Agent skill

Legal Verification Workbench

by infometa in infometa/workbuddyskills

法律检索核验工作台。任务单出现【核验工作台:必用】、【输出档位:重量】或输出形态属于全面合规检索、文书引用素材、诉讼仲裁支撑、非诉文书检索、企业合规体检、案例专题分析、刑事量刑参考、行政复议证据时必须使用。本 skill 执行脚本化动作:保存 answer/sources/claims,运行 legal-verify all/html/repair- 生成模板 HTML;禁止手写 HTML。

No licenceAuto-check passed

Install Legal Verification Workbench

skills CLI
$ npx skills add infometa/workbuddyskills --skill legal-verification-workbench -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install infometa/workbuddyskills legal-verification-workbench --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/infometa/workbuddyskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/experts/legal-search-pro/skills/legal-verification-workbench .claude/skills/legal-verification-workbench && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
legal-verification-workbench
GitHub stars
348
Token cost
~1.8k tokens
SKILL.md length
272 words
Files
20 (incl. scripts, references)
Skills in repo
218
Repo updated
First seen
Licence
None found

At a glance

法律检索核验工作台。任务单出现【核验工作台:必用】、【输出档位:重量】或输出形态属于全面合规检索、文书引用素材、诉讼仲裁支撑、非诉文书检索、企业合规体检、案例专题分析、刑事量刑参考、行政复议证据时必须使用。本 skill 执行脚本化动作:保存 answer/sources/claims,运行 legal-verify all/html/repair- 生成模板 HTML;禁止手写 HTML。

  • Works in 9 steps: 检索即捕获(新增强制步骤):凡本轮任务调用过… → 定稿正文:先按场景写好最终意见,原样保存为… → 整理来源:优先使用 capture… → …
  • SKILL.md covers 何时启用, 标准流程, 输入格式 and 命令, plus 4 more sections
  • Runs JavaScript scripts from its folder; calls node

What it does

Legal Verification Workbench is an agent skill from infometa/workbuddyskills. 法律检索核验工作台。任务单出现【核验工作台:必用】、【输出档位:重量】或输出形态属于全面合规检索、文书引用素材、诉讼仲裁支撑、非诉文书检索、企业合规体检、案例专题分析、刑事量刑参考、行政复议证据时必须使用。本 skill 执行脚本化动作:保存 answer/sources/claims,运行 legal-verify all/html/repair- 生成模板 HTML;禁止手写 HTML。

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 21 other files, including scripts and reference files (for example `references/evidence-matching-spec.md`, `references/html-report-spec.md` and `references/paragraph-indexing-spec.md`).

The repository describes itself as: WorkBuddy skills / connectors / experts archive for offline study.

Example prompts

  • “/legal-verification-workbench”

Requirements

  • Node.js

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. 检索即捕获(新增强制步骤):凡本轮任务调用过 WebSearch/WebFetch、北大法宝、华宇元典、用户自有 Skill/MCP 或其他检索工具,必须把每一批返回资料先写入检索批次 JSON,并运行 legal-verify…
  2. 定稿正文:先按场景写好最终意见,原样保存为 answer.md。不要为了核验改写正文。
  3. 整理来源:优先使用 capture 已入库的资料;如仍需手工补充,把本次真实检索到、报告会用到的资料写入 sources.json 并运行 legal-verify persist。不得只在聊天上下文里保留来源。
  4. 声明依据:通读定稿,对关键法律句子写 claims.json,声明它对应的来源和条号。
  5. 一键生成首轮报告:运行 legal-verify all。这是首轮稿,不等于最终交付稿。
  6. 强制读取补检门禁:查看 repairRequired、supplementalQueuePath、supplementalQueueCount、sourceFulltextQueuePath、sourceFulltextIssueCount、sourceFulltextBloc…
  7. 先补全文,再补关联:若 sourceFulltextBlockerCount>0 或 health.gates 含 source_fulltext_required,先打开 sourceFulltextQueuePath,逐条用 WebFetch/官方库/MCP detail…
  8. 补充检索/补充关联(强制门禁触发时):若统计中弱关联/待核验比例过高,或正文有未高亮但明显需要法律依据的内容,使用补检队列逐条语义判断;补到真实依据后应用补充关联并重建 HTML;确认无需独立依据的点必须 ignore 并从最终可见统计中抑制。
  9. 看返回结果:success:false 必须修复后重跑;health.ok:false、health.deliveryBlocked:true 或 repairRequired:true 必须完成补全文/补检闭环后再交付。

What it can do on your machine

Read from SKILL.md and the folder at commit 91b77ea. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 11 files in scripts/ (JavaScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Legal Verification Workbench loads about 1.8k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 57 tokens; SKILL.md has 272 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~16k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 272 words (~1,811 tokens).

