Index of every page on this site: llms.txt
All skills
deanpeters avatar

/research-synthesis

@476ae12
Run it yourself

Turn raw interview notes and feedback into themes, insights, and opportunity statements. Use when you have a pile of research and need to know what it says before deciding anything.

Use this Skill: https://skilld.dev/gh/deanpeters/product-manager-skills/research-synthesis

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

examplessample-industrial.md

≈581 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Research Synthesis Example: Industrial

Research: notes from 6 plant visits and 3 phone calls with maintenance engineers (Northfield Automation) Question: what stops plants from replacing aging controllers, even when parts are scarce? Hypothesis going in: "It's the price."

Why this example exists: industrial research is smaller and slower, so strength of signal and sampling honesty matter more. It also shows two sources disagreeing.


## Research frame
9 sources (6 on-site, 3 calls), recruited through 3 partners, so skewed to partner-served plants.
Hypothesis held: price blocks replacement. [FROM YOU]

## Themes
| Theme | Sources | N |
|---|---|---|
| "We can't give up a weekend of production" | V1, V2, V4, V5, V6, C2 | 6 of 9 |
| "Nobody else understands our program" | V1, V3, V5, C1, C3 | 5 of 9 |
| Price mentioned as the main blocker | V6 | 1 of 9 |

## Insights
| # | Insight | Evidence | N | Confidence |
|---|---|---|---|---|
| 1 | The barrier is downtime and program risk, not price | V1 "...a weekend we don't have"; V5 "...one engineer knows that code" | 6 and 5 of 9 | Suggestive (partner-skewed sample) |

## Opportunity statements
| # | "I need to..." | From | Ideas heard |
|---|---|---|---|
| 1 | "...swap the controller inside a shift we already have." | 1 | "Pre-wire the bracket" (V4) |
| 2 | "...keep my existing program working without rewriting it." | 1 | "Import tool" (C1) |

## Contradictions
V6, the only plant citing price, runs the oldest controllers and is nearest to failure.
Price may matter once downtime is already unavoidable. That's a hypothesis, not a finding.
The partner calls (C1-C3) were more technical than the on-site visits: partners may see program
risk more than plant managers do.

## What the research does not show
- No procurement or finance interviews (price may live there)
- No plants that already replaced their controllers (the opposite case)
- Sample came through partners, so direct-served plants are unrepresented

What to learn from this

  • The team's hypothesis was mostly absent from the data, and the skill said so plainly.
  • One outlier was kept, not dismissed, with a hypothesis for why it differs.
  • The gaps list names who holds the price story (procurement), so the next round targets them.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning7d3 checks · Risk SAFE
  • Gen Agent Trust Hub7d

    The skill provides a structured workflow for research synthesis but possesses an inherent attack surface for indirect prompt injection due to the processing of untrusted external research data.

  • Socket7d

    No alerts

  • Snyk7d

    Risk: MEDIUM · 1 issue

Signed by skilld at 476ae12. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated last week
argument-hint
[the research you have: interview notes, tickets, survey comments]
type
workflow
theme
discovery-research
Other metadata
intent
Take research that is still raw (interview notes, call transcripts, tickets, survey comments) and walk it through coding, affinity grouping, insight writing, and opportunity framing, with every insight traced to the notes behind it and every claim sized by how many people said it. Ends with opportunity statements ready for an opportunity solution tree, and a list of what the research does not show.
best_for
[
  "Making sense of 5 to 30 interviews before anyone proposes a solution",
  "Separating what customers did and said from what the team concluded",
  "Producing opportunity statements that trace back to evidence",
  "Showing a stakeholder what the research does and does not support"
]
scenarios
[
  "I ran eight dispatcher interviews and have a folder of notes. What do they say?",
  "Support tickets and interviews seem to disagree. Help me sort what's real",
  "Turn these plant-visit notes into opportunities for the roadmap discussion",
  "Leadership wants the insight in one page; I want it traceable"
]
estimated_time
45-90 min

README badge

README badge for deanpeters/product-manager-skills/research-synthesis