From mureo
Generates a weekly marketing operations report across platforms (Google Ads, Meta Ads, etc.) with goal progress, week-over-week changes, and platform discovery.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mureo:weekly-reportThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> PREREQUISITE: Read `../_mureo-shared/SKILL.md` for auth, security rules, output format, and **Tool Selection** (Read/Write on Code, `mureo_strategy_*` / `mureo_state_*` MCP on Desktop / Cowork).
PREREQUISITE: Read
../_mureo-shared/SKILL.mdfor auth, security rules, output format, and Tool Selection (Read/Write on Code,mureo_strategy_*/mureo_state_*MCP on Desktop / Cowork).
Generate a weekly marketing operations report.
onboard skill first)Before you start: Run the Diagnostic preamble from ../_mureo-shared/SKILL.md — load learning insights (mureo_learning_insights_get) and consult advisors (mureo_consult_advisor) before drawing conclusions.
Load context: Read STRATEGY.md and STATE.json.
Discover platforms: Identify all configured platforms and available data sources — built-in, mcp__mureo__<plugin>_* plugin platforms, and any hosted official-MCP connector present in the session (e.g. TikTok's tt-ads-* tools, key tiktok_ads). See ../_mureo-shared/SKILL.md → Plugin platforms and Hosted-connector platforms; pull a hosted connector's numbers from its own reporting tools and omit mureo-only value-adds.
Period: Determine the reporting period (last 7 days from today).
Goal progress: For each Goal, pull performance data from the relevant platforms:
google_ads_performance_report (with period: "LAST_7_DAYS" then period: "LAST_14_DAYS" and subtract the first 7 from the next 7 for previous-week comparison). If mureo's Google Ads tools are unavailable (e.g. MUREO_DISABLE_GOOGLE_ADS=1 after mureo providers add google-ads-official), fall back to the official google-ads-official MCP's equivalent performance-report tool over the same two windows and perform the WoW subtraction the same way.meta_ads_insights_report similarly. When summing Meta "results" across campaigns, group by result_indicator — never aggregate link_click totals together with pixel_lead totals (PR #61). If mureo's Meta Ads tools are unavailable, fall back to the official meta-ads-official hosted MCP for the raw insights over the same two windows; the official MCP does not surface a result_indicator field, so you must inspect each campaign's optimization goal / actions list yourself and avoid aggregating link_click-optimized totals with offsite_conversion.fb_pixel_lead-optimized totals — note this caveat in the report.byod/ directory (or ~/.mureo/byod/ for legacy CLI users) and is only accessible through mureo MCP tools — do not look for raw CSVs in the project directory.Actions taken: Read action_log from STATE.json, filter to the reporting period.
Present as a timeline:
| Date | Command | Action | Platform | Summary |
|---|
Impact assessment: For each action taken, evaluate impact using the relevant platform's trend/analysis tools. Cross-reference with GA4 data if available to validate on-site impact.
Cross-platform insights:
Next week recommendations:
/rescue, /budget-rebalance, /creative-refresh, /goal-review)Evidence pipeline: Include an evidence assessment section:
observation_due dates that passed this week — evaluate their outcomes by comparing metrics_at_action with current metricsPresent report in a structured format suitable for sharing with stakeholders:
Log to action_log in STATE.json that a weekly report was generated, including the reporting period.
Persist the report summary (best-effort): Call mureo_state_report_set with report="weekly" and a concise summary object so the read-only dashboard can render this report without re-running you. Follow this convention:
generated_at: ISO 8601 timestamp of this runperiod: the reporting window (e.g. "LAST_7_DAYS" or an explicit date range)kpis: per-platform and/or totals headline numbers (spend, conversions, cpa, week-over-week change)flags: a list of structured flags — each a small object {code, severity, params} so the dashboard renders a coarse, localizable chip with the numbers on drill-down:
code: a canonical vocabulary key — one of goals_met, cpa_over_target, cpa_under_target, cv_below_target, cv_above_target, spend_spike, cpa_spike, invalid_traffic_suspected, zero_cv_adspots, budget_overspend, budget_drift, tracking_suspect, zero_conversions, supply_tools_unconfigured, anomaly_baseline_insufficient, pending_observations, search_console_no_property, ga4_not_configured.severity: one of action/watch/info/positive (omit to take the code's default — info/positive keep informational and good-news flags visually distinct from alarms).params: an object holding the DETAIL (platform, yen, cpa, week-over-week change). Keep detail in params, NOT baked into the code — write {"code":"cpa_over_target","params":{"cpa":15200}}, never a slug like meta_ads_cpa_up_15pct.{code:"custom", severity, label} where label is a string or a {"ja":…,"en":…} map. Unknown non-custom codes are rejected. (A legacy bare-string flag still works but renders without the drill-down — prefer the object form.)[{"code":"cpa_over_target","params":{"cpa":15200}}, {"code":"goals_met"}]narrative: the 2-3 sentence executive summaryThis is best-effort: if mureo_state_report_set is unavailable (e.g. a pure file-mode host without the context MCP), skip it silently — the rest of this skill still works.
npx claudepluginhub logly/mureo --plugin mureoGenerates a client-facing monthly marketing operations report with month-over-month comparison, goal attainment, action-log recap, budget utilization, and next-month recommendations.
Use this skill when the user wants a quick, factual weekly or periodic overview of marketing metrics across channels. This is a lightweight report with numbers and anomalies — no subagents, no strategic synthesis. Activate when the user says "weekly report", "how did we do this week", "give me a marketing summary", "cross-channel report", "what happened with our marketing", "channel performance", "marketing digest", "weekly metrics", or asks for a combined view of organic and paid results. Do NOT use when the user wants strategic recommendations or cross-channel connections — that belongs to ds-brain. Works best with Dataslayer MCP connected. Also works with manual data.
Generates concise marketing reports following a 'read 5 minutes, know what to do next' format with insights first, metrics as evidence, and actionable recommendations with deadlines and owners. Supports weekly/monthly global performance reports.