agentleFS
jhy0285jhy0285/monofield/skills/research-decision-room/SKILL.md

research-decision-room

Skill6 starsChanged 6 months agoApache-2.0View on GitHub

Turn messy user research notes, interviews, support tickets, surveys, and product context into an evidence-backed decision room: a single HTML artifact with an evidence ledger, theme map, confidence heatmap, opportunity matrix, decision memo, and experiment queue. Use when teams need to move from qualitative signals to product or design decisions without fabricating certainty.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 12 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a single-page HTML decision artifact that helps a product or design team turn messy evidence into a clear next move.

    line 49
  2. Very specific:

    Read references/evidence-model.md before synthesis and run references/checklist.md before emitting the artifact.

    line 65
  3. Distinctive:

    Use this skill when the user has any mix of:

    line 70
  4. Distinctive:

    Do not use it for pure visual inspiration, campaign ideation, or brand moodboards.

    line 81
  5. Distinctive:

    Write a short frame with:

    line 90
  6. Distinctive:

    If key context is missing and the task is not blocked, proceed with labelled assumptions instead of asking a broad question.

    line 98
  7. Distinctive:

    Never invent quotes, participant counts, dates, revenue impact, or metrics.

    line 117
  8. Distinctive:

    Prefer verbs over nouns: "Teams abandon setup when the first blank state asks for too much" is better than "Onboarding problem".

    line 131
  9. Distinctive:

    Create an opportunity matrix with 3 to 5 options.

    line 136
  10. Distinctive:

    Write a decision memo with:

    line 149
  11. Distinctive:

    Keep the memo short enough to read in under one minute.

    line 158
  12. Distinctive:

    No framework dependency is required.

    line 177
  13. Distinctive:

    Run the checklist. Then emit one concise orientation sentence and one HTML artifact:

    line 181

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research Decision Room Skill

Create a single-page HTML decision artifact that helps a product or design team turn messy evidence into a clear next move. The output is not a decorative research deck. It is a working room for debate: evidence, themes, confidence, tradeoffs, and recommended experiments stay visible together.

Resource map

research-decision-room/
├── SKILL.md
├── example.html
└── references/
    ├── checklist.md
    └── evidence-model.md

Read references/evidence-model.md before synthesis and run references/checklist.md before emitting the artifact.

When to use this skill

Use this skill when the user has any mix of:

  • Interview notes, usability-test observations, support tickets, sales call notes, app-store reviews, NPS comments, survey open text, analytics snippets, or product-decision context.
  • A decision that needs evidence: "Should we build X?", "Which onboarding path should we try?", "Why are users dropping off?", "What do customers actually mean by slow?"
  • A need to share findings with stakeholders who will not read a long research report.

Do not use it for pure visual inspiration, campaign ideation, or brand moodboards.

Workflow

Step 1 - Establish the decision frame

Identify the decision scope from the user's prompt. If the user did not give a decision, derive one from the evidence and label it as inferred.

Write a short frame with:

  • Decision question.
  • Audience or segment.
  • Time horizon.
  • Known constraints.
  • What this artifact will not decide.

If key context is missing and the task is not blocked, proceed with labelled assumptions instead of asking a broad question.

Step 2 - Build the evidence ledger

Normalize every useful signal into ledger rows using the model in references/evidence-model.md.

Each ledger row must include:

  • id: short stable id, such as I-03, T-14, M-02.
  • source_type: interview, usability, support, survey, analytics, sales, field note, or stakeholder.
  • segment: user type or "unknown".
  • signal: one-sentence observation.
  • quote_or_metric: direct quote, metric, or "not provided".
  • strength: strong, medium, or weak.
  • limitations: why this evidence may be biased or incomplete.

Never invent quotes, participant counts, dates, revenue impact, or metrics. If the user did not provide a number, use "not provided" and explain what evidence would increase confidence.

Step 3 - Synthesize themes and tensions

Cluster evidence into 4 to 6 themes. For each theme:

  • Name the theme in plain human language.
  • List the evidence ids that support it.
  • Explain the behavior behind it, not just the UI complaint.
  • Mark confidence as high, medium, or low.
  • Note contradictions or segment differences.

Prefer verbs over nouns: "Teams abandon setup when the first blank state asks for too much" is better than "Onboarding problem".

Step 4 - Score opportunities

Create an opportunity matrix with 3 to 5 options. Score each option on a 1 to 5 scale:

  • Evidence strength.
  • User pain.
  • Business leverage.
  • Implementation risk, where 5 means low risk and 1 means high risk.

Show the total score, but do not let the score replace judgment. Add one sentence on why the top recommendation wins.

Step 5 - Draft the decision memo

Write a decision memo with:

  1. Recommended move.
  2. Why now.
  3. What evidence supports it.
  4. What could be wrong.
  5. What to measure next.
  6. Reversible next step.

Keep the memo short enough to read in under one minute.

Step 6 - Create the HTML artifact

Produce a self-contained index.html. Use the active DESIGN.md for typography, spacing, color roles, and component tone, but keep the information architecture stable:

  1. Header with decision question, confidence, and last-updated label.
  2. Executive readout with recommendation, risk, and next experiment.
  3. Evidence ledger with filter chips.
  4. Theme map with evidence ids and confidence.
  5. Opportunity matrix.
  6. Decision memo.
  7. Experiment queue with owner, metric, and success threshold.
  8. Assumptions and limitations.

The artifact should be interactive but durable. Simple vanilla JavaScript is allowed for filtering evidence, switching views, or highlighting related ids. No framework dependency is required.

Step 7 - Self-check and emit

Run the checklist. Then emit one concise orientation sentence and one HTML artifact:

<artifact identifier="research-decision-room" type="text/html" title="Research Decision Room">
<!doctype html>
<html>...</html>
</artifact>

Nothing after the closing </artifact>.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.