ads-tiktok
TikTok Ads deep analysis covering creative quality, tracking, bidding, campaign structure, and TikTok Shop. Evaluates 28 checks with emphasis on creative-first strategy, safe zone compliance, and Smart+ campaigns. Use when user says TikTok Ads, TikTok marketing, TikTok Shop, Spark Ads, Smart+, or TikTok 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-tiktok/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 (TikTok Ads deep analysis), lists specific capabilities (28 checks across creative quality, tracking, bidding, campaign structure), and provides explicit trigger guidance with natural user terms. It uses proper third-person voice and is concise without being vague. The description effectively carves out a distinct niche that would be easy for Claude to match against user requests.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: creative quality evaluation, tracking, bidding, campaign structure, TikTok Shop analysis, 28 checks, safe zone compliance, Smart+ campaigns, and creative-first strategy. | 3 / 3 |
Completeness | Clearly answers both 'what' (deep analysis covering creative quality, tracking, bidding, campaign structure, TikTok Shop with 28 checks) and 'when' (explicit 'Use when user says...' clause with specific trigger terms). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'TikTok Ads', 'TikTok marketing', 'TikTok Shop', 'Spark Ads', 'Smart+', 'TikTok campaign'. These cover the main variations a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche focused specifically on TikTok Ads analysis. The platform-specific triggers (TikTok Shop, Spark Ads, Smart+) and domain-specific terminology (safe zone compliance, creative-first strategy) make it very unlikely to conflict with other 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 TikTok Ads audit skill with strong progressive disclosure and clear categorization of checks with specific thresholds. Its main weaknesses are the inclusion of general TikTok marketing knowledge that Claude already knows (creative-first philosophy, UGC outperforming studio content) and the lack of validation checkpoints in the workflow for what is a complex multi-step audit process. The actionability is moderate — strong on criteria definition but weak on executable implementation details.
Suggestions
Remove or significantly trim the 'Creative-First Strategy' and 'What Makes a TikTok Ad Work' sections — Claude already knows these marketing principles; keep only the specific thresholds and check criteria.
Add validation checkpoints to the workflow: e.g., 'Verify all 28 checks have a status before calculating score' and 'If data is missing for a check, mark as UNABLE_TO_ASSESS and note in report'.
Add a concrete example of how a single check evaluation looks (e.g., 'T05: 4 creatives found → WARNING (3-5 range), recommendation: add 2+ creatives') to make the audit process more actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and structured lists, but includes some unnecessary explanatory content Claude already knows (e.g., 'Creative-First Strategy' section explaining what makes TikTok ads work is general marketing knowledge, not actionable instruction). The 'TikTok Context' table and some benchmark data could be deferred to the referenced files. | 2 / 3 |
Actionability | Provides concrete check IDs, specific thresholds, and clear pass/warning/fail criteria which are highly actionable. However, there's no executable code, no example of how to parse Ads Manager exports, and the process steps are high-level directions ('Collect TikTok Ads data') without specifying exact commands or tool usage. The safe zone diagram and threshold tables are strong, but the skill reads more as a checklist specification than step-by-step executable guidance. | 2 / 3 |
Workflow Clarity | The 8-step process at the top provides a clear sequence, and the weighted scoring categories are well-defined. However, there are no validation checkpoints or feedback loops — no guidance on what to do if reference files are missing, if data is incomplete, or how to handle edge cases like accounts without TikTok Shop. For a 28-check audit involving scoring calculations, the absence of explicit verification steps caps this at 2. | 2 / 3 |
Progressive Disclosure | Excellent use of progressive disclosure — the skill provides a clear overview and process, then references four specific files (tiktok-audit.md, benchmarks.md, platform-specs.md, scoring-system.md) for detailed content. References are one level deep and clearly signaled in the process steps. The main file contains enough context to understand the audit without needing to read the references first. | 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.