Content
42%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is well-structured and rich with examples, but it is verbose due to repeated restatements of the same use cases, offers only placeholder prompts without executable extraction detail, and lacks validation checkpoints for its batch scraping workflow.
Suggestions
Collapse redundant sections ('What You Can Learn', 'Related Use Cases', 'Tips for Success') into the existing 'When to Use' and 'What This Skill Does' sections to cut repetition.
Add validation checkpoints to the extraction workflow (e.g., verify expected ad count, confirm all screenshots saved before analyzing).
Move the large worked Notion example into a references/ file (e.g., EXAMPLE.md) and link to it, keeping SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Sections such as 'What You Can Learn', 'Related Use Cases', 'Tips for Success', and 'Output Formats' largely restate 'What This Skill Does' and 'When to Use This Skill', creating several padded, repetitive blocks rather than lean guidance. | 2 / 5 |
Actionability | Prompt templates like 'Extract all current ads from [Competitor Name] on Facebook Ad Library' give some concrete guidance, but they are placeholder prompts with no executable code or technical extraction details, leaving key implementation steps missing. | 3 / 5 |
Workflow Clarity | Sequenced steps exist ('What This Skill Does' and 'Common Workflows'), but this batch scraping operation has no validation/verification checkpoints (e.g., confirm screenshots saved, verify ad count), capping workflow clarity at 3. | 3 / 5 |
Progressive Disclosure | The file is well-sectioned with headers, but everything is inlined in one ~290-line SKILL.md with no bundle references, and the large worked example (~90 lines) is content that could live in a separate reference file. | 3 / 5 |
Total | 11 / 20 Passed |