discovery-research-synthesis
Turning research artifacts into actionable PM insight. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the decisions they are meant to inform. The discipline of moving from raw discovery data to clear product direction without losing signal in the synthesis or fabricating insight that was not actually there. Triggers on research synthesis, customer interview synthesis, user research analysis, discovery readout, research insights, sales call analysis, support ticket analysis, qualitative data analysis.
Profile →npx skills add rampstackco/claude-skills --skill discovery-research-synthesis --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.
What it does
Turns a batch of discovery artifacts into decision-ready product insights by tagging artifacts, clustering into patterns, naming those patterns, inferring product implications, and articulating the specific decisions they inform. It emphasizes moving beyond raw data to actionable synthesis that can drive roadmaps and specs.
How it works
The skill outlines a six-stage synthesis sequence: 1) Transcribe and prepare artifacts into a synthesizable format; 2) Tag at the artifact level with topics and quotes; 3) Cluster tags across artifacts into themes; 4) Name patterns that capture the behavior revealed by the data; 5) Infer product implications for each pattern; 6) Name the so-what, mapping implications to concrete decisions. It stresses avoiding data-dump and insight-theater and requires that patterns include explicit, decision-facing implications and so-what decisions.
Additionally, it defines three synthesis outcomes: data-dump (no synthesis), insight-theater (overly polished but not decision-driven), and actionable-synthesis (decision-grade, referenced in roadmap discussions and specs). It describes research types (interviews, support tickets, sales calls, surveys, in-app feedback) and emphasizes documenting decisions, not just decks, with a focus on decision-input sections.
When to use it
Use when synthesizing a recent batch of customer interviews, auditing why prior research hasn’t produced decisions, designing synthesis output for a multi-week discovery sprint, or establishing synthesis discipline within a team lacking it.
What it can touch
Tools listed: claude-code. The process requires transforming raw artifacts into tagged data, clustering patterns, and deriving decision inputs; the output is a synthesized document with pattern sections, each including evidence summary, implications, and the so-what decision input.
Caveats
The skill cautions against skipping stages (data-dump or insight-theater) and mandates that implications be actionable and falsifiable. It positions the synthesis as a bridge from observation to decision and specifies that the final output should be decision-oriented rather than deck-centric. License and other non-technical constraints are not stated beyond tool and process guidance; no explicit limitations beyond adhering to the six-stage sequence.
# Discovery Research Synthesis A senior PM's playbook for turning research artifacts into decisions. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the product direction they are meant to inform. Most discovery research never produces decisions. The team conducts interviews; the transcripts pile up; a researcher hands product the raw artifacts (data-dump) or builds a polished readout deck (insight-theater); the deck gets a 30-minute review meeting and is never referenced again. Two months later the team is making the same product decisions that the research was supposed to inform, with the same gut-feel inputs the research was supposed to displace. The discipline is in the synthesis. Synthesis is where research earns its keep: where transcripts become tagged observations, observations cluster into patterns, patterns get named, named patterns surface product implications, and implications drive specific decisions. Without that sequence, research is performance art. This skill covers one-off discovery research projects: a 12-week customer development sprint, a sales-call review for an onboar
- What this skill is for
- Data-dump vs insight-theater vs actionable-synthesis
- Discovery research types
- The synthesis sequence
- Tagging and clustering discipline
- Pattern naming
- From pattern to product implication
- Writing for decisions, not deck performance
- The synthesis review and validation loop
- When to halt and gather more data
- Common failure modes
- The framework: 12 considerations for discovery synthesis
- Reference files
- Closing: synthesis is where research earns its keep
What does the discovery-research-synthesis skill do?
Turning research artifacts into actionable PM insight. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the decisions they are meant to inform. The discipline of moving from raw discovery data to clear product direction without losing signal in the synthesis or fabricating insight that was not actually there. Triggers on research synthesis, customer interview synthesis, user research analysis, discovery readout, research insights, sales call analysis, support ticket analysis, qualitative data analysis.
How do I install it?
Run `npx skills add rampstackco/claude-skills --skill discovery-research-synthesis --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 rampstackco/claude-skills, a repository with 515 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.