ads-budget
Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy appropriateness, scaling readiness, and identifies campaigns to kill or scale. Uses 70/20/10 rule, 3x Kill Rule, and 20% scaling rule. Use when user says budget allocation, bidding strategy, ad spend, ROAS target, media budget, or scaling.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates specific capabilities, includes domain-specific frameworks, and provides explicit trigger terms. It uses proper third-person voice throughout and covers both the 'what' and 'when' comprehensively. The named rules and ad-platform-specific terminology make it highly distinctive and easy for Claude to select appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: evaluates spend distribution, bidding strategy appropriateness, scaling readiness, identifies campaigns to kill or scale. Also names specific frameworks (70/20/10 rule, 3x Kill Rule, 20% scaling rule). | 3 / 3 |
Completeness | Clearly answers both 'what' (evaluates spend distribution, bidding strategy, scaling readiness, identifies campaigns to kill/scale using specific rules) and 'when' (explicit 'Use when user says...' clause with trigger terms). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'budget allocation', 'bidding strategy', 'ad spend', 'ROAS target', 'media budget', 'scaling'. These are terms practitioners naturally use when discussing ad platform budget decisions. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around budget allocation and bidding strategy for ad platforms. The specific frameworks (70/20/10 rule, 3x Kill Rule) and domain-specific triggers (ROAS target, media budget) make it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with clear decision frameworks, specific thresholds, and well-structured validation steps. The main weakness is potential redundancy between the extensive inline content and the referenced external files, plus some minor verbosity in explaining bidding type definitions. The concrete rules (3x Kill Rule, 20% scaling rule, 70/20/10) and decision tables make this highly executable.
Suggestions
Clarify the relationship between inline content and referenced files (budget-allocation.md, bidding-strategies.md) — either keep detailed frameworks in references and summarize here, or remove the reference reads if the content is fully inline.
Trim bidding type descriptions that merely restate what the name implies (e.g., 'Lowest Cost: maximize conversions within budget') to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is fairly comprehensive but includes some information Claude could infer (e.g., basic definitions of bidding types like 'Lowest Cost: maximize conversions within budget'). The tables and decision trees are dense but mostly earn their place as reference material. Some sections like MER explanation are slightly padded. | 2 / 3 |
Actionability | Highly actionable with specific rules (70/20/10, 3x Kill Rule, 20% scaling rule), concrete thresholds (≥20 clicks, ≥$100 spend, ≥14 days), decision trees with exact conversion count breakpoints, and specific budget minimums per platform. The kill decision framework table provides exact scenarios with required data and actions. | 3 / 3 |
Workflow Clarity | The process section has a clear numbered sequence with two explicit validation checkpoints (step 6: confirm ≥14 days data, step 8: verify kill list candidates have sufficient data). The kill decision framework includes data sufficiency requirements before action, creating an implicit feedback loop that prevents premature decisions. | 3 / 3 |
Progressive Disclosure | The skill references external files (budget-allocation.md, bidding-strategies.md, benchmarks.md, scoring-system.md) in the process steps, which is good progressive disclosure. However, the SKILL.md itself contains extensive inline content (bidding decision trees, platform matrices, scaling rules) that significantly overlaps with what those reference files likely contain, making it unclear what value the references add versus what's already here. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- AgriciDaniel/claude-ads
- Commit
c2ca51f
- Reviewed
Table of Contents
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.