Content
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A lean, actionable skill body: concrete executable commands, a clear sequenced workflow with an explicit validation checkpoint, and well-signaled references to the real registry/script bundle files. No verbosity or off-topic explanation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and project-specific — tables for coord-source priority and common problems, code blocks for commands — with no padding about concepts Claude already knows; the 史记三家注/汉书·地理志 notes are genuine domain context, not fluff, so every token earns its place. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready commands such as 'python3 .claude/skills/map/scripts/map_page.py {PAGE} --write' with concrete flags (--list-maps, --crop-deg 4.0, {时代}), specific file paths, and exact validation output to look for. | 3 / 3 |
Workflow Clarity | Clear two-step sequence (confirm/research coords → run script with --write) with an explicit validation checkpoint ('脚本末尾应出现 ✓ {PAGE} rev=...，否则写入失败') and error-recovery guidance in the common-problems table, so the batch/destructive write is not left unvalidated. | 3 / 3 |
Progressive Disclosure | Body is a concise overview that one-level-deep references the real bundle files — scripts/map_page.py (invoked in commands) and references/map_extents.json (described as a registry with its field schema and how to extend it) — keeping the heavy map-extent data out of the overview. | 3 / 3 |
Total | 12 / 12 Passed |