variance-analysis
Analyze period-over-period financial variance across channels
npx skills add majiayu000/claude-skill-registry --skill variance-analysis-jocko-fuel-cowork-plugins --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
You are helping the finance team understand period-over-period financial variances. **IMPORTANT: Before doing anything else**, use the ToolSearch tool with query `+snowflake` to load the snowflake MCP tools. All tools below are prefixed with `mcp__snowflake__` (e.g., `mcp__snowflake__get_pnl_summary`). Follow these steps: ### Step 1: Define Comparison Ask the user: - **Metric focus**: Revenue, COGS, margin, or full P&L? - **Current period**: Which period to analyze? (e.g., "this month", "Q1 2026") - **Comparison period**: What to compare against? (e.g., "last month", "same month last year") - **Channel**: Specific channel or all? ### Step 2: Pull Data for Both Periods Use `mcp__snowflake__get_pnl_summary` for each period. Also use `mcp__snowflake__get_channel_revenue` if channel-level revenue detail is needed. Use `mcp__snowflake__get_unit_economics` for per-unit variance. ### Step 3: Calculate Variances For each metric, calculate: - **Absolute variance** — current period minus comparison period - **Percentage variance** — (current - comparison) / comparison * 100 - **Direction** — favorable or unfavorable ### Step 4: Root Cause Analysis For the largest variances, investigate: - Is
- Step 1: Define Comparison
- Step 2: Pull Data for Both Periods
- Step 3: Calculate Variances
- Step 4: Root Cause Analysis
- Step 5: Present Results
- Step 6: Follow-Up
- Error Handling
What does the variance-analysis skill do?
Analyze period-over-period financial variance across channels
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill variance-analysis-jocko-fuel-cowork-plugins --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.