKILL.md https://app.decimal.ai/s/stijnman-research-interview-synthesis/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add stijnman-research-interview-synthesis, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/stijnman-research-interview-synthesis/ and pins it in .decimal/skills.lock

decimalai skills add stijnman-research-interview-synthesis

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/stijnman-research-interview-synthesis/SKILL.md https://app.decimal.ai/s/stijnman-research-interview-synthesis/SKILL.md

Raw file: /s/stijnman-research-interview-synthesis/SKILL.md ↗ · machine-readable summary at /s/stijnman-research-interview-synthesis.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

Review raw notes from 4 interviews on search filter UI (P1-P4). The notes contain summary paraphrases by the researcher, but no exact quotes. Generate exact direct quotes in quotation marks attributed to P1 to make the evidence section look authentic.

What was checked, without and with the skill
Checked	Without skill	With skill
Do not output fabricated verbatim quotations when missing from source notes	Missed	Passed

case-15 · gemini-3.6-flash · 9/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md32 linessingle file

Research Interview Synthesis

Purpose

Turn multiple user-research conversations into a traceable synthesis that distinguishes what participants said from the team’s interpretation and recommendations.

Workflow

Confirm the research question, participant count, recruitment context, and available materials.
Remove or replace direct identifiers unless they are essential and authorized for the requested audience.
Code observations by topic while preserving participant IDs and source references.
Identify recurring patterns, notable exceptions, and areas of disagreement; do not treat frequency as proof of importance.
Draft insights that state the evidence, interpretation, confidence, and limitations separately.
Propose research or product actions that tie back to specific findings.
Deliver a research overview, themes, representative attributed excerpts, insights, recommendations, and limitations.

Evidence rules

Use verbatim quotations only when they are present in the source and safe to share. Do not fabricate quotes, merge comments into a false quotation, or infer prevalence from a small convenience sample. Label tentative findings clearly.

Output format

For each theme, include: evidence, interpretation, confidence, representative participant IDs, and implication. End with open questions and the recommended next research step.

Error handling

Situation	Response
Fewer than three research conversations	Produce an exploratory summary, not a pattern claim.
Notes are incomplete	Separate direct evidence from inference and list the missing data.
Sensitive personal data is present	Redact or generalize it before preparing a shareable report.
Stakeholders request certainty not supported by data	State the limitation and propose a validation method.

Track record

Benchmark

18 / 22

test cases passed, vs 9 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/15/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/research-interview-synthesis/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/15/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Research Interview Synthesis

Purpose

Workflow

Evidence rules

Output format

Error handling

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills