Content
81%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 a lean, actionable, well-sequenced agent-executed skill with explicit validation and fix loops. Its main improvement levers are adding a full example output post and optionally offloading a catalog or two to reference files.
Suggestions
Include one fully rendered example output post (with frontmatter) so the agent has a copy-paste-ready template, not just example briefs.
Consider moving the framing catalog or voice-guide resolution chain into a reference file to shorten SKILL.md and sharpen the overview.
Tighten the parenthetical rationales in the LinkedIn-Specific Defaults section to pure directives where the why is obvious.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Efficient and domain-specific rather than padded — defaults, framings, and checks are operational, not general knowledge — with only minor rationale commentary (e.g. 'LinkedIn rewards longer than X but shorter than a blog post') that could be trimmed. | 4 / 5 |
Actionability | Provides concrete invocation commands, a framing table with structure and when-to-use, file-naming conventions, a frontmatter template, and a 7-point self-check list; the main gap is the absence of a full example output post alongside the example briefs. | 4 / 5 |
Workflow Clarity | A clear 6-phase sequence with an explicit validation checkpoint in Phase 4 (self-check) and fix loops ('rewrite', 'Add a why this matters beat if missing'), satisfying the batch-operation feedback-loop expectation. | 5 / 5 |
Progressive Disclosure | Well-organized with clear section headers, no nested references, and self-contained navigation, though at ~154 lines the framing catalog or voice-guide resolution chain could optionally be split into reference files. | 4 / 5 |
Total | 17 / 20 Passed |