Tw Legal RAG
aa0101181514/tw-legal-rag
Retrieve real Taiwan court judgments with verifiable citations before answering any question about Taiwan law or case law.
Draft a unanimous written consent of the board or a committee in house format, with precedent search from the consents repository.
$ npx skills add anthropics/claude-for-legal --skill written-consent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install anthropics/claude-for-legal written-consent --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/corporate-legal/skills/written-consent .claude/skills/written-consent && rm -rf skills-srcUse ~/.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/
Install the "written-consent" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/corporate-legal/skills/written-consent into .claude/skills/written-consent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "written-consent", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/anthropics/claude-for-legal/tree/main/corporate-legal/skills/written-consentType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add anthropics/claude-for-legal --skill written-consent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install anthropics/claude-for-legal written-consent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .agents/skills && cp -r skills-src/corporate-legal/skills/written-consent .agents/skills/written-consent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "written-consent" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/corporate-legal/skills/written-consent into .agents/skills/written-consent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "written-consent", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add anthropics/claude-for-legal --skill written-consent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install anthropics/claude-for-legal written-consent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/corporate-legal/skills/written-consent .cursor/skills/written-consent && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "written-consent" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/corporate-legal/skills/written-consent into .cursor/skills/written-consent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "written-consent", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/anthropics/claude-for-legal.git --path corporate-legal/skills/written-consent--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add anthropics/claude-for-legal --skill written-consent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install anthropics/claude-for-legal written-consent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/corporate-legal/skills/written-consent .gemini/skills/written-consent && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "written-consent" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/corporate-legal/skills/written-consent into .gemini/skills/written-consent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "written-consent", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install anthropics/claude-for-legal written-consentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add anthropics/claude-for-legal --skill written-consent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .github/skills && cp -r skills-src/corporate-legal/skills/written-consent .github/skills/written-consent && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "written-consent" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/corporate-legal/skills/written-consent into .github/skills/written-consent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "written-consent", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add anthropics/claude-for-legal --skill written-consent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install anthropics/claude-for-legal written-consent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/corporate-legal/skills/written-consent .opencode/skills/written-consent && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "written-consent" agent skill from https://github.com/anthropics/claude-for-legal/tree/main/corporate-legal/skills/written-consent into .opencode/skills/written-consent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "written-consent", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
written-consentDraft a unanimous written consent of the board or a committee in house format, with precedent search from the consents repository.
Written Consent is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Draft a unanimous written consent of the board or a committee in house format, with precedent search from the consents repository. Handles multi-resolution consents, director conflict flags, state-law notice requirements, and signatory tracking, with a built-in scope warning for major one-off actions. Use when user says "written consent", "unanimous consent", "board consent", "consent in lieu", "UWC", or describes an action needing board approval without a meeting.
Its SKILL.md is about 5.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Legal & Compliance, covering Legal research. The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4a6c651. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Written Consent loads about 5.1k tokens when it runs. Until then it costs about 121 tokens; SKILL.md has 2,351 words of instructions outside code blocks.
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.
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); files beside SKILL.md are not scanned.
The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 2,351 words, ~5,100 tokens.
.claude/skills/written-consent/SKILL.md (or your agent's skills folder).~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md → Board & Secretary (consents repository, resolution language, state of incorporation, board composition).~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md.Matter context. Check ## Matter workspaces in the practice-level CLAUDE.md. If Enabled is ✗ (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run /corporate-legal:matter-workspace switch <slug> or say practice-level." Load the active matter's matter.md for matter-specific context and overrides. Write outputs to the matter folder at ~/.claude/plugins/config/claude-for-legal/corporate-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.
Most routine board approvals don't need a meeting. Officer appointments, equity grants, bank authorizations, contract approvals above the officer threshold, intercompany arrangements — these happen by unanimous written consent. This skill drafts them quickly in your house format, finds the prior consent that's closest to what you need, and flags the actions where you should be getting outside counsel eyes before anyone signs.
This skill is designed for day-to-day consents with direct precedents in your repository or seed documents. Routine actions — officer appointments, equity grants, annual authorizations, standard contract approvals — are the right use case. The skill finds a prior consent that closely matches, adapts it to the current action, and produces a clean draft.
