Content
82%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 lean, well-organized instruction skill: every section is directive with no filler, platform rules are specific, and the repurposing flow ends in an explicit quality gate. The main gaps are the absence of any worked input-to-output example and a quality gate that acts as a final checklist rather than a mid-process feedback loop.
Suggestions
Add one short worked example showing a single source claim adapted into an X post and a LinkedIn post, so the quality bar ('platform-native without persona drift') is demonstrable rather than only described.
Turn the Quality Gate into an explicit feedback loop in the Repurposing Flow (e.g., 'if any gate check fails, rewrite that draft and re-check before delivering') so validation is embedded mid-process, not only terminal.
Consider moving the per-platform adaptation rules into references/ files (e.g., references/platforms.md) to keep SKILL.md as a leaner overview, and clarify whether brand-voice/crosspost/x-api are sibling skills with on-disk paths.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is written in terse, instruction-dense fragments ('open with the strongest claim, artifact, or tension'; 'no praise-stacking, no "journey" filler') with zero explanation of concepts Claude already knows. Every line is directive; there is no padding to trim, matching the lean anchor 5 rather than anchor 4's 'minor instances that could be trimmed'. | 5 / 5 |
Actionability | Guidance is concrete and executable for an instruction-only skill: verbatim banned phrases, 'Extract 3 to 7 atomic claims or scenes', per-platform structural rules, and a deliverables list. It stops short of anchor 5 because there is no worked example (e.g., one source claim rendered as an X post vs. a LinkedIn post) demonstrating the output quality bar. | 4 / 5 |
Workflow Clarity | The Repurposing Flow is a clear 7-step sequence whose final step explicitly ties into the Quality Gate checklist, and Hard Bans supply remediation ('Delete and rewrite any of these'). It is below anchor 5 because the Quality Gate is a terminal checklist rather than an embedded validate-fix-retry loop mid-process. | 4 / 5 |
Progressive Disclosure | No bundle files exist, so everything is one flat, well-sectioned document that is easy to navigate — no buried or nested references. It sits at anchor 4 rather than 5 because the ~126-line body inlines per-platform adaptation rules that could be split into references/ files, and the related-skill pointers (brand-voice, crosspost, x-api) are listed without path context. | 4 / 5 |
Total | 17 / 20 Passed |