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.md

≈641 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Research Synthesis Example: SaaS

Research: 8 dispatcher interviews at Fieldlight customers (service companies, 50-300 technicians) Question: why do rescheduled days still go wrong? Hypothesis going in: "Dispatchers need smarter auto-scheduling" (the team's belief)

Why this example exists: the hypothesis was a solution. The synthesis shows the need underneath it, and one contradiction that changed the insight.


## Research frame
Participants: 8 dispatchers, recruited from customer accounts by CS (so possibly friendlier than
average). Hypothesis held: smarter auto-scheduling is the answer. [FROM YOU]

## Coded observations (excerpt)
| # | P | Observation | Unprompted | Contradicts hypothesis |
|---|---|---|---|---|
| 14 | P3 | "I print the schedule and rebuild it in a spreadsheet at 2 p.m." | Yes | No |
| 22 | P5 | "The auto-schedule is fine. I can't tell which jobs I'm allowed to move." | Yes | **Yes** |
| 31 | P7 | "I don't trust the board once a rush call lands." | Yes | No |

## Themes
| Theme | Participants | N |
|---|---|---|
| The 2 p.m. rebuild | P1, P3, P4, P5, P7, P8 | 6 of 8 |
| Can't see what's movable | P2, P5, P6, P7 | 4 of 8 |
| Calling customers to renegotiate | P1, P4, P6 | 3 of 8 |

## Insights
| # | Insight | Evidence | N | Confidence |
|---|---|---|---|---|
| 1 | Dispatchers rebuild the day by hand not because the schedule is poor, but because they can't see which jobs are safe to move | Obs 14, 22, 31 | 4-6 of 8 | Suggestive (CS-recruited sample) |

## Opportunity statements
| # | "I need to..." | From | Ideas heard |
|---|---|---|---|
| 1 | "...know which jobs I can move without calling the customer." | 1 | "Color-code flexible jobs" (P2) |
| 2 | "...trust the plan after a rush call lands." | 1 | none |

## Contradictions
Obs 22 (P5): the auto-schedule is fine. It cuts against the hypothesis that scheduling quality is
the problem. It **changed** the insight from "better scheduling" to "visibility of flexibility."

## What the research does not show
- No dispatchers from companies under 50 technicians
- Recruited by CS, so likely engaged customers; unhappy accounts missing
- "Movable" job rules rest on P5 and P7 only; ask others what makes a job movable

What to learn from this

  • The contradiction was the finding. P5's remark turned a scheduling story into a visibility story.
  • Counts, not percentages. "6 of 8" says what was true of these eight people.
  • The solution (P2's color-coding) was kept, not buried, and kept out of the opportunity.

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