SKILLEMALL.ai

BF 建筑规范转Skill (code-to-skill)

建筑规范→AI Skill转换器。将建筑设计规范、国家标准(GB)、行业规程、法律法规转化为可查询的条文系统——按触发条件索引每一条条文,保留应/宜/可/不应/不得的法律效力措辞原文,提取数据表格为结构化JSON,绘制跨规范引用关系图。输入'把这个规范做成skill'/'查这条规范'/'建立规范知识库'即可使用。面向中国建筑设计规范(GB 50xxx系列)优化,也可适配任何地区的技术法规。内置自包含PDF提取引擎(本 skill 自带 scripts/extract.py + book_to_skill/,无需外部安装)。| Convert building codes/GB standards/regulations into structured queryable skills — indexing clauses by trigger, preserving mandatory-force wording, extracting tables as JSON. Use when user says 'code to skill' or '把规范做成skill'.

ClawHub Agent Skills author: 51comic v1.0.6 MIT-0 23 files body ≈ 3 347 tokens Open the sourceclawhub.ai analyzed 2 d ago

建筑规范→AI…

As a process F 28/100 · Will not run — References files that are not bundled: ../tables/<表号>.md, clauses/ch03.md, clauses/ch01-scope.md

ProcedureSoftware developmentAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
100
Quality 40%
73
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: ../tables/<表号>.md, clauses/ch03.md, clauses/ch01-scope.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
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 · 0

✓ No critical or high findings

Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning missing-ref reference to a missing file: ../tables/<表号>.md
  • warning missing-ref reference to a missing file: clauses/ch03.md
  • warning missing-ref reference to a missing file: clauses/ch01-scope.md
  • warning missing-ref reference to a missing file: clauses/ch02-terms.md
  • warning missing-ref reference to a missing file: tables/3.2.1.json
  • warning missing-ref reference to a missing file: tables/3.2.1.md
  • warning missing-ref reference to a missing file: clause-index.md
  • warning missing-ref reference to a missing file: clauses/
  • warning missing-ref reference to a missing file: tables/
  • warning missing-ref reference to a missing file: cross-refs.md
  • warning missing-ref reference to a missing file: mandatory-map.md
  • warning missing-ref reference to a missing file: terminology.md
  • note frontmatter-key unknown frontmatter key "categories"
  • note frontmatter-key unknown frontmatter key "slug"

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: ../tables/<表号>.md, clauses/ch03.md, clauses/ch01-scope.md
  • 0Tools and files. 12 referenced file(s) missing: ../tables/<表号>.md, clauses/ch03.md, clauses/ch01-scope.md
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (建筑规范转Skill (code-to-skill)) differs from the folder (code-to-skill)
  • 100Steps. 50 steps
  • 100Execution cost. Instruction body is 3347 tokens
  • low 22 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (7 tags): a typed call is more reliable

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)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 492: enough signal without eating the budget
  • +4Structure: 35 headings
  • +3Step-by-step instructions: 50 items
  • +4Has examples (14 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 1 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: clean
This skill converts user-provided building-code PDFs into local queryable skill files, with its local commands and file outputs disclosed and aligned to that purpose.
LLM: benign (high) · VirusTotal: · 22 Aug 2026