Content
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose, spending many tokens on concepts Claude already understands (how to plan content, what makes good writing, basic research practices). It lacks concrete examples—no sample post, no 'Normal vs Better' comparison, no actual prompt text—which undermines its core message of 'show, don't just tell.' The workflow structure is reasonable but would benefit from inline validation criteria and at least one complete example output.
Suggestions
Cut the 'When to Use This Skill' section and 'Key Principles' section entirely—these restate things Claude already knows and are covered by the skill description and writing guidelines file.
Add a concrete example: include a complete short sample post (or a 'Normal vs Better' comparison) inline so Claude can see the target output format without needing to reference external files.
Inline the key quality checklist criteria from writing-guidelines.md into step 4, so the validation step is self-contained and actionable without requiring a file lookup.
Add an explicit review/validation step after drafting (e.g., 'Verify: Does the post contain at least 3 concrete examples? Does it include a Normal vs Better comparison? Are all dates and version numbers verified?').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is verbose and explains many things Claude already knows—how to plan content, what a hook is, what a call-to-action is, how to research a topic. The 'When to Use This Skill' section repeats the description. The 'Key Principles' section restates common writing advice (show don't tell, make it actionable, verify facts) that Claude inherently understands. Much of this could be cut to a fraction of its length. | 1 / 3 |
Actionability | The skill provides a structured workflow and references templates/guidelines, but lacks any concrete executable examples—no sample post excerpt, no actual 'Normal vs Better' comparison, no example prompt text. The guidance remains at the level of 'fill in the template' and 'apply the checklist' without showing what good output looks like. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and includes a research checklist, which is good. However, there are no validation checkpoints after drafting—no review step that verifies the output against specific criteria before sharing, and no feedback loop for revision. The checklist in step 4 references an external file without providing the actual criteria inline. | 2 / 3 |
Progressive Disclosure | The skill references `references/writing-guidelines.md` and `assets/post-template.md` with brief descriptions of their contents, which is good structure. However, no bundle files were provided, so these references are unverifiable. The main file also contains substantial inline content that overlaps with what the referenced files presumably cover (tone, structure, quality standards), suggesting poor separation of concerns. | 2 / 3 |
Total | 7 / 12 Passed |