Real Skill packageSource verifiedClawHub registry

标准语料分类器

将一批标准 PDF（国家 GB / 行业 QX·JB·YY… / 地方 DB11·DB31…）按「级别 × 领域」自动归置： 解析文件名中的标准代号，查注册表得级别与归属，按名称关键词分入编号领域子文件夹， 并产出 CSV 编目与 HTML 可视化报告，支持按分类/年份/标准号/名称筛选打包下载。 This skill should be used when a user has a folder of standard PDFs (国家标准/行业标准/地方标准/团体标准/企业标准) and wants them classified, organized into domain subfolders, or inventoried — e.g. "把这批标准按建筑、食品、交通等分类", "整理一下地方标准文件夹", "给这些 PDF 出个分类目录", "下载某分类/某年度标准".

Identity and source

Publisher attributionjeffm2020registry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 55% rule confidence
Package forminstruction with code12 recorded files
Canonical sourceClawHub registryclawhub:jeffm2020:standards-corpus-classifier
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/15/2026.claude/skills/standards-corpus-classifier

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/15/2026.agents/skills/standards-corpus-classifier

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/15/2026skills/standards-corpus-classifier

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @jeffm2020/standards-corpus-classifier
clawhub inspect @jeffm2020/standards-corpus-classifier --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
11 / 12 inspected as text
Checked
8/15/2026, 3:40:20 PM
Scanner
0.1.3
Policy
1.0.3
3 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
21 dependency and API indicators
  • api: amr.gd.gov.cn
  • api: amr.guizhou.gov.cn
  • api: amr.hainan.gov.cn
  • api: amr.sz.gov.cn
  • api: amr.xizang.gov.cn
  • api: clawhub.ai
  • api: jst.nx.gov.cn
  • api: openstd.samr.gov.cn
  • api: pt.fjbz.org.cn
  • api: scjdglj.gxzf.gov.cn
  • api: scjg.jl.gov.cn
  • api: scjg.ln.gov.cn
  • api: scjgj.hebei.gov.cn
  • api: scjgj.shanxi.gov.cn
  • api: snamr.shaanxi.gov.cn
  • api: std.samr.gov.cn
  • api: www.cnsonline.com.tw
  • api: www.imisinfo.cn
  • api: www.jxbz.org.cn
  • api: www.qhzlbz.cn
  • api: www.ynstdinfo.net
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/15/2026, 3:12:54 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: clean
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:d9217c1e5119501f0967befbdb2e5a4d36d04689d881cf85f420d12f3fc19c90
Show up to 12 recorded paths
  • assets/cover.png
  • manifest.yaml
  • references/domains.json
  • references/qx_domains.json
  • references/sources.json
  • scripts/classify_standards.py
  • scripts/discover_sources.py
  • scripts/export_standards.py
  • scripts/make_report.py
  • scripts/verify_consistency.py
  • skill-card.md
  • SKILL.md

Source changelog

- Initial release: standards-corpus-classifier v1.0.0. - Classifies standard PDFs by level (国家/行业/地方) and domain (建筑/食品/交通等), organizing files and generating an inventory CSV. - Provides an offline HTML report with filterable categories, statistics, and domain/year breakdowns. - Includes scripts to export/download filtered subsets (by domain, year, standard number, or name) to ZIP archives with strong safety guarantees. - Ensures consistency and accuracy with a verification script checking all outputs, and supports easy metadata and taxonomy extension without internet. - Tested and verified on large real-world corpora (e.g., 北京DB11, 气象QX) with 0 missing or duplicate entries.