“本工作台是重量级法律检索任务的脚本化执行终点:接收已经定稿的正文和真实检索来源,运行 legal-verify 生成一份可点击溯源的 HTML 报告。 任务单标记【核验工作台:必用】时必须进入本工作台,不能由其他步骤手写 HTML 替代。”

— opening of SKILL.md by infometa
name
legal-verification-workbench

Read the full SKILL.md on GitHub

Files

SKILL.md and 19 other files (scripts, references) in experts/legal-search-pro/skills/legal-verification-workbench of infometa/workbuddyskills.

  • SKILL.md
  • references/evidence-matching-spec.md
  • references/html-report-spec.md
  • references/paragraph-indexing-spec.md
  • references/verification-point-spec.md
  • references/verification-workflow.md
  • references/virtual-memory-schema.md
  • scripts/audit-source-completeness.mjs
  • scripts/capture-retrieval-batch.mjs
  • scripts/extract-verification-points.mjs
  • scripts/generate-verification-html.mjs
  • scripts/legal-memory-init.mjs
  • scripts/lib.mjs
  • scripts/match-evidence.mjs
  • scripts/paragraphize-source.mjs
  • scripts/persist-legal-sources.mjs
  • scripts/run-verification-pipeline.mjs
  • scripts/supplement-weak-evidence.mjs
  • templates
  • … and 1 more

Open the folder on GitHubat commit 91b77ea

Compare with similar skills

Legal Verification Workbench next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Legal Verification Workbench compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Legal Verification Workbench this skillinfometa/workbuddyskills348—~1.8kAutomated safety check: PassNone
Metabolomics Workbench Databasedavila7/claude-code-templates33k12 repos~2.6kAutomated safety check: PassMIT
SenseNova PPT WorkbenchOpenSenseNova/SenseNova-Skills5.7k—~2.5kAutomated safety check: NotesMIT
Chat First WorkbenchBuilderIO/agent-native7.1k—~622Automated safety check: PassNone
Ansys Structural WorkbenchCai-aa/CAE-Agent-Hub1k—~2.2kAutomated safety check: PassMIT
Shell Data Workbenchbionic-gpt/bionic-gpt2.4k—~131Automated safety check: PassApache-2.0

Similar skills

  • Metabolomics Workbench Database

    davila7/claude-code-templates

    Access NIH Metabolomics Workbench via REST API (4,200+ studies).

    33k GitHub starsUsed in 12 repos~2.6k tokens
    Backend & APIsAuto-check passed
  • SenseNova PPT Workbench

    OpenSenseNova/SenseNova-Skills

    Opens the PPT Workbench web editor for an existing SenseNova HTML slide deck so you can preview, inspect and visually edit it without regenerating.

    5.7k GitHub stars~2.5k tokensUpdated 2 days ago
    Documents & OfficeAuto-check: notes
  • Chat First Workbench

    BuilderIO/agent-native

    Implement or extend the opt-in Codex/T3-like chat-first shell.

    7.1k GitHub stars~622 tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Ansys Structural Workbench

    Cai-aa/CAE-Agent-Hub

    Operate or inspect live ANSYS Workbench Mechanical structural simulations through the configured MCP, including model setup, materials, connections, loads, mesh, solve, convergence, validation, and…

    1k GitHub stars~2.2k tokensUpdated 10 days ago
    Auto-check passed
  • Shell Data Workbench

    bionic-gpt/bionic-gpt

    Inspect, filter, summarize, and transform sandbox files with shell tools.

    2.4k GitHub stars~131 tokensUpdated 4 days ago
    Auto-check passed
  • Metabolomics Workbench Database

    jaechang-hits/SciAgent-Skills

    Query Metabolomics Workbench REST API (4,200+ NIH studies) for metabolite ID, study discovery, RefMet standardization, m/z precursor searches, and gene/protein annotations.