For major one-off actions, outside counsel review is prudent regardless of what this skill produces. This includes: M&A transactions (asset purchases, stock purchases, mergers, investments), financing rounds, equity issuances to new investors, change-of-control provisions, dissolution or winding down, material real estate transactions, and any action that will be scrutinized in a subsequent due diligence process.
The skill will flag automatically when the action looks like a major one-off. That flag is not a block — you can proceed. It is a prompt to think about whether a clean precedent-adapted draft is sufficient for this particular action.
A board consent for a major one-off action (M&A, financing, dissolution, capital structure change, director election tied to a financing or M&A) that the user wants signed TODAY — "send for DocuSign this afternoon," "meeting in an hour," "signing tonight," "we need this before market open" — goes through outside counsel review. Not because the plugin can't draft it — because a wrong consent on a major action is a one-way door, and the urgency pressure is exactly when mistakes happen.
Trigger (both must be true):
When both are true, output this and stop:
⛔ Major action + same-day signature — I won't mark this ready to sign.
This is [action type], which is a one-way door. You've asked for it to be signed today. That combination is exactly when mistakes on a board consent become hardest to unwind.
I'll draft it — happily — but I won't mark it ready to sign without an outside-counsel look. If outside counsel is already engaged on this deal, hand them this draft. If not, this is the thing outside counsel is for. Your professional regulator (state bar in the US, SRA/Bar Standards Board in England & Wales, Law Society in Scotland/NI/Ireland/Canada/Australia, or your jurisdiction's equivalent) can point you to a lawyer referral service that can find one same-day if needed.
Two ways forward:
- I draft, outside counsel reviews, then signatures — the normal path for a major corporate action. Tell me to draft and I will.
- Outside counsel is already on this deal and cleared the draft path — tell me who reviewed and when. I'll proceed and include a note that outside counsel has the draft.
I will not draft in "ready-to-send" form under same-day pressure without one of those two. This is not a delay — it's the only way a same-day major-action consent is defensible if anyone ever looks at the file.
Do not proceed to Step 1 or any drafting under this gate without an explicit response choosing path 1 or path 2. A routine consent with no major-action trigger, or a major-action consent without the same-day signature ask, follows the normal flow below — the "Outside counsel review recommended" flag on the major-one-off category still applies but does not hard-stop.
~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md → ## Board & Secretary:If (a) no consents repository is configured in ## Board & Secretary → Consents repository, AND (b) no seed consent document has been provided to this skill (either uploaded this session or referenced in the ## Board & Secretary → Consent format section with extracted resolution/recital/authorisation language from a specific seed), STOP before drafting. Do not proceed to Step 1 intake, do not draft from a generic template, do not "get started" with a filler format.
Output exactly this block and wait for a response:
No precedent available — stopping before draft.
I don't have a precedent to match. A board consent drafted without your house format will need more correction than it saves — resolution language, recital depth, authorisation boilerplate, and signature-block conventions all carry house-specific choices that the reviewer will rewrite from scratch if I start from a generic template.
Two ways to unblock:
- Paste or upload a prior consent (any recent UWC from this company in any category — I extract the format, not the substance), OR
- Tell me "draft from a generic template anyway — I'll adjust the formalities myself" — only pick this if you know you'll rework the resolution language, recital style, and authorisation block by hand before circulation. Say it explicitly; I will not infer it.
Which do you want to do?
Do NOT proceed without an explicit response choosing one of those two paths. Draft attempts absent a precedent are the highest-rework-to-value output this skill can produce — the hard stop is intentional.
Ask the user what action the board needs to approve. Gather:
~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md written-consent scope says certain actions require a meeting rather than consent, flag it now.Classify the action before searching for precedent:
Routine — direct precedent likely:
Review flag — major one-off, outside counsel prudent:
If the action is in the review-flag category, show this before drafting:
⚠️ Outside counsel review recommended. This looks like [action type], which is a major corporate action where a precedent-adapted draft may not be sufficient. Consider having outside counsel review before circulation. Want me to proceed with a draft anyway?
Search the repository for the closest prior consent. Search strategy:
I found [N] prior consents that look like this:
- [Consent title / description] — [Date]
- [Consent title / description] — [Date]
Which one is closest to what you need? Or should I use the most recent?
