Analyze Performance Intake
Step of the analyze-performance playbook: gathers the week's numbers from tools...
Install
npx skills add gooseworks-ai/goose-skills --skill analyze-performance-intake -g -a claude-code -y- Repository
- gooseworks-ai/goose-skills1.3k
- Category
- Engineering
- Updated
- 9d ago
- License
- MIT
- Context cost
- Lightabout 404 tokens
- Runs scripts
- No, instructions only
What it does
Step of the analyze-performance playbook: gathers the week's numbers from tools, exports and pastes, cleans them, and writes the coverage line or switches to claims-only mode. Run analyze-performance instead; not for direct use.
Intake, hygiene and coverage (atom)
Load: ../analyze-performance/references/measurement-contract.md.
Inputs: the measurement contract (company type, referee, channel roster); tool reads (meta_read performance, social_analytics_get, ads_creative_read, video_read, campaign_read); the marketer's connectors / exports / screenshots / pastes from the one input message.
Do:
- Start from the minimum useful read (contract §4) and tick the rest against the roster; big pasted exports are totalled in code when a code tool exists; with none, never totalled by eye, ask for the summary report and mark the referee not measured until it arrives (contract §4); never echoed. Then: what arrived, what didn't ("not checked this week", no mid-run asks).
- Hygiene: strip test, wholesale, staff orders and subscription renewals from new revenue; net refunds; align timezone and currency; note discount depth.
- Maturity: compare this week as first reported with last week as first reported; show last week restated separately. Exports are the week's source;
meta_readidentifies Goose ads and cross-checks, de-duplicate by ad id. 3b. Save the input summary toreports/performance/inputs/<YYYY-MM-DD>.mdfor run-paid-campaigns to reuse. - Coverage line: per channel, truth / claimed / not measured / not used; share of Meta spend seen in detail.
- The type's referee missing (or no total spend) → claims-only mode (labels, no MER, calls capped at first look, first-line notice).
Output: a clean dataset per channel with labels, the coverage line, and the list of asks for next week.
