shift-budget
Skill15 starsChanged 36 days agoMITView on GitHub
Use when the user wants to move, raise or cut budget: where to put the next $X, which campaigns can scale inside target, budget pacing against the monthly plan, underspending or capped campaigns, or reallocating across Meta, Google, TikTok and Microsoft Ads. Finds headroom from pacing, marginal efficiency and targets, then proposes the exact budget and bid-target changes for approval.
In this repository61 other files it gives its agents.
- access-and-permissionsSkill
- accounts-and-connectionsSkill
- ad-brief-generatorSkill
- affiliate-marketingSkill
- analyse-creativeSkill
- automate-with-agentsSkill
- brief-creativeSkill
- build-reportsSkill
- clean-wasted-spendSkill
- competitor-ad-intelligenceSkill
- creative-psychology-hooksSkill
- creative-researchSkill
- diagnose-performanceSkill
- email-marketingSkill
- ga4-source-of-truthSkill
- get-startedSkill
- gomarble-skills-creative-strategistsSkill
- gomarble-skills-ecommerce-brandsSkill
- gomarble-skills-google-ads-auditSkill
- gomarble-skills-meta-ads-auditSkill
- gomarble-skills-saas-companiesSkill
- google-ads-create-master-skillSkill
- google-ads-depth-of-analysisSkill
- google-ads-guardrailsSkill
- google-ads-keywordplannerSkill
- google-ads-pmax-evaluationSkill
- google-ads-pmax-scalingSkill
- google-ads-search-analysisSkill
- google-ads-search-executionSkill
- google-ads-shoppingSkill
- google-ads-tool-fundamentalsSkill
- google-impression-shareSkill
- google-pmax-pulseSkill
- google-search-auditSkill
- google-search-term-auditSkill
- launch-campaignsSkill
- linkedin-adsSkill
- manage-campaignsSkill
- meta-ads-auditSkill
- meta-agent-operationsSkill
- meta-create-master-skillSkill
- meta-creative-analysisSkill
- meta-creative-fatigue-detectionSkill
- meta-creative-strategySkill
- meta-custom-event-interpretationSkill
- meta-daily-optimizationSkill
- meta-depth-of-analysisSkill
- meta-guardrailsSkill
- meta-performance-analysisSkill
- meta-tool-fundamentalsSkill
- microsoft-adsSkill
- organic-socialSkill
- own-creative-diagnosisSkill
- research-competitorsSkill
- search-console-master-skillSkill
- shopify-order-disciplineSkill
- tiktok-adsSkill
- tiktok-create-master-skillSkill
- winning-ads-engineSkill
- winning-ads-orchestratorSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Protected budgets: Ask whether any campaigns, tests or budget floors must not move (brand search, prospecting floors, active tests).
- Distinctive: line 45
Default to hold when the data is thin or contradictory.
- Very specific: line 49
Read meta-guardrails or google-ads-guardrails first.
- Distinctive: line 52
Don't change the budget and the bid strategy of the same campaign at the same time.
- Distinctive: line 53
Always say whether a budget is daily or lifetime.
- Very specific: line 69
Every change: one item per field change → dry run → show current and new values → the user approves in chat → mode: "live" with only the …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Shift budget
Move budget while the opportunity is still open. Find campaign headroom, correct pacing, and approve the exact budget moves while the signal is fresh.
When to use
- "Where can we move $12k without pushing CAC above target?"
- "Which campaigns should get more budget?"
- "Are we on pace for the month?"
- "This campaign is capped — should we raise it?"
- "Cut spend on what isn't working."
Before you start
- Targets. ROAS, CPA or CAC target per campaign or channel. If there isn't one, use the trailing 30-day average and say so.
- Protected budgets. Ask whether any campaigns, tests or budget floors must not move (brand search, prospecting floors, active tests).
recall_memorymay already know. - The plan. For pacing questions, the monthly or flight budget per channel.
Workflow
1. Pacing
Compare spend so far with the plan and each campaign's budget.
- Budget utilization = spend ÷ (daily budget × days). Below about 85% means the campaign can't spend what it has; look for the cause (bid cap, small audience, low rank) before adding money.
- Google:
google_ads_run_gaqlfor spend by day, budget, and search impression share lost to budget vs rank. - Meta:
facebook_list_campaignsandfacebook_list_adsetsfor budgets (returned in cents), andfacebook_get_adaccount_insightsfor spend. - TikTok:
tiktok_get_campaigns,tiktok_get_adgroupsandtiktok_get_basic_report_enhanced. Account balance and ad group quota:tiktok_get_account_finance. - Microsoft Ads:
bing_ads_list_campaigns,bing_ads_list_budgets(shared budgets) andbing_ads_get_performance.
2. Headroom: where the next dollar works hardest
A campaign can take more budget only when all of these hold:
- It's at or better than target over 7 and 14 days, not just yesterday.
- It's actually constrained: impression share lost to budget (Google), sustained full spend of its budget, or a stable 3-day ROAS against a 7-day ROAS.
- It has enough conversions to trust (see the guardrails skill for each platform).
- Nothing changed in the last 48–72 hours.
Cut or cap where results are below target and trending worse. Diagnose first (diagnose-performance); don't cut a campaign that's just in its learning phase.
Default to hold when the data is thin or contradictory.
3. Size the moves
Read meta-guardrails or google-ads-guardrails first. Key limits:
- At most 20% per move on Meta and Google Search/Shopping. Up to 50% on mature Performance Max (
google-ads-pmax-scaling). - Budgets exist only at campaign (CBO) or ad set (ABO) level on Meta, and campaign level on Google. Never "move budget between ads, placements, audiences or keywords"; those aren't controls.
- Don't change the budget and the bid strategy of the same campaign at the same time.
- Always say whether a budget is daily or lifetime. Warn on increases above 100% or cuts above 50%.
Output
- Pacing: spend vs plan by channel and campaign.
- Headroom: campaigns that can scale inside target, and why.
- Proposed moves: a table with campaign, current budget, new budget, change %, reason and expected effect. Show that the total fits the plan.
- Held: what you chose not to move, and why.
Making the change
- Meta:
facebook_propose_update_campaigns(campaign budgets, bid strategy, spend cap) orfacebook_propose_update_adsets(ad set budgets on ABO campaigns). Pass budgets in account currency; the tools convert. - Google:
google_ads_propose_update_campaigns(budget, tCPA/tROAS targets). Callgoogle_ads_get_currencyfirst. - TikTok (beta):
tiktok_propose_update_campaignsandtiktok_propose_update_adgroups. For Smart+ campaigns,tiktok_propose_manage_smart_pluswithUPDATE_BUDGETS, one ad group per proposal. Checktiktok_get_automated_rulesfirst so a rule doesn't undo the change. - Microsoft Ads: read-only through the connector. Give the user the exact moves to make.
Every change: one item per field change → dry run → show current and new values → the user approves in chat → mode: "live" with only the approved operation_ids. Never go live without that yes.
Put it on a schedule
Offer a daily budget pacing agent. With write access and ask_approval, it proposes moves for approval, capped by maxBudgetChangePct (see automate-with-agents).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