Extract the format from the seed consents in ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md. Note that no precedent search is available — the draft will follow house format but without substantive precedent matching. Flag this to the user:
No consents repository is connected, so I'm working from your seed documents for format. For this action type specifically, you may want to check whether you have a prior consent to use as a substantive starting point.
Use the house format. The structure below is the standard — adapt to match the precedent or seed format exactly.
UNANIMOUS WRITTEN CONSENT
[OF THE BOARD OF DIRECTORS / OF THE [COMMITTEE NAME]]
OF [COMPANY NAME]
[Date]
The undersigned, constituting all of the members of the
[Board of Directors / [Committee]] of [Company Name], a [State] [corporation /
limited liability company] (the "Company"), hereby adopt the following
resolutions by written consent pursuant to [Section X of the [State] General
Corporation Law / applicable operating agreement], in lieu of a meeting:
[AGENDA ITEM / ACTION HEADING — if multiple resolutions]
WHEREAS, [background recital — one or two sentences stating the relevant facts
and why the board is being asked to act]; and
WHEREAS, [additional recital if needed]; and
NOW, THEREFORE, BE IT RESOLVED, that [the specific action being approved,
in precise language — name names, state amounts, reference the specific
agreement or instrument where applicable];
RESOLVED FURTHER, that [any related or implementing resolution — e.g., the
specific officers authorized to sign documents, the authority granted];
RESOLVED FURTHER, that the officers of the Company are, and each of them
hereby is, authorized and directed, in the name and on behalf of the Company,
to take all actions and to execute and deliver all documents, instruments,
certificates and agreements as such officers may deem necessary or appropriate
to carry out the intent and purposes of the foregoing resolutions; and
RESOLVED FURTHER, that any actions previously taken by any officer of the
Company in connection with the foregoing are hereby ratified, confirmed and
approved in all respects.
[Repeat WHEREAS / RESOLVED block for each additional action if multi-resolution consent]
This Written Consent may be executed in one or more counterparts, each of
which shall be deemed an original and all of which together shall constitute
one and the same instrument. Electronic signatures shall be deemed original
signatures for all purposes.
[SIGNATURE BLOCKS — one per required signatory]
_______________________________
[Director Name]
[Title, if applicable]
Date: _______________
[Repeat for each director / committee member]Check the state of incorporation in ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md. Research the written-consent requirements for that state before drafting:
Cite the controlling statute section and any charter/bylaw provisions relied on. Verify currency — state corporate codes are amended regularly. Flag uncertainty for attorney verification rather than stating a rule you haven't confirmed.
If ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md records a house position on any of these questions, apply it and note the legal backstop being relied on. Add a short "State-law notice" block to the output summarizing what you confirmed (or flagged) so the user isn't left wondering.
Before proceeding to output: Read ## Who's using this in ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md. If the Role is Non-lawyer:
Executing a written consent has legal consequences — it binds the entity and becomes a corporate record. Have you reviewed this with an attorney? If yes, proceed. If no, here's a brief to bring to them:
- What the action is (the resolution)
- What the analysis found (state-law notice, signature threshold, any flagged conflicts)
- Open questions (anything flagged for attorney verification above)
- What could go wrong (invalid consent, breach of fiduciary duty, signature defect, conflict not properly handled)
- What to ask the attorney (is this the right vehicle; are there missing recitals; does the charter/bylaws permit consent for this action)
If you need to find an attorney, solicitor, barrister, or other authorised legal professional: contact your professional regulator (state bar in the US, SRA/Bar Standards Board in England & Wales, Law Society in Scotland/NI/Ireland/Canada/Australia, or your jurisdiction's equivalent) for a referral service.
Do not produce the final signatory-ready draft past this gate without an explicit yes. Research, format extraction, and a marked-DRAFT for attorney review are fine.
