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.
57
36%
Does it follow best practices?
Impact
97%
1.22xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/competitive-ads-extractor/SKILL.mdQuality
Discovery
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 identifies a clear niche (competitor ad library analysis) with good natural trigger terms that users would actually say. However, it lacks an explicit 'Use when...' clause and could be more specific about the concrete actions performed. The second-person voice ('your own ad campaigns') should also be corrected to third person.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to research competitor ads, analyze ad libraries, or benchmark advertising creative and messaging.'
Replace second-person 'your own ad campaigns' with third-person phrasing like 'the user's ad campaigns' or rephrase to 'Inspires and improves ad campaign strategy based on competitive insights.'
List more specific concrete actions, e.g., 'categorize messaging themes, identify calls-to-action, compare creative formats, and surface trending ad approaches.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (competitor ad analysis from ad libraries) and some actions (extracts, analyzes), but doesn't list multiple concrete specific actions like 'categorize messaging themes, identify CTAs, compare creative formats'. | 2 / 3 |
Completeness | The 'what' is reasonably covered (extracts and analyzes competitor ads from ad libraries), but there is no explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'competitors' ads', 'ad libraries', 'Facebook', 'LinkedIn', 'messaging', 'creative', 'ad campaigns'. Good coverage of terms a user researching competitor advertising would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The niche of extracting competitor ads specifically from ad libraries (Facebook, LinkedIn) is quite distinct and unlikely to conflict with other skills. The combination of 'ad libraries' + 'competitors' ads' creates a clear, unique trigger space. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is fundamentally hollow—it describes what a competitive ads extraction tool would do in extensive detail but provides zero actual implementation. There are no executable commands, no API integrations, no scraping code, and no tool configurations. The bulk of the content is aspirational marketing copy about the skill itself rather than actionable instructions Claude can follow.
Suggestions
Replace the fabricated example with actual executable code for accessing Facebook Ad Library (e.g., using their public API or browser automation with specific selectors and URLs).
Remove all the filler sections ('When to Use', 'What You Can Learn', 'Tips for Success', 'Related Use Cases', 'Output Formats') that describe the skill rather than instruct Claude how to perform it.
Add concrete tool usage: specify which MCP tools, browser automation steps, or API endpoints to use, with real code examples for at least one platform.
Add validation steps for the scraping workflow—how to verify ads were captured correctly, handle rate limiting, deal with missing data, and confirm screenshot quality.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive sections that add little actionable value. Lists like 'When to Use This Skill', 'What You Can Learn', 'Tips for Success', 'Related Use Cases', and 'Output Formats' are padded filler that Claude doesn't need. The example output alone is ~80 lines of fabricated data. The entire skill could be condensed to under 30% of its current length. | 1 / 3 |
Actionability | Despite its length, the skill contains zero executable code, no actual scraping commands, no API calls, no tool usage instructions, and no concrete implementation details. The 'example' is entirely fabricated output with no real mechanism for how to actually extract ads from Facebook Ad Library or any other platform. The prompts shown are just natural language requests with no backing implementation. | 1 / 3 |
Workflow Clarity | The workflows listed (e.g., 'Ad Campaign Planning', 'Positioning Research') are vague high-level steps with no validation checkpoints, no error handling, and no concrete tool or command sequences. There's no guidance on what to do when scraping fails, rate limits are hit, or data is incomplete. The 'process' in the example is a fictional progress bar, not a real workflow. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files. Everything is inline despite the massive length. Sections like 'What You Can Learn', 'Common Workflows', 'Tips for Success', 'Output Formats', and 'Related Use Cases' could either be removed or split into separate reference files. The structure creates the illusion of organization but is actually repetitive and poorly layered. | 1 / 3 |
Total | 4 / 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
- Lingjie-chen/MT5
- Commit
3069d33
- 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.