    374 GitHub starsUsed in 1 repo~5.3k tokens
    Research & ScienceAuto-check passed

More from infometa/workbuddyskills

All 218 skills in this repo
  • Campus Event Playbook

    infometa/workbuddyskills

    This skill should be used when planning, coordinating, running, or reviewing student-led campus events, including club recruitment, freshman mixers, welcome activities, small talks, competitions…

    349 GitHub stars~861 tokensUpdated today
    Auto-check passed
  • Teachany

    infometa/workbuddyskills

    K-12 interactive courseware creation. An agent skill from infometa/workbuddyskills.

    349 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check: notes
  • Weight Management HTML

    infometa/workbuddyskills

    A skill your agent uses when the adult weight-management MCP needs to be installed/set up in WorkBuddy (connector) or its result must be rendered as a standalone Chinese HTML plan.

    349 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Agent Browser

    infometa/workbuddyskills

    A skill your agent uses when the user needs browser automation, including opening web pages, taking screenshots, extracting page content, clicking elements, filling forms, or testing web flows.

    349 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • AI Research Radar

    infometa/workbuddyskills

    定时任务:每日研究简报。漏掉重要论文和行业报告?每天帮你盯着,关键信息一条不漏 This skill should be used when the user asks about 定时任务:每日研究简报.

    349 GitHub stars~438 tokensUpdated today
    Auto-check passed
  • Check Deck

    infometa/workbuddyskills

    Investment banking presentation quality checker. An agent skill from infometa/workbuddyskills.

    348 GitHub stars~687 tokensUpdated yesterday
    Auto-check passed

Questions about Legal Verification Workbench

What does Legal Verification Workbench do?

法律检索核验工作台。任务单出现【核验工作台:必用】、【输出档位:重量】或输出形态属于全面合规检索、文书引用素材、诉讼仲裁支撑、非诉文书检索、企业合规体检、案例专题分析、刑事量刑参考、行政复议证据时必须使用。本 skill 执行脚本化动作:保存 answer/sources/claims,运行 legal-verify all/html/repair- 生成模板 HTML;禁止手写 HTML。. Legal Verification Workbench is an agent skill from infometa/workbuddyskills.

How do I install Legal Verification Workbench in Claude Code?

Run `npx skills add infometa/workbuddyskills --skill legal-verification-workbench -a claude-code`. Or copy the skill folder (experts/legal-search-pro/skills/legal-verification-workbench in infometa/workbuddyskills) into .claude/skills/legal-verification-workbench in your project. Claude Code loads it when a task matches its description.

How do I install Legal Verification Workbench in Codex?

Run `npx skills add infometa/workbuddyskills --skill legal-verification-workbench -a codex`. Or copy the skill folder (experts/legal-search-pro/skills/legal-verification-workbench in infometa/workbuddyskills) into .agents/skills/legal-verification-workbench in your project. Codex loads it when a task matches its description.

Can I use Legal Verification Workbench in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add infometa/workbuddyskills --skill legal-verification-workbench -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/legal-verification-workbench, .gemini/skills/legal-verification-workbench, .github/skills/legal-verification-workbench and .opencode/skills/legal-verification-workbench in your project.

What does Legal Verification Workbench need to run?

Going by SKILL.md and its folder, Legal Verification Workbench needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js.

Does Legal Verification Workbench access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Legal Verification Workbench safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Legal Verification Workbench use?

No licence was found for Legal Verification Workbench or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Legal Verification Workbench use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 14k tokens, read only when the agent opens those files.

What are the alternatives to Legal Verification Workbench?

Skills that share tags, products or a category with Legal Verification Workbench: Metabolomics Workbench Database (davila7/claude-code-templates, 33k stars), SenseNova PPT Workbench (OpenSenseNova/SenseNova-Skills, 5.7k stars), Chat First Workbench (BuilderIO/agent-native, 7.1k stars) and Ansys Structural Workbench (Cai-aa/CAE-Agent-Hub, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Legal Verification Workbench?

infometa (a GitHub user) maintains it in infometa/workbuddyskills, which has 348 GitHub stars. The repository holds 218 skills in this directory. The repository was last updated on October 9, 2026.

Source: infometa/workbuddyskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.