Content
88%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 highly actionable with a rigorously gated, validated multi-step workflow and clean progressive disclosure into reference files. The main weaknesses are mild cross-step repetition and one broken reference (sub-agents/frame-worker.md).
Suggestions
Create sub-agents/frame-worker.md (or correct the path) so the repeated Step 4 / Quick Reference / directory-layout citations resolve.
Consolidate the 'one analyzer, trust it' and 'no narration' rules so they are stated once and merely back-referenced from Step 0 and Step 1.
Verify the ../hyperframes-core and ../hyperframes-creative cross-skill paths are reachable from this skill's install location.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Assumes Claude's competence with no concept padding, but the 'one analyzer, trust it' rule and the 'no narration/no website capture' point recur across the 'Two ideas' section, Step 0, and Step 1 — minor repetition that could be trimmed. | 4 / 5 |
Actionability | Every step ships copy-paste-ready bash with concrete flags and paths (init, analyze-beatgrid.py, validate-plan.mjs, assemble-index.mjs, hyperframes check/render), plus an explicit sub-agent dispatch context block. | 5 / 5 |
Workflow Clarity | Clear Step 0–6 sequence with an explicit Gate after each step, validation checkpoints (validate-plan.mjs, hyperframes check), and feedback loops (fix every ✗, re-dispatch failed workers and re-assemble); the batch/destructive operations carry validation, so no cap applies. | 5 / 5 |
Progressive Disclosure | Well-signaled one-level-deep references with a Read/When table and a directory layout, but sub-agents/frame-worker.md is referenced repeatedly and the sub-agents/ directory does not exist on disk — a minor navigation gap. | 4 / 5 |
Total | 18 / 20 Passed |