paid-ads-tiktok

Audit, diagnose, and safely operate connected TikTok Ads accounts through the NotFair MCP. Use for TikTok advertising, Spark Ads, short-form video ads, campaign or ad-group analysis, spend, conversions, targeting, creative, budgets, bids, creator briefs, campaign setup, or approved TikTok Ads changes.

Quality

86%

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

81%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.

A well-structured, action-oriented operating manual that respects Claude's intelligence and embeds the right validation safeguards for destructive ad-account mutations. The main improvement opportunity is adding a local reference file for the denser platform-interpretation rules to improve progressive disclosure.

Suggestions

Move the platform-interpretation rules (currency units, API code semantics, rate limits, timezone/reporting lag) into a local references file and link to it, keeping SKILL.md as a leaner overview.

Add one concrete example of the preview/apply/read-back write cycle with representative entity fields to strengthen actionability for the safe-mutation workflow.

Clarify which read capability to use for the initial 'harmless account/setup read' so the diagnose step is unambiguous across connector versions.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with platform-specific gotchas ('currency units, not micros', 'API code must be zero even when HTTP is 200', 'long IDs must be preserved as strings'), with only minor phrasing that could be trimmed.	4 / 5
Actionability	Concrete, executable guidance is given throughout ('Resolve `~~tiktok-ads`', 'Record the advertiser currency, timezone, objective...', 'Preview, obtain approval, apply once, then read back'), though it is instruction-only with no literal code or commands.	4 / 5
Workflow Clarity	A clearly sequenced three-phase process (establish scope, diagnose, execute) with explicit validation checkpoints — approval before mutation, read-back after, rollback triggers, and 'stop before claiming live access' on authorization failure — satisfying the destructive-operation feedback-loop requirement.	5 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep references at the top ('../shared/operating-contract.md', '../shared/measurement-framework.md', '../../docs/mcp-connection.md'), though those references point outside the skill's own bundle rather than to local reference files.	4 / 5
	Total	17 / 20 Passed

Description

92%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.

A strong, third-person description that clearly states both capability and trigger conditions with concrete domain-specific terms. Minor scope for adding synonym/extension variants to reach full trigger-term comprehensiveness.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('Audit, diagnose, and safely operate', 'campaign or ad-group analysis, spend, conversions, targeting, creative, budgets, bids, creator briefs, campaign setup') with comprehensive coverage of the TikTok Ads domain.	5 / 5
Completeness	It explicitly answers both 'what' ('Audit, diagnose, and safely operate connected TikTok Ads accounts through the NotFair MCP') and 'when' ('Use for TikTok advertising, Spark Ads...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keyword coverage including 'TikTok advertising, Spark Ads, short-form video ads, spend, conversions, targeting, budgets, bids', but lacks synonyms/file-extension variants that would push it to the top anchor.	4 / 5
Distinctiveness Conflict Risk	The niche is tightly scoped to TikTok Ads via the NotFair MCP with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: nowork-studio/notfair-plugin
Path: paid-ads/paid-ads-tiktok/SKILL.md
Commit: 5094263

Reviewed: 5 days 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.