SKILLEMALL.ai

BD GIS_SKILL

统一 GIS 综合知识库 V1.0(45文件模块化体系 | 2026年6月 公开上架版)。 七群组架构:基础底座(4) | 标准与规范(6) | 软件工具(13) | 开发与自动化(8) | 实战与避坑(5) | 现代GIS技术栈(7) | 自进化机制(1) + 独立附录(1)。 本次更新(8个GitHub GIS Skill包深度交叉对比驱动):结构重组(删除3空占位/20号统一/27号激活/游离文件归组/29号去数字后缀/31号独立附录)| 新增7个核心模块:R语言GIS生态(39)|OGC国际标准速查(40)|现代GIS管道(41)|多语言空间库(42)|格式决策树(43)|QGIS算法速查(44)|Agent技能范式(45)| QGIS全面重写:从概览→PyQGIS完整教材(13号)|云原生格式扩充(03号)|PMTiles部署(23号)|结构化反模式(29号)|2个新案例(28号)。 覆盖:坐标系/投影/椭球基准(GB标准EPSG WKID)、CASS11.0/iData/SuperMap GIS 2026/GlobalMapper v26.2/FME 2025/ArcGIS Pro 3.7/**LiDAR360 V9.0**等9款专业软件实操、 国家测绘标准体系(65+项现行国标神经链接版,含2025年7月发布的5项新国标)、新型基础测绘实体规范、 GIS↔CAD数据转换方法论、Python GIS生态(GeoPandas/Rasterio/Shapely/PyProj/GDAL/DuckDB Spatial)、 **R语言GIS生态**(terra/sf/tmap/leaflet/spatSample)、**OGC国际标准体系**(60+标准WMS/WFS/WMTS/OGC API/PMTiles/COG/GeoParquet)、 **现代GIS数据处理管道**(7种标准化模式/验证清单/可重现性要求)、**QGIS Processing 200+算法ID全目录**、 多语言几何引擎链(JTS→GEOS→Shapely→NTS→JSTS)、格式选择决策树与12条反模式、 **GIS Agent技能设计范式**(Reviewer/Inversion/Pipeline/Orchestrator)、 遥感与GEE/WebGIS/实景三维/GNSS/空间分析/深度学习、避坑库160+条目(WRONG/CORRECT/WHY结构化)、10大行业项目案例、 专家级批量处理指南(OSGB→SLPK工程化/ArcPy性能优化/FME调优11技巧/QGIS Processing API)、 跨软件协同工作流、坐标系七参数实战、GitHub已知Bug速查、Esri官方博客技术收录(GeoAI/3D Analyst/Reality Studio/Pro Assistant)、 **LiDAR360点云分类算法PTD vs CSF深度对比与避坑(重点)、32类AI自动分类、林业单木18+属性提取、 **ArcGIS Pro 3.7完整新功能详解**(File Knowledge Graph/Telecom Domain Networks/Embeddings-Based Analysis/Analyze Map)、 **自进化反馈机制**(用户反馈驱动迭代/知识缺口自动检测/增量搜索触发/版本自动升级)。 This skill should be used when the user mentions GIS, surveying/mapping, coordinate systems, CASS, iData, SuperMap, GlobalMapper, FME, QGIS, ArcGIS, GDB, DWG conversion, geodatabase, projections, datums, spatial data processing, quality inspection, geo-entity, basic surveying and mapping standards, project cost estimation, national standards GB/T, batch processing, performance tuning, automation, ETL, OSGB, SLPK, point cloud, deep learning, LiDAR360, lidar, point cloud classification, PTD, CSF, ground filtering, GreenValley, self-evolution, feedback, knowledge gap, Arc

ClawHub Agent Skills author: 坤图_GIS v1.0.0 MIT-0 51 files · 1 script body ≈ 5 074 tokens Open the sourceclawhub.ai analyzed 31 h ago

统一 GIS 综合知识库 V1.0(45文件模块化体系 | 2026年6月 公开上架版)。 七群组架构:基础底座(4) | 标准与规范(6) | 软件工具(13) | 开发与自动化(8) | 实战与避坑(5) | 现代GIS技术栈(7) | 自进化机制(1) + 独立附录(1)。 本次更新(8个GitHub GIS…

As a process D 46/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureGitHubAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
75/100
safety, quality, tests
Safety 60%
97
Quality 40%
41
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

✓ No critical or high findings

Medium and low: 3
  • low Secrets in code secret-high-entropy-token references/02_坐标系统与投影.md:92
    High-entropy token-like string (may be an id, hash or a credential)
    | GCS_…000 | 4490 | 1043 | CGCS2000 (1024) | 中国 |
  • low Secrets in code secret-high-entropy-token references/12_ArcGIS_Pro.md:352
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    output_sr = arcpy.SpatialReference("CGCS…11E")
    quoted
  • low Secrets in code secret-high-entropy-token references/35_专家级批量处理与自动化实战指南.md:434
    High-entropy token-like string (may be an id, hash or a credential)
    - [ ] ✅ 使用**投影坐标系**(如 CGCS…_38)

Files scanned: 51. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 2209 chars, limit 1024
  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 5074 tokens (recommended < 5000); move details to references/
  • note description-budget description takes 2209 of the ~15000-char shared budget for all skills
  • note frontmatter-key unknown frontmatter key "agent_created"
  • note frontmatter-key unknown frontmatter key "x-author-id"
  • note frontmatter-key unknown frontmatter key "x-skill-fingerprint"
  • note frontmatter-key unknown frontmatter key "x-license"

Process rating: all ten parameters 46/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (GIS_SKILL) differs from the folder (giser)
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5074 tokens
  • 100Steps. 55 steps
  • 100Running it twice. No mutating operations
  • low 10 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 2208: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -251 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 55 items
  • +4Has examples (9 code blocks)
  • +4Reference files are cited in the instructions (43 of 43)
  • +3All 1 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 41.

External checks

ClawHub: suspicious
This is mostly a GIS reference skill, but it also tells the agent to run persistent self-updating feedback, search, logging, and knowledge-base mutation workflows with broad triggers.
LLM: suspicious (high) · VirusTotal: · 16 Jun 2026