Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a well-structured editorial playbook with strong actionability, a clear sequenced framework with audit checkpoints, and exemplary progressive disclosure via one-level-deep references that all resolve to real files. Its only real weakness is conciseness: the core failure-mode framing and the 12-consideration framework recap material already covered in earlier sections.
Suggestions
Consolidate the repeated bloggy-long/academic-bloat framing: define it once in its dedicated section and reference it from the intro, failure modes, and closing rather than restating each time.
Trim the '12 considerations' section to either new synthesis or cross-references to the detailed sections, since it currently restates the lede, section-weight, citation, visual, and closing guidance already covered above.
Consider moving the rapid-fire 'Common failure modes' list (which overlaps the closing-patterns and lede-patterns sections) entirely into common-long-form-failures.md and keeping only a brief pointer in the body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient and assumes editorial competence, but the bloggy-long/academic-bloat framing is restated in the intro, its own section, the failure modes, and the closing, and the '12 considerations' section largely recapitulates the preceding sections. It is not at 3 because some material could be tightened without loss; it is not at 1 because it does not explain basic concepts Claude already knows and most tokens carry load. | 2 / 3 |
Actionability | As an instruction-only skill it provides concrete, specific guidance: named lede and closing patterns, exact section-weight percentages (e.g. 'Body 60-70%'), and explicit audit tests ('If one section is more than 3x the length of another bearing similar argumentative load...'). The rubric does not penalize absence of code when guidance is this actionable, so it reaches 3; it is not at 2 because the guidance is copy-ready and specific rather than abstract. | 3 / 3 |
Workflow Clarity | The '12 considerations for long-form content' provides a clearly sequenced planning/auditing workflow, and audits like the 3x section-weight test and the litmus test ('would cutting this section weaken the argument') act as explicit checkpoints. It is not at 2 because the sequence and checkpoints are explicit; it is not a destructive/batch operation, so missing validation feedback loops do not cap it. | 3 / 3 |
Progressive Disclosure | Each major section closes with a one-level-deep, clearly signaled reference ('Detail in [`references/...`]'), all nine referenced files exist in the bundle, and a 'Reference files' index lists them with descriptions. It is not at 2 because the split is clean and navigation is easy rather than ad-hoc. | 3 / 3 |
Total | 11 / 12 Passed |