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.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, well-structured decision workflow with strong safety boundaries and precondition gates. Its main weakness is the absence of executable commands or explicit error-recovery loops, which caps actionability and workflow_clarity just below the top.

Suggestions

Add an explicit feedback loop for verification failure (e.g., 'if remote state no longer matches the draft precondition, abort and re-snapshot before retrying') to reach top workflow_clarity.

Include one concrete example of invoking the mutation gate or adapter (a representative command/signature) to lift actionability to fully executable.

Show a brief ranked-recommendation output shape so Claude knows the expected artifact from step 4.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — 'Default to `--draft`.' and the numbered list assume Claude's competence with zero padding and no explanation of concepts Claude already knows.	5 / 5
Actionability	Concrete, specific rules ('Refuse permanent deletion...', 'Offer reversible alternatives: leave objects paused, archive where supported, apply labels, export a backup') but no executable code or commands; minor execution gaps for an instruction-only skill interfacing with domain adapters.	4 / 5
Workflow Clarity	A clear 6-step sequence with explicit checkpoints ('verify, audit', 'only when... remote state still matches the draft precondition', 'only through the main mutation gate'), but no explicit error-recovery feedback loops beyond the destructive-action refusal conditions.	4 / 5
Progressive Disclosure	Under 50 lines with no external references needed; well-organized into a numbered process and a clearly signaled 'Destructive-action boundary' section, matching the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: third-person, concrete, comprehensive, and explicit about both capability and triggers. Every dimension lands at the top anchor with no padding or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'budget reallocation, bid changes, pausing or archiving ads, search-term or negative-keyword actions, creative rotation, or improving CPA and ROAS' — giving comprehensive coverage of paid-ad operations rather than vague abstractions.	5 / 5
Completeness	Explicitly answers both 'what' ('Diagnose and draft or explicitly apply paid-ad optimizations using evidence, financial constraints, experiments, and capability-gated adapters') and 'when' ('Use for campaign optimization, budget reallocation...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural ad-management phrases users would say ('campaign optimization, budget reallocation, bid changes', 'CPA and ROAS') are comprehensively covered, including synonyms and domain shorthand.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear paid-media niche with distinct, domain-specific triggers (CPA/ROAS, negative-keyword actions, mutation gate) that minimize overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: AgriciDaniel/claude-ads
Path: skills/ads-optimize/SKILL.md
Commit: ac21644

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.