跳到正文
cccskills
免费在 GitHub 公开

docx-processing-superdoc

Edit, query, and transform Word documents with the SuperDoc CLI v1 operation surface. Use when the user asks to read, search, modify, comment, or review changes in .docx files.

中文简介正在准备中。当前显示原文说明。

集成工具Word

实测评分 未实测

查看安装方法

包含的文件(3)

  • SKILL.md5.3 KB
  • LICENSE.txt33.7 KB
  • README.md149 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

SuperDoc CLI (v1)

Use SuperDoc CLI for DOCX work. Use v1 commands (canonical operations and their helper wrappers). Do not default to legacy commands unless explicitly needed for v0-style bulk workflows.

Use superdoc if installed, or npx @superdoc-dev/cli@latest as a fallback.

First Step: Discover Exact Params

For unknown commands or flags, inspect runtime metadata first:

superdoc describe
superdoc describe command find
superdoc describe command "comments add"

Use describe command for per-command args and constraints.

Preferred Workflows

1) Stateful multi-step edits (recommended)

superdoc open ./contract.docx
superdoc query match --select-json '{"type":"text","pattern":"termination"}' --require exactlyOne
superdoc replace --target-json '{"kind":"text","blockId":"p1","range":{"start":0,"end":11}}' --text "expiration"
superdoc save --in-place
superdoc close
  • Always use query match (not find) to discover mutation targets — it returns exact addresses with cardinality guarantees.
  • After open, commands run against the active/default session when <doc> is omitted.
  • Use superdoc session list|set-default|save|close for explicit session control.
  • close on dirty state requires --discard or a prior save.

2) Stateless one-off reads

superdoc get-text ./proposal.docx
superdoc get-markdown ./proposal.docx
superdoc info ./proposal.docx

3) Stateless one-off mutations

superdoc replace ./proposal.docx \
  --target-json '{"kind":"text","blockId":"p1","range":{"start":0,"end":5}}' \
  --text "Updated" \
  --out ./proposal.updated.docx
  • In stateless mode (<doc> provided), mutating commands require --out unless using --dry-run.

Safety: preview before apply

  • Use --dry-run to preview any mutation without applying it.
  • Use --expected-revision <n> with stateful mutations for optimistic concurrency checks.

Common v1 Commands

Query & inspect

  • Search/browse content: find --type text --pattern "..." or find --query-json '{...}'
  • Find mutation target: query match --select-json '{...}' --require exactlyOne
  • Inspect blocks: blocks list, get-node, get-node-by-id
  • Extract content: get-text, get-markdown, get-html

Mutate

  • Replace text: replace --target-json '{...}' --text "..."
  • Insert inline text: insert --block-id <id> --offset <n> --value "..."
  • Delete text/node: delete --target-json '{...}'
  • Delete blocks: blocks delete, blocks delete-range
  • Batch mutations: mutations apply --steps-json '[...]' --atomic true --change-mode direct
  • Create paragraph: create paragraph --text "..." (with optional --at-json)
  • Create heading: create heading --input-json '{"level":<n>,"text":"..."}'

Format

  • Apply formatting: format apply --block-id <id> --start <n> --end <n> --inline-json '{"bold":true}'
  • Shortcuts: format bold, format italic, format underline, format strikethrough

Lists

  • List items: lists list, lists get
  • Insert list item: lists insert --node-id <id> --position after --text "..."
  • Modify: lists indent, lists outdent, lists set-level, lists set-type, lists convert-to-text

Comments

  • Add/reply: comments add, comments reply
  • Read: comments get, comments list
  • Edit/resolve/move: comments edit, comments resolve, comments move, comments set-internal
  • Delete: comments delete (canonical) or comments remove (alias)

Track changes

  • List: track-changes list, track-changes get
  • Decide: track-changes accept, track-changes reject, track-changes accept-all, track-changes reject-all

History

  • history get, history undo, history redo

Low-level

  • Direct invoke: call <operationId> --input-json '{...}' (JSON output only — --pretty is not supported)

JSON/File Payload Flags

Not all --*-file variants are available on every command. Use describe command <name> to check.

