ads-linkedin
LinkedIn Ads deep analysis for B2B advertising. Evaluates 27 checks across technical setup, audience targeting, creative quality, lead gen forms, and bidding strategy. Includes Thought Leader Ads, ABM, and predictive audiences. Use when user says LinkedIn Ads, B2B ads, sponsored content, lead gen forms, InMail, or LinkedIn campaign.
82
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ads-linkedin/SKILL.mdQuality
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 a strong skill description that clearly defines its scope (LinkedIn Ads deep analysis), lists specific capabilities (27 checks across 5 domains plus specialized features), and provides explicit trigger guidance with natural user terms. It follows third-person voice, is concise without being vague, and occupies a clearly distinct niche.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: 'Evaluates 27 checks across technical setup, audience targeting, creative quality, lead gen forms, and bidding strategy' plus specific features like 'Thought Leader Ads, ABM, and predictive audiences.' | 3 / 3 |
Completeness | Clearly answers both 'what' (deep analysis evaluating 27 checks across multiple dimensions) and 'when' (explicit 'Use when user says...' clause with specific trigger terms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'LinkedIn Ads, B2B ads, sponsored content, lead gen forms, InMail, LinkedIn campaign.' These are all terms a user would naturally use when seeking help with LinkedIn advertising. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche focused specifically on LinkedIn Ads and B2B advertising. The platform-specific terms (LinkedIn, InMail, Thought Leader Ads, ABM) make it very unlikely to conflict with other ad platform skills or general marketing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%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 LinkedIn Ads audit skill with clear categorization, specific benchmarks, and good progressive disclosure to reference files. Its main weaknesses are the lack of validation checkpoints in the workflow (important for a complex 27-check audit), some redundancy in benchmark data presentation, and reliance on external files for the actual scoring methodology without providing enough inline detail to execute independently. The actionability is moderate—strong on what to evaluate but weaker on how to calculate and validate the final score.
Suggestions
Add a validation checkpoint after step 5 (e.g., 'Verify all 27 checks have a PASS/WARNING/FAIL status before calculating score; flag any checks where data was unavailable as N/A and adjust weights accordingly').
Include a brief inline scoring formula or example calculation so the skill is partially self-contained even without the external scoring-system.md file (e.g., 'Score = Σ(category_weight × checks_passed/total_checks × 100)').
Remove redundant benchmark mentions—the TLA CPC range and standard SC CPC appear both in the TLA section and the LinkedIn Context table; consolidate to one location.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and bullet points, but includes some unnecessary context Claude would know (e.g., explaining what Thought Leader Ads are, what ABM stands for). The TLA section repeats engagement stats that could be consolidated. Some benchmark data is useful but the LinkedIn Context table partially duplicates information already stated in the checks above. | 2 / 3 |
Actionability | Provides concrete check IDs, specific thresholds, and clear pass/warning/fail criteria which are highly actionable. However, the actual audit execution relies entirely on external reference files (linkedin-audit.md, benchmarks.md, scoring-system.md) without providing the scoring calculation method inline. The process steps are more of a checklist than executable instructions—no concrete commands or code for data collection or score calculation. | 2 / 3 |
Workflow Clarity | The 7-step process at the top provides a clear sequence, and the output section shows expected deliverables. However, there are no validation checkpoints—no guidance on what to do if data is incomplete, if reference files are missing, or how to handle edge cases like accounts with no TLA history. For a 27-check audit with scoring, the absence of a verify/reconcile step before final output is a gap. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear references to external files (linkedin-audit.md, benchmarks.md, scoring-system.md) that are one level deep and well-signaled in the process steps. The main skill provides a comprehensive overview with key thresholds and context inline while deferring the full 27-check details to reference files. Sections are logically organized by audit category. | 3 / 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
402ba63
- 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.