quick-stats
/quick-stats
Lightning-fast answers to simple numeric questions — "how many users yesterday", "what's the conversion rate", "how many sessions today". Use when the question is a single number, no analysis needed. Skips the full general-analysis workflow.
- Author
- reatlat ↗
- Repository
- fullstory-claude-plugin ↗
- Licence
- MIT
- Last repository change
- 13.08.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 13.08.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Lightning-fast answers to simple numeric questions — "how many users yesterday", "what's the conversion rate", "how many sessions today". Use when the question is a single number, no analysis needed. Skips the full general-analysis workflow.
Triggers from the description
Original author description
Lightning-fast answers to simple numeric questions — "how many users yesterday", "what's the conversion rate", "how many sessions today". Use when the question is a single number, no analysis needed. Skips the full general-analysis workflow.
How it works
- When to Use
- Workflow
- When NOT to Use
- Guidelines
SKILL.md preview
---
name: quick-stats
description: Lightning-fast answers to simple numeric questions — "how many users yesterday", "what's the conversion rate", "how many sessions today". Use when the question is a single number, no analysis needed. Skips the full general-analysis workflow.
---
# Quick Stats
One-number answers. No analysis, no session investigation, no validation dance. Just the number, with context.
## When to Use
- "How many users yesterday?"
- "What's the conversion rate this week?"
- "How many sessions today?"
- "How many rage clicks last month?"
- "What's our error count for this week?"
Short questions that expect a single numeric answer.
## Workflow
Everything is one step: build, compute, present.
```
fullstory:build_metric(query="page views yesterday", output_type="single_number")
fullstory:compute_metric(metric_id)
```
Present: "12,340 page views yesterday (Aug 3)."
Add minimal context: "That's +3% vs the daily average last week" — but only if you already have the comparison data. Don't make extra calls to get it.
## When NOT to Use
Don't use this skill if the question is:
- A comparison ("mobile vs desktop") → `comparisons`
- A trend ("is it getting worse?") → `general-analysis` (trend metric)
- A breakdown ("by page" or "by device") → `general-analysis` (top_n metric)
- A "why" question → any of the deep-dive skills
Quick Stats is for "what's the number" — nothing more.
## Guidelines
- One metric, one compute call, one answer. No extra API calls.
- Include the time period in the answer: "12,340 page views yesterday" not "12,340 page views."
- Surface the `metric_url` so the user can verify.
- If the metric already exists from a previous call in the conversation, reuse it. Don't rebuild.
- If the question needs validation (result is zero, looks wrong), don't use Quick Stats — upgrade to `general-analysis` which handles validation.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · reatlat/fullstory-claude-plugin | 100 | MIT |
| hoangsonww/Claude-Code-Agent-Monitor | 95 | MIT |
Database snapshot: 13.11.2026 · package version 93ca4862f9ef (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100quick-research
Quick web research for simple questions — fast answer with 3-5 cited sources in ~1 minute. Use for fact-checks, simple lookups, "what is X", "latest version of Y", "who made Z". For anything deeper, use /research (L1) or /deep-research (L2). - 100data-analysis
Answer questions about funnels, conversion, errors, friction, traffic and trends using Quantum Metric. Use for any request that needs a number, a breakdown, a drop-off or a comparison from Quantum Metric data. - 90quick-check
Answer a small, ad hoc data question fast while leaving a reproducible trail (a dated folder with notes and the query). Use when someone wants a number or a sanity look without a decision or acceptance criteria behind it. Formal work goes to new-request; scheduled work is a pipeline.