competitive-ads-extractor

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

1.22x

Quality

54%

Does it follow best practices?

Impact

97%

1.22x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/competitive-ads-extractor/SKILL.md

Quality

Content

38%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.

The skill is well-organized with clear headers and useful example formats, but it is verbose, lacks executable guidance or real tooling, omits validation for its batch scraping step, and inlines reference-grade material instead of splitting it into bundle files.

Suggestions

Trim sections that restate marketing knowledge Claude already has ('What You Can Learn', 'Related Use Cases', 'Tips for Success') and compress the illustrative Output example.

Add concrete, executable guidance — real scraping commands/tools or library references — instead of pseudocode like 'Accessing Facebook Ad Library...'.

Insert an explicit validation checkpoint after batch extraction (e.g., confirm all screenshots saved and ad count matches the library total) and split the detailed output template and example analysis into references/ files.

Dimension	Reasoning	Score
Conciseness	The ~330-line body is noticeably verbose, restating marketing concepts Claude already knows ('What You Can Learn', 'Related Use Cases', 'Tips for Success', 'Best Practices') and padding a large illustrative Output block with fabricated percentages and ad inventories.	2 / 5
Actionability	Concrete example prompts and a detailed output template are provided, but there is no executable code, real scraping tooling, or library references; the 'Process' block is illustrative pseudocode rather than runnable instruction, leaving guidance incomplete.	3 / 5
Workflow Clarity	Numbered workflows exist but describe user-side planning rather than technical execution, and the batch scraping step (saving many ad screenshots) has no validation/verification checkpoint, which caps workflow clarity at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	No bundle files exist and the single ~330-line SKILL.md inlines content that clearly belongs in separate references (full output template, example analysis, 'What You Can Learn' reference); section headers provide some structure but heavy inlining keeps it below the midpoint.	2 / 5
	Total	10 / 20 Passed

Description

70%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.

The description is specific, uses natural trigger terms, and carves out a distinct niche, but it omits an explicit 'Use when...' clause, leaving the activation trigger only implied and capping completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when researching competitor ad strategies, finding ad inspiration, or analyzing messaging on Facebook/LinkedIn ad libraries.'

Include more natural synonyms users say, such as 'ad spy', 'Facebook Ad Library', 'TikTok ads', and 'competitor creative'.

Keep the concrete action list but pair it with the trigger clause to lift completeness from 3 to 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('competitors' ads from ad libraries') and several concrete actions — 'Extracts and analyzes', 'understand what messaging, problems, and creative approaches are working' — but 'understand ... are working' is somewhat abstract, leaving minor coverage gaps below a 5.	4 / 5
Completeness	Clearly states what the skill does (extracts and analyzes competitor ads), but the 'when' is only weakly implied and there is no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('competitors' ads', 'ad libraries', 'messaging', 'ad campaigns', Facebook/LinkedIn) with good coverage, but is missing common synonyms like 'ad spy', 'Facebook Ad Library' as a set phrase, or platform variations like TikTok.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — competitor ad-library analysis with named platforms (Facebook, LinkedIn) — giving it distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/competitive-ads-extractor/SKILL.md
Commit: a9fa86d

Reviewed: about 19 hours 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.