Always supported alongside their -json counterpart (use one, not both):

Flag pairAvailable on
--query-json / --query-filefind, lists list
--address-json / --address-fileget-node, lists get
--input-json / --input-filecall, create paragraph
--at-json / --at-filecreate paragraph

--target-json is widely available on mutation commands but has no --target-file counterpart. Use flat flags (--block-id, --start, --end) as an alternative to --target-json.

Output and Global Flags

  • Default output is JSON envelope.
  • Use --pretty for human-readable output (not supported by call).
  • Global flags: --output <json|pretty>, --session <id>, --timeout-ms <n>.
  • <doc> can be - to read DOCX bytes from stdin.

Legacy Compatibility (Use Sparingly)

Legacy v0.x bridge commands still exist:

superdoc search <pattern> <files...>
superdoc replace-legacy <find> <to> <files...>
superdoc read <file>

Use these only when you specifically need v0-style behavior (especially multi-file glob search/replace). For new automations, prefer v1 operations.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Public-safe preliminary screen for challenges to the impartiality of an AI evaluator, LLM-as-a-judge, decision-support agent, or adjudicative system based on prior outputs, suspected bias, unstable reasoning, or self-reinforcing memory. Use when asked whether an AI should be recused, disqualified, replaced, audited, or escalated. Does not decide real cases or claim that human judicial-recusal doctrine automatically applies.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8942026年10月20日 更新

Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how the agent can be suspended, revoked, or escalated.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8942026年10月20日 更新

EU AI Act Knowledge Engine — authoritative regulatory Q&A grounded in 70 official EU source documents (including the 2026 Commission draft guidelines on Art. 6 high-risk classification — general principles, Annex I, Annex III). Answers any question about the AI Act with article-level citations from the full regulation text, Commission guidelines, EDPB/EDPS opinions, codes of practice, harmonised standards, FRIA guides, incident templates, and sector-specific guidance. This skill should be used when the user asks about the "EU AI Act", "AI Act regulation", "Regulation 2024/1689", "KI-Verordnung", asks to "explain an AI Act article", "what does Article X say", "AI Act requirements", "AI Act penalties", "AI Act timeline", "GPAI obligations", "high-risk AI", "prohibited AI practices", "AI Act and GDPR", "fundamental rights impact assessment", "AI Act standards", "AI Act national implementation", "AI literacy", "serious incident reporting", "Digital Omnibus", "AI regulatory sandbox", or any question about EU artificial intelligence regulation. Also triggers on German terms: "KI-Gesetz", "KI-Verordnung", "Hochrisiko-KI", "KI-Kompetenz", "Grundrechte-Folgenabschaetzung", "GPAI-Verhaltenskodex". For assessment workflows that produce a classification decision rather than a knowledge answer, offer to run a structured risk-tier classification in-session.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8942026年10月20日 更新

This skill builds a structured audit trail of an AI-assisted task: what the tool was asked to do, what materials it was given, what it produced, how the output was verified, and what was ultimately relied upon. It documents the workflow for supervision and later review without ruling on privilege or disclosure, so the record stays accurate rather than self-serving.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8942026年10月20日 更新

Use this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review of an internal AI use case, an AI product feature, an LLM workflow, or a third-party AI vendor. The skill asks intake and clarifying questions first when facts or evidence are missing, identifies required documentation and missing evidence, maps the use case to AI governance frameworks and applicable legal domains, and produces a preliminary or final governance review with scorecards, findings, owners, remediation actions, and follow-up questions.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8942026年10月20日 更新

Turn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable. Produces a multi-page website (default), a single-page interactive site, a Microsoft Word document, a PowerPoint deck, or a LaTeX/PDF. Use whenever a user has a stress-test result, ambiguity audit, or "where will this be litigated" scenarios and wants to publish, present, or share them. Triggers on "publish the audit," "make a report from this," "turn this into a website / deck / brief / Word doc," "make a Netlify site," "build slides of these ambiguities," "render the scenarios," "package this stress test," "produce a LaTeX version," and similar. Pairs with the ambiguity-stress-test skill (the underlying analysis) but works on any structured or semi-structured ambiguity analysis. Visual design is opinionated but the user can override colors, fonts, and brand label. Most formats need Python and a writable filesystem; single-file HTML works where the host has neither.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8942026年10月20日 更新

查看 lawve-ai 的全部技能

报告此技能的问题