gooseworks-ai/goose-skills / skills/marketing/analyze-performance
analyze-performance
VerifiedWeekly performance read across every channel we run: what worked, why, and what to make next, judged on the business's real number (store revenue, qualified pipeline, retained users), not platform claims. Use when: write my Monday report; how are my ads doing — which ad won?; are my ads actually making money (Meta says 4x ROAS but revenue is flat); why did sales drop this week; did the test win; is my tracking working; monthly numbers for the replan; anything on fire today. Not for acting on the recommendations (pausing, scaling, launching) — use run-paid-campaigns; not for replanning the budget — use plan-campaign.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.0 KB |
| references/creative-and-channels.md | markdown | 7.0 KB |
| references/diagnosis.md | markdown | 5.5 KB |
| references/local-mode.md | markdown | 2.1 KB |
| references/measurement-contract.md | markdown | 10.3 KB |
| references/monday-report.md | markdown | 8.9 KB |
| references/monthly-and-pulse.md | markdown | 4.4 KB |
| references/revenue-join.md | markdown | 4.6 KB |
| references/run-memory.md | markdown | 14.7 KB |
| references/tests-and-learnings.md | markdown | 5.5 KB |
| skill.meta.json | config | 5.9 KB |
| tests/test-by-hand.md | markdown | 6.9 KB |
skill.meta.json
View on GitHub{
"slug": "analyze-performance",
"category": "playbooks",
"tier": "playbook",
"version": "0.1.2",
"tags": [
"ads",
"monitoring"
],
"collections": [
"brand-growth"
],
"collection_stage": "analyze",
"requires_skills": [
"analyze-performance-call-and-learn",
"analyze-performance-diagnose",
"analyze-performance-intake",
"analyze-performance-rank-and-read",
"analyze-performance-revenue-join",
"claims-gate",
"marketing-data-access",
"marketing-guide",
"run-memory",
"save-learning",
"save-to-brain",
"spend-gate",
"write-report"
],
"pillar": "13 — Analytics, measurement and experimentation",
"intents": [
"What worked this week across every channel we run — why, and what do I make next?",
"write my Monday report",
"which ad won?",
"are my ads actually making money?",
"Meta says 4x ROAS but revenue is flat",
"did the test win?",
"monthly numbers for the replan",
"anything on fire today?"
],
"reads": [
"campaign brief (campaign_read): economics, targets, test plan, measurement plan, replan triggers, change-log slug — plan-campaign",
"ads/campaigns/<slug>/state.md (harness frontmatter, health line, open recommendations) and decisions.md (### dated blocks) — run-paid-campaigns and the server",
"statics' lower-case tags (ads_creative_read) and batch files ads/batches/<YYYY-MM-DD>-<slug>.md — make-static-ads; videos' angle and hook names (video_read; a video without them is unannotated)",
"Goose ads' Meta results (meta_read performance) — cross-check only",
"own TikTok/Instagram analytics (social_account_list, social_analytics_get)",
"lifecycle/program.md — email-lifecycle; social calendar — run-organic-social; creator roster and wave results creators/roster.csv — work-with-creators (roster seeding, creators row)",
"research/competitors/watch/<date>.md — research-competitors; research/market/<D>-read.md section 'What people are saying' (newest *-read.md; check its window line) — research-market; improve-search-visibility's last check, when they exist",
"learnings log (brand_read learnings, knowledge_search learning)",
"measurement contract, past reports and their Decisions (reports/performance/) — its own",
"human (one message): the type's referee (store, CRM, app consoles, bookings), exports per rostered channel, retailer sell-through, customer-level export monthly",
"its own last run records runs/analyze-performance/<job-slug>/<date>.md (up to four weekly back: scorecards, angle history, calls) — run-memory",
"run-paid-campaigns' run records runs/run-paid-campaigns/weekly-ads-check/<slug>/<date>.md (money moves, baseline recipes, verdicts, per-ad scorecard)",
"Brand Brain (brand_knowledge_browse, brand_knowledge_read, brand_knowledge_search where listed): chapters 18, 20, 22, 23 (experiment_readout.*, worn_out_angle.*, lessons)",
"connectors the marketer already has (ads platforms, store, CRM, billing, product analytics) — read-only, never their write tools",
"local mode: gooseworks-local/<brand-slug>/ (brand-notes.md, its own contract, reports and run records, the paid run's local state.md and decisions.md) — the marketing-guide skill (../marketing-guide/SKILL.md) §5"
],
"writes": [
"reports/performance/<YYYY-MM-DD>.md weekly read (with Decisions) — read by run-paid-campaigns, plan-campaign, make-static-ads, make-content, run-organic-social, email-lifecycle",
"reports/performance/monthly/<YYYY-MM>.md + brand document — read by plan-campaign",
"reports/performance/inputs/<YYYY-MM-DD>.md — read by run-paid-campaigns (reuses exports)",
"reports/performance/definitions.md + brand document (contract, roster, story pick) — its own, every week",
"learnings rows (brand_update patch.facts, user_correction) — read by every planner and maker; angle ids for research-competitors",
"daily pulse (chat, exception-only) — interim until watch-and-alert",
"run records runs/analyze-performance/<job-slug>/<date>.md + brand documents (keep-history) — per-channel and per-ad scorecards, calls with owner / review-by / test, outcomes — read by its own next run and plan-campaign",
"measured readouts kind 23 experiment_readout.<slug>-t<n> and <slug>-r<n>-store (worked / didn't work, never from a scheduled run), and worn_out_angle.<id> on the marketer's yes — via save-learning",
"reports/performance/method/ (copied method for the scheduled worker) — read by the weekly automation",
"local mode: the same reports, contract and run records under gooseworks-local/<brand-slug>/; learnings appended to brand-notes.md — read by its own next run, run-paid-campaigns and plan-campaign in local mode"
],
"needs": {
"gooseworks": "optional — without it, local mode (the marketing-guide skill, ../marketing-guide/SKILL.md §5): connectors the marketer has (read-only), else exports and screenshots",
"connectors_optional": [
"ads-platform, store, CRM, billing or product-analytics connector (read-only)"
],
"mcp": [
"gooseworks:get_started",
"gooseworks:brand_read",
"gooseworks:knowledge_search",
"gooseworks:brand_update",
"gooseworks:campaign_read",
"gooseworks:ads_creative_read",
"gooseworks:meta_read",
"gooseworks:social_account_list",
"gooseworks:social_analytics_get",
"gooseworks:file_list",
"gooseworks:file_read",
"gooseworks:file_write",
"gooseworks:automation_upsert",
"gooseworks:video_read",
"gooseworks:media_upload",
"gooseworks:knowledge_import",
"gooseworks:job_get",
"gooseworks:media_list",
"gooseworks:media_update",
"gooseworks:account_whoami",
"gooseworks:tools_load",
"gooseworks:brand_knowledge_browse",
"gooseworks:brand_knowledge_read",
"gooseworks:brand_knowledge_search",
"gooseworks:automation_list"
]
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |