Content
86%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 well-structured, token-efficient instruction skill: lean per-platform guidance, a clear clarify→adapt→deliver workflow, and a pre-delivery quality checklist, all appropriately inlined with no unnecessary bundle files. The gaps are the absence of a worked example demonstrating platform-native adaptation and the lack of a remediation step when the Quality Gate fails.
Suggestions
Add one compact worked example in the Repurposing Flow: a single source idea shown as a platform-native X post and a LinkedIn post, so the 'adapt, don't cross-post' rule is concrete rather than only stated.
Extend the Quality Gate with a remediation loop, e.g., 'If a draft fails: re-check the hook against the first-3-seconds / first-line rule, cut to one idea, then re-run the gate,' to give the validation checkpoint a feedback path.
Tighten actionability further by replacing a few abstract directives with measurable checks (e.g., 'hooks are strong and specific' → 'the hook names a concrete result, number, or mistake in the first line').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence throughout — no explanation of what the platforms are or how social content works; every section ("Core Rules", per-platform bullets, "Repurposing Flow", "Quality Gate") carries only directive content. This matches 'Lean and efficient; assumes Claude's competence; every token earns its place'; there is no padded or over-explained passage that would pull it to a 4. | 5 / 5 |
Actionability | The guidance is concrete and instruction-specific rather than abstract: "first 3 seconds must interrupt attention", "refresh the visual every 20-30 seconds", "extract 3-7 atomic ideas", "keep links out of the main body unless necessary". Per the scoring note this is an instruction-only skill, so absent code is not penalized, but it stops short of the top anchor ('specific examples cover the common cases') because it contains no worked example — e.g., one source idea rendered as an X post vs. a LinkedIn post — which would make the platform-native distinction fully concrete. | 4 / 5 |
Workflow Clarity | There is a clear sequence with an explicit validation checkpoint: "First Questions" (gather inputs) → "Core Rules" → "Repurposing Flow" numbered cascade ("1. anchor asset ... 5. align CTAs") → "Deliverables" → "Quality Gate" ("Before delivering: each draft reads natively..."). This satisfies 'Clear sequence with most checkpoints present'. Not a 5 because the Quality Gate is a checklist without a feedback loop — nothing says what to do when a draft fails the gate (which rule to revisit, how to re-check) — so the error-recovery element of the top anchor is missing. | 4 / 5 |
Progressive Disclosure | No bundle files exist (references/, scripts/, assets/ are absent) and none are needed: the body is compact (~85 lines), organized under clear headers ("When to Activate", "Platform Guidance", "Repurposing Flow", "Deliverables", "Quality Gate"), and all inline content is core guidance that any invocation would need — nothing belongs in a separate reference file. Per the rubric's simple-skill exception, well-organized sections with no need for external references score 5; there are no nested or buried references that would lower it. | 5 / 5 |
Total | 18 / 20 Passed |