Operations Data Diagnostician
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_fccf428b/operations-data-diagnostician into your AI assistant.
About this skill
Problem
Operations metrics often stop at surface-level interpretation: anomalies, channel differences, and funnel bottlenecks are mixed together without clear evidence boundaries. This skill is for teams that need diagnostics to become testable actions. It first aligns business goals, funnel definitions, time windows, historical baselines, and metric definitions, then separates confirmed facts, conservative assumptions, and items that need evidence.
How It Works
The workflow follows methodology, execution-rules, quality-boundaries, and output-contract:
- Input gate: when key information is missing, ask one focused question instead of guessing a mode.
- Diagnostic ranking: identify priority issues from the funnel problem tree, anomaly location, and bottleneck ranking.
- Actionable delivery: output evidence tasks, single-variable retests, a metric dictionary, escalation conditions, and stop lines.
- Quality check: run validate_output.py --check-output; if validation fails, fix business content rather than loosen rules.
Boundaries
Use it for operations metrics review, funnel diagnosis, anomaly attribution, and retest design. Do not expect fixed growth results, raw links, accounts, API keys, or source material. Passing machine validation only means structure and specificity are sufficient; business owners still need to confirm metric definitions and action fit.
Use Cases
- During campaign reviews, identify the funnel stage causing conversion drops and create evidence tasks with single-variable retests.
- When channel metrics shift, separate confirmed facts, assumptions, and gaps, then generate a bottleneck ranking.
- When designing growth experiments, convert diagnostics into a metric dictionary, escalation conditions, and stop lines for review.
- When reviewing multi-period reports, verify definitions, baselines, and anomalies to build a reviewable data-quality checklist.
Best For
- Operations leads: need to turn metric anomalies into testable retest plans instead of directional conclusions.
- Growth analysts: need to locate funnel, channel, and baseline bottlenecks and output evidence tasks with stop lines.
- Product managers: need to verify metric definitions, anomalies, and escalation conditions before and after experiments.
- Data analysts: need to structure diagnostics into facts, assumptions, gaps, and a metric dictionary.
Related Skills
Scrapes JD search results for product titles, prices, sales, and stores, then exports verified data to UTF-8 CSV.
An A-share market monitor using Sina Finance API for real-time quotes, price and percentage alerts, daily logging, and scheduled checks.
Turn pasted or queried Xiaohongshu notes into a research memo covering title patterns, structure, quoted comments, and follow-up angles; public lookups are optional and confirmed before paid execution.
A universal base component that automatically launches the Edge browser and connects the BrowserSkill extension, ensuring readiness for web scraping and browser automation tasks.