synthesize-research
Synthesize interview notes, feedback, and transcripts into themed research findings with JTBD statements when the user asks to analyze research, synthesize interviews, or make sense of qualitative data
npx skills add majiayu000/claude-skill-registry --skill synthesize-research --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Synthesize Research ## Overview Perform thematic analysis across multiple qualitative research sources — interview notes, user feedback, support transcripts, survey responses — to produce a structured synthesis with verbatim quotes, themed clusters, JTBD statements, contradictions, and actionable recommendations. This skill turns messy qualitative data into a decision-ready document. ## Workflow 1. **Read product context** — Load `.chalk/docs/product/0_product_profile.md` and any existing JTBD canvases or prior research syntheses. These provide the lens for interpreting new data: existing personas, known jobs, and previously identified themes. If no context exists, note this and proceed without assumptions. 2. **Locate source files** — Parse `$ARGUMENTS` to identify the research inputs. These may be: - Direct file paths or glob patterns (e.g., `.chalk/docs/research/*.md`) - A folder to scan (e.g., `.chalk/docs/research/`) - A list of file names Read all source files. If fewer than 3 sources are provided, warn the user that synthesis from limited sources carries high bias risk. If no files are found, ask the user to provide paths. 3. **Extract verbatim quotes** — Read each source
- Overview
- Workflow
- Synthesis Structure
- Output
- Anti-patterns
What does the synthesize-research skill do?
Synthesize interview notes, feedback, and transcripts into themed research findings with JTBD statements when the user asks to analyze research, synthesize interviews, or make sense of qualitative data
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill synthesize-research --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.