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

61%

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

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-sectioned and covers the workflow, but it is verbose with significant redundancy, lacks executable extraction detail and validation checkpoints, and keeps everything inline with no progressive disclosure. Tightening and concretizing would raise all dimensions.

Suggestions

Collapse the redundant capability/learnings/tips/related sections into one concise list and trim the fabricated example output to a compact representative snippet to recover token budget.

Replace vague 'Scrapes ads from Facebook Ad Library' with concrete, executable extraction steps (a specific site flow, tool, or script) so the guidance is copy-paste ready.

Add validation checkpoints to the workflows (e.g., confirm expected ad count retrieved, verify screenshots saved and non-empty, retry on partial fetches) since batch ad extraction is failure-prone.

Dimension	Reasoning	Score
Conciseness	The ~290-line body is padded with heavily redundant sections ("What You Can Learn", "Related Use Cases", "Tips for Success" restate "When to Use" and "What This Skill Does") and a ~90-line fabricated mock-output example; it does not teach known concepts, but it could be cut substantially without losing guidance.	2 / 3
Actionability	It gives concrete prompt templates and clear step lists, but the actual extraction mechanism ("Scrapes ads from Facebook Ad Library") is never specified with executable tools or commands, and the long Example is illustrative mock output rather than copy-paste-ready instruction.	2 / 3
Workflow Clarity	Sequenced steps are present in "Common Workflows" and "What This Skill Does", but there are no validation or verification checkpoints, and per the rubric batch/scraping operations missing validation should cap workflow clarity at 2.	2 / 3
Progressive Disclosure	The body is a single ~290-line monolithic file with no bundle files and no external references; it has section structure, but content that could be split out (the large example, detailed learnings) is inline rather than one level deep in referenced files.	2 / 3
	Total	8 / 12 Passed

Description

72%

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 clear, distinct, and uses natural trigger terms, but it omits an explicit "Use when..." clause and relies on only two truly concrete actions. Adding explicit trigger guidance and a fuller action list would lift it to top marks.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when researching competitor ad strategies, mining Facebook/LinkedIn ad libraries for messaging inspiration, or planning ad campaigns') to satisfy the 'when' half of completeness.

List more distinct concrete actions in the description (e.g., 'captures screenshots, categorizes ads by theme, and exports CSV reports') to move specificity from a partial action list to a comprehensive one.

Include the canonical phrase 'Facebook Ad Library' verbatim alongside 'LinkedIn ads' to maximize exact trigger-term matching.

Dimension	Reasoning	Score
Specificity	It names the domain and two concrete actions ("Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.)"), but the remaining verbs ("understand", "helps inspire and improve") are abstract, so it is not a comprehensive list of distinct concrete actions like the score-3 anchor.	2 / 3
Completeness	It clearly answers "what" (extract and analyze competitor ads) but has no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guideline "when" is only implied and completeness is capped at 2.	2 / 3
Trigger Term Quality	It covers natural terms a user would actually say — "competitors' ads", "ad libraries", "Facebook", "LinkedIn", "messaging", "ad campaigns" — giving good coverage of phrasings users would use when they need this skill.	3 / 3
Distinctiveness Conflict Risk	The niche is clear and narrow — competitor ad extraction/analysis from ad libraries — with distinct triggers unlikely to conflict with other skills, matching the score-3 anchor.	3 / 3
	Total	10 / 12 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: b79ed72

Reviewed: about 10 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.