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.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
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.
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.
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
query match (not find) to discover mutation targets — it returns exact addresses with cardinality guarantees.open, commands run against the active/default session when <doc> is omitted.superdoc session list|set-default|save|close for explicit session control.close on dirty state requires --discard or a prior save.superdoc get-text ./proposal.docx
superdoc get-markdown ./proposal.docx
superdoc info ./proposal.docx
superdoc replace ./proposal.docx \
--target-json '{"kind":"text","blockId":"p1","range":{"start":0,"end":5}}' \
--text "Updated" \
--out ./proposal.updated.docx
<doc> provided), mutating commands require --out unless using --dry-run.--dry-run to preview any mutation without applying it.--expected-revision <n> with stateful mutations for optimistic concurrency checks.find --type text --pattern "..." or find --query-json '{...}'query match --select-json '{...}' --require exactlyOneblocks list, get-node, get-node-by-idget-text, get-markdown, get-htmlreplace --target-json '{...}' --text "..."insert --block-id <id> --offset <n> --value "..."delete --target-json '{...}'blocks delete, blocks delete-rangemutations apply --steps-json '[...]' --atomic true --change-mode directcreate paragraph --text "..." (with optional --at-json)create heading --input-json '{"level":<n>,"text":"..."}'format apply --block-id <id> --start <n> --end <n> --inline-json '{"bold":true}'format bold, format italic, format underline, format strikethroughlists list, lists getlists insert --node-id <id> --position after --text "..."lists indent, lists outdent, lists set-level, lists set-type, lists convert-to-textcomments add, comments replycomments get, comments listcomments edit, comments resolve, comments move, comments set-internalcomments delete (canonical) or comments remove (alias)track-changes list, track-changes gettrack-changes accept, track-changes reject, track-changes accept-all, track-changes reject-allhistory get, history undo, history redocall <operationId> --input-json '{...}' (JSON output only — --pretty is not supported)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 pair | Available on |
|---|---|
--query-json / --query-file | find, lists list |
--address-json / --address-file | get-node, lists get |
--input-json / --input-file | call, create paragraph |
--at-json / --at-file | create 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.
--pretty for human-readable output (not supported by call).--output <json|pretty>, --session <id>, --timeout-ms <n>.<doc> can be - to read DOCX bytes from stdin.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.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
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.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
Adversarially stress-tests a legal text — a contract, statute, regulation, or judicial opinion — for interpretive ambiguity: it finds the seams where the people governed by it will later disagree about what it means and turns each into a concrete dispute scenario with both sides' arguments, the likely outcome, and a fix. Use it whenever someone wants to pressure-test, red-team, audit, or find weak spots, loopholes, gaps, ambiguities, or drafting problems in a legal document; whenever a drafter wants to tighten a contract, statute, regulation, or opinion before it issues; whenever a litigator wants to mine an opinion or contract for arguments; or whenever someone hands over a legal text and asks where it will be fought over or for issue-spotting. Trigger it for contract review, statutory-ambiguity analysis, judicial-opinion scope analysis, and drafting QA — even if the user never says "stress-test" or "ambiguity."
日本語の概要は準備中です。原文の説明を表示しています。