data-analysis-insights
Skill0 starsChanged 22 days agoMITView on GitHub
Analyse business, conversion or product data from CSV, sheets or exports: schema and null checks, defined denominators, segments, correlation vs causation, reproducible steps. Use for "analyse this data", "what does this CSV show", "find trends". NOT client SEO reports (client-report).
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/setup-project-context/templates/CLAUDE.mdCLAUDE.md
- backend-architectureSkill
- build-review-loopSkill
- capability-intakeSkill
- competitor-market-analysisSkill
- context-auditSkill
- data-privacy-securitySkill
- dev-agentsSkill
- dev-patternsSkill
- frontend-system-designSkill
- idea-validatorSkill
- intellectual-property-licensingSkill
- international-legal-researchSkill
- legal-document-drafterSkill
- llm-councilSkill
- make-slidesSkill
- password-authentication-securitySkill
- privacy-data-protection-lawSkill
- project-estimation-planningSkill
- project-startSkill
- rea-researchSkill
- requirements-business-analystSkill
- secrets-credential-managerSkill
- seo-tech-stackSkill
- setup-project-contextSkill
- shopify-ui-auditSkill
- site-incidentSkill
- sop-process-builderSkill
- task-dispatchSkill
- technical-feasibilitySkill
- tech-research-intelligenceSkill
- update-mdSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Write directly and specifically.
- Distinctive: line 30
Never reveal client secrets or personally identifying data unnecessarily.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
data-analysis-insights
Purpose
Analyze operational conversion and product data. Use concrete evidence and project-specific constraints. Do not claim work was executed, tested, legally approved, or verified unless it actually was.
Activation
Activate when the request concerns analyze operational conversion and product data. Read relevant project instructions first. When current laws, platform APIs, or tool capabilities matter, check authoritative current sources.
Procedure
- Validate schema units nulls and sample bias.
- Compute metrics with defined denominator.
- Segment and test alternative explanations.
- Distinguish correlation and causation.
- Show replicable transformations and limitations.
Verification gate
- State what was examined, what was not accessible, and any assumptions.
- Separate confirmed findings, risks, recommendations, and unverified hypotheses.
- For development, require relevant automated tests and manual checks before marking complete.
- Provide exact file paths/line references, data sources, or legal citations when appropriate.
- Report blockers and proposed fixes by severity. Never silently change production systems.
the agency editorial and safety rules
- Write directly and specifically. No generic AI fluff, em dashes, exaggerated claims, artificial case studies, unnecessary dividers, or fabricated proof.
- Never reveal client secrets or personally identifying data unnecessarily. Use redacted examples and placeholders.
- Seek explicit approval before sending external communication, changing production, deploying code, deleting data, or conducting active security tests.
- For regulated legal or tax conclusions, provide research support, not a claim of professional sign-off.
Deliverable template
- Scope and context, 2. Evidence and findings, 3. Prioritized action plan, 4. Validation/acceptance criteria, 5. Uncertainties or approvals needed. Adapt format to the actual request rather than forcing five headings.
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
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.

