CtrlK
BlogDocsLog inGet started
Tessl Logo

create-maps-and-spatial-plans

创建、改造或审查由真实位置、边界、方向、尺度、路网、楼层或空间可达性驱动的地图与空间规划交付。用于定位与参考地图、导航路线、专题与分区地图、服务区和网络分析、场地总平面、楼层与室内导视;不用于以统计比较为主的数据图、可任意布局的抽象流程图或只把地图当背景的普通界面。

71

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

The body is a lean, well-structured instruction skill: dense without padding, clear sequenced workflow with validation gates, and exemplary progressive disclosure into two one-level reference files. The main gap is the absence of executable copy-paste examples for an otherwise highly actionable skill.

Suggestions

Add one or two minimal executable snippets (e.g., a MapLibre source/layer skeleton or an OSMnx route call) to lift actionability from concrete-guidance to copy-paste-ready.

Make the validate→adjust→recheck loops more explicit (mirroring section 8) so the feedback pattern reads as a named checkpoint rather than an inline clause.

DimensionReasoningScore

Conciseness

Dense, terse prose that assumes Claude's competence — jargon like CRS, MediaBox, PMTiles, pgRouting is used without explanation and every line carries prescriptive content rather than padding.

5 / 5

Actionability

Concrete and specific for an instruction skill — named tools (MapLibre, deck.gl, PostGIS+pgRouting, QGIS Print Layout) and explicit checklists (record CRS/axis/units, ordered edge/cost) — but lacks copy-paste executable examples, leaving minor gaps.

4 / 5

Workflow Clarity

A clear 1→8 sequence with an upfront flow diagram and a section-8 completion checklist including the SELF_REVIEW_ONLY gate and a section-6 '不成立时调整' feedback signal, though the validate→fix→retry loops are less explicit than the top anchor.

4 / 5

Progressive Disclosure

SKILL.md is an overview that points to two well-signaled, one-level-deep references ([patterns.md], [tool-profiles.md]) with guidance to load only relevant sections; the bundle structure is clean and navigable.

5 / 5

Total

18

/

20

Passed

Description

87%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.

The description is strong: third-person voice, explicit what/when structure with a negative boundary, and a distinct spatial-planning niche. The only soft spot is trigger-term synonym coverage and slightly generic action verbs.

Suggestions

Add a few natural synonyms (e.g., GIS、地理信息、地图制作、site plan) to widen trigger-term match coverage.

Consider sharpening the opening verbs beyond generic create/transform/review with one or two domain-specific actions (e.g., 路线计算、服务区求解、制图派生).

DimensionReasoningScore

Specificity

Names three concrete verbs ('创建、改造或审查') plus the spatial drivers (位置、边界、方向、尺度、路网、楼层、空间可达性) and six deliverable subtypes, giving broad coverage, but the verbs themselves are generic so it sits just below the comprehensive anchor.

4 / 5

Completeness

Clearly states what ('创建、改造或审查...地图与空间规划交付') and explicit when guidance via the '用于...' trigger list plus a '不用于...' negative boundary, answering both with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms users would say — 地图、空间规划、导航路线、服务区、专题与分区、楼层与室内导视、场地总平面 — with good coverage, but omits common synonyms (GIS、地理信息、地图制作) so it is not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

A clearly delineated spatial-relationship niche with explicit negative boundaries against data viz, abstract flowcharts, and map-as-background UIs, minimizing conflict with adjacent skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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
EverMind-AI/Raven
Reviewed

Table of Contents

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.