agentleFS
Sign inStart free
adhyayanrathi01adhyayanrathi01/product-manager-os/skills/data/analyze-query-results/SKILL.md

analyze-query-results

Skill2 starsChanged 2 months agoMITView on GitHub

Interpret product-data query results and convert them into grounded findings for a PM decision. Use after receiving tables, query output, exports, experiment results, cohort data, or other structured product evidence.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Verify provenance, sample size, denominator, identity mapping, freshness, and cohort maturity before interpreting.

    line 12
  2. Distinctive:

    If provenance or a critical definition is missing, describe observable table properties but block decision-level conclusions.

    line 13
  3. Distinctive:

    Read the original question, metric definition, query or method, filters, and exclusions.

    line 19
  4. Distinctive:

    Verify the result grain, sample size, denominators, missing values, and comparison groups.

    line 20
  5. Distinctive:

    Look for magnitude, direction, distribution, segments, changes over time, and meaningful anomalies.

    line 21
  6. Distinctive:

    Check whether the result could be explained by tracking changes, seasonality, selection bias, or small samples.

    line 22
  7. Very specific:

    Every field above must appear as a labeled section in the produced output.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Analyze Query Results

<!-- CORE:BEGIN -->

Contract

  • Require the decision, result artifact, generating query or method, metric definition, grain, filters, exclusions, absolute period, and comparison.
  • Verify provenance, sample size, denominator, identity mapping, freshness, and cohort maturity before interpreting.
  • If provenance or a critical definition is missing, describe observable table properties but block decision-level conclusions.
  • Emit the shared evidence handoff for reusable findings.
<!-- CORE:END -->

Process

  1. Read the original question, metric definition, query or method, filters, and exclusions.
  2. Verify the result grain, sample size, denominators, missing values, and comparison groups.
  3. Look for magnitude, direction, distribution, segments, changes over time, and meaningful anomalies.
  4. Check whether the result could be explained by tracking changes, seasonality, selection bias, or small samples.
  5. Separate observations from interpretations and causal hypotheses.
  6. Compare with other available evidence when relevant.
  7. Explain what the result changes—or does not change—about the PM’s decision.
<!-- CORE:BEGIN -->

Output

Provide findings, confidence, limitations, plausible explanations, contradictory evidence, and decision implications. Do not overstate statistical or practical significance.

Required fields: Findings|Confidence|Limitations|Plausible explanations|Contradictory evidence|Decision implications

Every field above must appear as a labeled section in the produced output. Verify with evals/check-output.sh analyze-query-results <artifact>.

<!-- CORE:END -->

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.

Check your setup, free