Budget Rebalance

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).

Tool names below refer to the built-in platforms; a namespaced variant (see _mureo-shared → Namespaced built-in variants) is used with its prefix substituted.

Analyze budget allocation and suggest rebalancing across all campaigns.

Prerequisites

• STRATEGY.md and STATE.json must exist (run the onboard skill first)

Steps

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.

0. Establish today: call mureo_state_get first, on every host (including Claude Code, where you would otherwise Read the file) and take server_now from its response — ISO 8601 with UTC offset, e.g. 2026-07-28T10:12:33+09:00. Its date is the only source of the current date for this run: the observation_due you write in step 16, and every "is a previous change still inside its observation window?" check in step 14, are measured from it. Do not shell out (this skill must run in Bash-less headless hosts) and do not read the date off STATE.json — last_synced_at, reports.*.period and action_log timestamps are history, never evidence of what day it is now. Never write server_now into STATE.json: it is a response field, and a persisted copy becomes tomorrow's stale "today".
1. Load context: Read STRATEGY.md (Operation Mode, Market Context, Goal sections, Data Sources) and STATE.json (the same mureo_state_get response from step 0 on MCP hosts).
2. Discover platforms: Identify all configured ad platforms from STATE.json platforms. Also include any hosted official-MCP connector present in the session (e.g. TikTok, key tiktok_ads) — drive it via its own tools and skip mureo-only value-adds; see ../_mureo-shared/SKILL.md → Hosted-connector platforms.
3. Analyze budget efficiency: For each ad platform:
   • Google Ads: prefer mureo native — call google_ads_budget_efficiency (campaign × budget × spend × conv ratio) and google_ads_performance_report for the period. In BYOD mode, budget.efficiency may return [] because daily budgets aren't carried in the Apps Script bundle — fall back to performance.report cost / conv numbers and rank by CPA. 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 for the performance report only, then skip google_ads_budget_efficiency (mureo-only analysis) and rank campaigns by CPA from the raw cost / conv numbers yourself; note to the user that mureo's automated budget-efficiency scoring requires the native MCP (mureo setup claude-code).
   • Meta Ads: prefer mureo native — call meta_ads_insights_report and meta_ads_analysis_cost. In BYOD mode, daily budgets aren't surfaced — rank by spend × result_indicator-aware conversions instead. If mureo's Meta Ads tools are unavailable, fall back to the official meta-ads-official hosted MCP for raw insights only, then skip meta_ads_analysis_cost (mureo-only cost-trend analysis) and the result_indicator-aware ranking; rank by raw spend / conversions from the official MCP's response instead and warn the user that CV-definition mismatches across campaigns are NOT detected in this fallback path.
   • mureo BYOD data is centralized in the workspace 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.
4. Rank campaigns by efficiency (CPA, ROAS, or CVR depending on campaign goals) across all platforms to enable cross-platform comparison.
5. Goal-driven prioritization: Reference Goal sections from STRATEGY.md to guide allocation:
   • Identify which platform is closer to achieving each Goal
   • Consider shifting budget toward the platform with better Goal progress
6. Cross-platform rebalancing: Evaluate whether budget should move between any configured platforms:
   • Compare CPA/ROAS across all platforms
   • If one platform significantly outperforms, suggest cross-platform budget shift
   • Present cross-platform comparison before within-platform reallocation
7. Organic intelligence (if Search Console is available): If organic rankings are strong for certain keywords, consider reducing paid spend on those terms and reallocating to keywords without organic coverage.
8. Conversion quality check (if GA4 is available): Incorporate conversion quality data (bounce rate, pages/session, time on site by traffic source) into budget decisions. A platform with lower CPA but higher bounce rate may not be the better allocation.
9. Mode guard: If Operation Mode is ONBOARDING_LEARNING or CREATIVE_TESTING, warn that budget changes are discouraged in this mode and ask whether to proceed.
10. Generate reallocation plan based on Operation Mode:
    • EFFICIENCY_STABILIZE: Shift budget from high-CPA to low-CPA campaigns
    • SCALE_EXPANSION: Increase budget for campaigns not limited by budget but performing well
    • TURNAROUND_RESCUE: Cut budget from campaigns with 0 conversions
    • COMPETITOR_DEFENSE: Increase budget on core brand/keyword campaigns under competitive pressure
    • LTV_QUALITY_FOCUS: Prioritize campaigns with highest conversion quality
    • ONBOARDING_LEARNING: Minimal changes only if user confirmed in step 9
    • CREATIVE_TESTING: Minimal changes only if user confirmed in step 9

11. Present plan as a table:

    Platform

    Campaign

    Current Budget

    Proposed Budget

    Change

    Reason

    Every Reason must be marginal, not average. A rank by average CPA identifies candidates; it does not justify the move. State what the next (or removed) unit of spend is expected to do — a top-average campaign that is not budget-limited is usually saturated, and a bad-average campaign may simply be spend-suppressed. Where the marginal effect is genuinely unknown, say so and offer /experiment instead of asserting it. See ../_mureo-pro-diagnosis/SKILL.md → Allocation & Learning-State Discipline.

12. Risk assessment: Flag any single budget change >20% — on Google Ads Smart Bidding / Meta CBO a large step can reset the learning phase, so prefer staged changes (e.g. two ≤20% steps). A platform that does not select delivery by a bid has no learning phase to reset: do not warn about one for it.
13. Ask for approval before any changes.
14. Check pending observations: Before executing, check action_log for campaigns being modified. If a previous budget change is still within its observation window, warn about stacking changes.
15. Execute: Use each platform's budget update tools to apply approved changes.
16. Record outcome context: For each campaign modified, log to action_log with observation_due (7 days from server_now's date for budget changes); omit metrics_at_action and mureo fills it from the campaign's snapshot.
17. Update STATE.json with new budget values, notes, and log the rebalancing action to action_log.