Ads optimize
Diagnose and draft or explicitly apply paid-ad optimizations using evidence, financial constraints, experiments, and capability-gated adapters. Use for campaign optimization, budget reallocation, bid changes, pausing or archiving ads, requests to delete campaigns, search-term or negative-keyword actions, creative rotation, or improving CPA and ROAS.From its SKILL.md
npx -y skills add AgriciDaniel/claude-ads --skill ads-optimizeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- runs commandsInstructs the agent to run 1 command, including `--draft`.
SKILL.md
1.9 KB, 287 tokens by cl100k_base, as published. Nobody here has run it
Paid Media Optimization
Default to --draft.
- Load the latest normalized snapshot, prior decisions, monitoring results, experiment state, conversion lag, economics, and platform capability manifest.
- Identify the decision and causal evidence; do not optimize a metric in isolation.
- Compare no-change, experiment, and mutation options, including learning, policy, tracking, inventory, and opportunity-cost effects.
- Produce ranked recommendations with confidence and success measures.
- Convert approved recommendations into mutation plans only through the main mutation gate.
- Apply, verify, audit, and retain rollback only when the exact operation is enabled and remote state still matches the draft precondition.
Never use a fixed CPA multiple, budget ratio, benchmark, or novelty claim as sole authorization to change an account.
Destructive-action boundary
Refuse permanent deletion of campaigns, ad groups, ads, audiences, conversions, or other account objects. Permanent deletion is outside the supported mutation contract and cannot be made safe by confirmation. Offer reversible alternatives: leave objects paused, archive where supported, apply labels, export a backup, and define a retention or later-review date. Do not create or apply a delete plan.
Search-term actions require a search terms report, business-relevance evidence, and an overblocking review. Without them, request the missing evidence and do not invent or illustrate specific negative keywords.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most performance cost skills give in 287 tokens
Counted across 797 of the 1,117 authors here whose files we hold, read 2026-09-06
- Check for product marketing context firstin 46 of 797, across 20 files
- Measure before optimizingin 31 of 797, across 25 files
- Profile first to identify the actual bottleneckin 23 of 797, across 22 files
- Verify your robots.txt allows AI crawlersin 21 of 797, across 12 files
- Import directly and avoid barrel filesin 19 of 797, across 15 files
- Spawn all runs in the same turnin 18 of 797, across 11 files
- Write a draft of the skillin 17 of 797, across 10 files
- Understand the user's intentin 17 of 797, across 10 files
- Use React.cache for per-request deduplicationin 16 of 797, across 11 files
- Profile before optimizingin 16 of 797, across 14 files
- Include specific numbers with sourcesin 15 of 797, across 8 files
- Add lazy loading to below-fold imagesin 15 of 797, across 10 files
Said here and by no other author read
- Default to draft mode.
- Load snapshot prior decisions and state.
- Identify causal evidence before optimizing.
- Compare no-change experiment and mutation options.
- Produce ranked recommendations with confidence measures.
- Convert recommendations into mutation plans.
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.