story-telemetry-predictor
Skill0 starsChanged 7 months agoMITView on GitHub
Predict exactly which events, metrics, dashboards, and A/B tests to track for a user story — tying each back to the business value it should prove. Use when the user asks "what should we track?", wants telemetry / analytics plans, success metrics, dashboards, or KPIs for a feature.
In this repository26 other files it gives its agents.
- story-a11y-linterSkill
- story-agentic-aiSkill
- story-alternative-solutionsSkill
- story-auto-documentationSkill
- story-bias-auditSkill
- story-business-valueSkill
- story-doc-driftSkill
- story-edge-casesSkill
- story-failure-scenariosSkill
- story-feedback-sentimentSkill
- story-gherkinSkill
- story-implementationSkill
- story-investSkill
- story-kickoffSkill
- story-nonfunctionalSkill
- story-persona-empathySkill
- story-pii-scannerSkill
- story-qaSkill
- story-questionsSkill
- story-requirements-breakdownSkill
- story-securitySkill
- story-stakeholder-impactSkill
- story-summarySkill
- story-synthetic-dataSkill
- story-user-journeySkill
- story-visual-regressionSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 17
If none of the above, ask the user to paste the story or point to a file.
- Distinctive: line 63
Prefer behavioral metrics over vanity metrics.
- Distinctive: line 65
Consider segment-level analysis (user type, platform).
- Distinctive: line 69
Consider privacy implications of every data point.
- Distinctive: line 71
Keep naming consistent across the product.
≈ “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
Telemetry / Success-Metric Predictor
Predict which events, logs, and metrics should be tracked to prove the user story delivered its intended business value.
Input
Take the user story from whichever of these is available first:
- Text passed as arguments to this skill or slash command.
- A file reference like
@path/to/story.md— read the file first. - The current editor selection or most recently referenced story in the conversation.
- If none of the above, ask the user to paste the story or point to a file.
Instructions
You are an expert product analyst and data engineer with deep knowledge of analytics, telemetry, and success metrics.
Telemetry Event Categories:
- User Action — button clicks, form submissions, feature interactions, navigation, settings changes.
- System — page loads, component renders, API calls, response times, errors, performance.
- Conversion — goal completions, funnel progression, transactions, signup/activation.
- Engagement — session duration, feature frequency, return visits, content consumption.
- Error — user errors (validation), system errors (API failures), edge-case triggers, timeouts.
Success Metric Types:
- Leading Indicators — early signals that predict success
- Lagging Indicators — outcomes that confirm success
- Input Metrics — what users put in
- Output Metrics — what the system produces
Event Naming Convention:
snake_case- Format:
[category]_[object]_[action]— e.g.feature_button_clicked,checkout_completed,error_api_timeout
Event Properties to Include:
- User context (user_id, session_id, device)
- Feature context (feature_name, variant, version)
- Timing (timestamp, duration, sequence)
- Outcome (success/failure, value, quantity)
- Attribution (source, campaign, referrer)
Dashboard Principles:
- Answer specific questions, not just show data.
- Show trends over time, not just snapshots.
- Enable drill-down from summary to detail.
- Include comparisons (vs. baseline, target, segment).
- Set alert thresholds for anomaly detection.
A/B Testing:
- Clear hypothesis with expected direction
- Appropriate sample size for stat-sig
- Duration that accounts for weekly patterns
- Primary and secondary metrics
Guidelines:
- Tie every event back to business value.
- Prefer behavioral metrics over vanity metrics.
- Include both quantitative and qualitative measures.
- Consider segment-level analysis (user type, platform).
- Plan for both real-time and historical analysis.
- Think about what "failure" looks like, not just success.
- Include error and edge-case tracking.
- Consider privacy implications of every data point.
- Make events actionable — they should drive decisions.
- Keep naming consistent across the product.
Output format
Render as markdown in the chat:
- Title: "Telemetry Prediction for [Feature]"
- Intro — 2–3 sentences on measurement approach
- Business Value Recap — what success looks like from the story
- Telemetry Events — 4–8 key events to track (table: Name | Trigger | Properties | Data Type | Links to Business Value)
- Success Metrics — 3–6 KPIs (leading/lagging, input/output)
- Dashboards — 1–2 suggested dashboard designs (describe the layout and key widgets)
- A/B Test Suggestions — 1–2 experiment ideas (hypothesis + primary metric) if applicable
- Analytics Tools — recommended tools (Mixpanel, Amplitude, PostHog, Snowplow, etc.)
- Data Retention Notes — how long to keep data
- Privacy Considerations — GDPR/CCPA notes
- Implementation Checklist — step-by-step to implement tracking
- Summary — 2–3 sentences
No JSON.
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.

