ads-audit
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads accounts. Generates health score per platform and aggregate score. Use when user says audit, full ad check, analyze my ads, account health check, or PPC audit.
84
81%
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 hits all the key criteria. It clearly specifies what the skill does (multi-platform ad auditing with health scoring), names the exact platforms supported, and provides explicit trigger terms in a 'Use when' clause. The description is concise yet comprehensive, making it easy for Claude to select this skill appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: multi-platform paid advertising audit, parallel subagent delegation, analyzes specific platforms (Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, Microsoft Ads), generates health scores per platform and aggregate score. | 3 / 3 |
Completeness | Clearly answers both 'what' (multi-platform paid advertising audit, analyzes specific ad platforms, generates health scores) and 'when' with an explicit 'Use when...' clause listing specific trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'audit', 'full ad check', 'analyze my ads', 'account health check', 'PPC audit'. Also names specific platforms (Google Ads, Meta Ads, etc.) which users would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: multi-platform paid advertising audits with specific platform names and the concept of health scoring. Unlikely to conflict with other skills due to the very specific domain of paid advertising account auditing. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration skill with clear workflow sequencing and validation checkpoints. Its main weaknesses are the lack of concrete executable examples (how to actually invoke subagents, what data structures look like) and some inline verbosity in the report structure section that could be offloaded to reference files. The scoring tables and priority definitions add value but the overall content could be more concise.
Suggestions
Add a concrete example of how to invoke/delegate to subagents (e.g., actual tool calls or function signatures) rather than just listing their names
Move the detailed Report Structure section to a separate template file (e.g., `ads/references/report-template.md`) and reference it with a one-line link
Include a brief example of expected subagent return format (e.g., JSON schema with platform score, findings array, quick wins) to make the validation step in step 6 actionable
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some sections that could be tightened—the report structure section is quite detailed and prescriptive about things Claude could infer (e.g., what an executive summary contains). The priority definitions and some table content are useful but border on over-specification for an orchestration skill. | 2 / 3 |
Actionability | The skill provides a clear process and references subagents and scoring files, but lacks executable code or concrete commands. The delegation step says 'if available, otherwise run inline sequentially' without specifying how to invoke subagents. The scoring formula is given but the actual calculation logic defers to an external file. No concrete examples of input/output are provided. | 2 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced with two explicit validation checkpoints: one before proceeding (confirm data availability) and one before aggregating (verify subagent scores). The workflow includes clear delegation steps, a defined scoring phase, and output generation. The Quick Wins criteria include a decision logic for prioritization. | 3 / 3 |
Progressive Disclosure | The skill references `ads/references/scoring-system.md` for the full scoring algorithm and names subagent skills, which is good progressive disclosure. However, the report structure section is very detailed inline content (executive summary, per-platform sections, cross-platform analysis, strategic recommendations) that could be split into a separate template or reference file. The balance between overview and inline detail is imperfect. | 2 / 3 |
Total | 9 / 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.