map

为 shiji-kb wiki 页面从谭其骧《中国历史地图集》自动裁切历史地图截图，并生成 frontmatter images 片段。适用于 type=place（地名）和 type=state（诸侯国/侯国/邦国）页面。当用户说 /map PAGE、/map PAGE 时间、/map PAGE all 时触发；/enrich 对 state/place 类型页面补图时也应调用。前提：页面 frontmatter 必须有 coords 字段（无 coords 则先补 coords 再调用）。

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body with executable commands, explicit validation, and clean references to real bundle files. The main gap is that the batch/write workflow's error recovery is a static FAQ table rather than an inline validate-fix-retry loop.

Suggestions

Replace or augment the static 常见问题 FAQ with an explicit validate→fix→retry loop in 第二步 (e.g., 'if ✓ line is missing, re-check coords and re-run') to strengthen the feedback loop for this batch/write operation.

Tighten the 地理范围注册表 section by moving the field-by-field schema description into map_extents.json as an inline _comment or a sibling doc, keeping SKILL.md focused on how to use the registry.

Add a one-line note on when to use --crop-deg 2.0 vs 4.0 defaults so the crop-range guidance is proactive rather than only surfaced in the troubleshooting table.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes competence; the coords-source table and FAQ are domain-specific knowledge Claude lacks and earn their place, with only minor trimming opportunities in the registry explanation.	4 / 5
Actionability	Fully executable, copy-paste-ready commands covering common cases — `python3 .claude/skills/map/scripts/map_page.py {PAGE} --write`, `--list-maps`, `{时代}`, `--crop-deg 4.0` — with flags and expected behavior specified.	5 / 5
Workflow Clarity	Clear two-step sequence (confirm 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 a troubleshooting table, though error recovery is a static FAQ rather than a validate→fix→retry loop.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview pointing to one-level-deep, clearly-signaled bundle files — scripts/map_page.py (with full path) and references/map_extents.json (with field schema) — making navigation easy and content appropriately split.	5 / 5
	Total	18 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with explicit trigger terms and a clear what/when structure, scoped to a distinct niche. The only minor weakness is that the core action set is just two verbs, slightly limiting specificity breadth.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — '自动裁切历史地图截图' and '生成 frontmatter images 片段' — tied to a specific source (谭其骧《中国历史地图集》) and output target, with minor coverage gaps (only two core actions).	4 / 5
Completeness	Clearly answers both 'what' (crop map screenshots, generate frontmatter images fragment) and 'when' (当用户说 /map PAGE... 时触发; /enrich... 也应调用) with concrete trigger phrases, and adds a prerequisite (coords field).	5 / 5
Trigger Term Quality	Explicit, natural trigger phrases users would actually say — '/map PAGE、/map PAGE 时间、/map PAGE all' plus the /enrich invocation — give comprehensive coverage of the skill's invocation surface.	5 / 5
Distinctiveness Conflict Risk	Clear niche (谭图 map cropping for type=place/state pages) with distinct /map and /enrich triggers and a coords prerequisite, minimizing overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: baojie/shiji-kb
Path: .claude/skills/map/SKILL.md
Commit: 6b836e3

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.