Content
85%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.
A highly actionable, well-sequenced workflow with strong validation checkpoints, only slightly let down by minor marketing padding and a monolithic structure that inlines content which could be split into reference files.
Suggestions
Move the detailed Apify API call/polling reference and the per-tool CSV column maps into separate reference files (e.g., references/apify-api.md, references/export-formats.md) and link to them from SKILL.md to improve progressive disclosure.
Trim marketing-style asides ('That's it. One env var. Nothing else.', the repeated 'No LinkedIn cookies' tagline) for tighter token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely lean concrete reference material assuming Claude's competence, with only minor trimmable marketing lines ('That's it. One env var. Nothing else.') and a repeated 'No LinkedIn cookies' mantra. | 4 / 5 |
Actionability | Provides fully executable curl commands with real endpoints and JSON payloads, exact polling patterns, per-unit costs, and complete per-tool CSV column schemas that are copy-paste ready and cover the common cases. | 5 / 5 |
Workflow Clarity | Six clearly sequenced phases with explicit validation checkpoints (confirm lead count before research, sample-then-iterate loop, character-limit enforcement, final user-confirmation gate) plus an error-handling table for recovery. | 5 / 5 |
Progressive Disclosure | Good internal section structure with headers, but the skill is a single monolithic file with no bundle references; the full Apify API detail, error catalog, and tool-specific column maps that could live in separate reference files are all inlined. | 3 / 5 |
Total | 17 / 20 Passed |