Produce:
The consent draft — complete, ready to review and circulate. The executed written consent itself is a corporate record, not privileged; do not apply the work-product header to the consent as circulated. The drafting notes, signatory tracker, and analysis below are work product — prepend the work-product header from ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md ## Outputs (it differs by user role — see ## Who's using this):
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]Signatory checklist:
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]
SIGNATORY CHECKLIST — [Action] — [Date]
Required signatories (unanimous consent required):
□ [Director Name 1]
□ [Director Name 2]
□ [Director Name 3]
[etc. — pulled from board composition in `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`]
Conflict disclosures:
[None / [Director Name] has a disclosed interest — confirm whether recusal or disclosure is appropriate]
State law notice: [confirmed-rule-for-state-of-incorporation / confirm][WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]
BEFORE CIRCULATING — check:
□ Resolution language precisely describes the action (no vague approvals)
□ Correct effective date
□ All required exhibits attached and referenced
□ Authorised signatories named correctly
□ Any director conflicts disclosed or resolved
□ For major actions: outside counsel has reviewedThis is a draft for attorney review, not an executed consent. Executing it binds the entity and becomes a corporate record — a licensed attorney reviews, edits as needed, and takes professional responsibility before it goes out. Do not circulate for signature unreviewed.
© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in corporate-legal/skills/written-consent of anthropics/claude-for-legal.
Open the folder on GitHubat commit 4a6c651
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.
Written Consent 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Written Consent this skillanthropics/claude-for-legal | 9.6k | 2 repos | ~5.1k | Automated safety check: Pass | Apache-2.0 | |
| Tw Legal RAGaa0101181514/tw-legal-rag | 328 | — | ~580 | Automated safety check: Pass | Custom licence | |
| Design Award SearchSeanJ1ang/design-judge-skills | 712 | — | ~3k | Automated safety check: Pass | Apache-2.0 | |
| China Lawyer AnalystCSlawyer1985/china-lawyer-analyst | 196 | — | ~3.3k | Automated safety check: Pass | None | |
| Billing And Litigation BudgetTHUYRan/Legal-Skills-Chinese | 874 | — | ~5k | Automated safety check: Pass | None | |
| Legal Issue ResearchGolden2002/legal-research-skill | 156 | — | ~6.8k | Automated safety check: Pass | MIT |
aa0101181514/tw-legal-rag
Retrieve real Taiwan court judgments with verifiable citations before answering any question about Taiwan law or case law.
SeanJ1ang/design-judge-skills
Find and verify award-winning designs in the same or adjacent functional category through eight explicit relevance dimensions: problem and user, core function, sensing technology, intervention…
CSlawyer1985/china-lawyer-analyst
通过中国法律视角分析事件,运用成文法解释、指导案例参照、请求权基础分析等方法, 理解权利义务、评估责任风险、识别法律依据并推荐合规策略。
THUYRan/Legal-Skills-Chinese
A skill your agent uses when the user needs to track or manage attorney hours, expert fees, and investigation costs; control litigation spend; or prepare timesheets or expense statements for clients.
Golden2002/legal-research-skill
中国法律全领域系统性检索专家. An agent skill from Golden2002/legal-research-skill.
Serein-81/financial_rag
Searches current Chinese tax laws, rates and policy changes with Tavily web search, prioritizing government sources and flagging outdated or conflicting results.
anthropics/claude-for-legal
Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.
anthropics/claude-for-legal
Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.
anthropics/claude-for-legal
Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.
anthropics/claude-for-legal
Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.
anthropics/claude-for-legal
Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.
anthropics/claude-for-legal
Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.
Categories
Draft a unanimous written consent of the board or a committee in house format, with precedent search from the consents repository. Written Consent is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Draft a unanimous written consent of the board or a committee in house format, with precedent search from the consents repository.
Written Consent fits situations like: user says written consent; unanimous consent; consent in lieu; describes an action needing board approval without a meeting.
Run `npx skills add anthropics/claude-for-legal --skill written-consent -a claude-code`. Or copy the skill folder (corporate-legal/skills/written-consent in anthropics/claude-for-legal) into .claude/skills/written-consent in your project. Claude Code loads it when a task matches its description.
Run `npx skills add anthropics/claude-for-legal --skill written-consent -a codex`. Or copy the skill folder (corporate-legal/skills/written-consent in anthropics/claude-for-legal) into .agents/skills/written-consent in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/claude-for-legal --skill written-consent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/written-consent, .gemini/skills/written-consent, .github/skills/written-consent and .opencode/skills/written-consent in your project.
SKILL.md names no scripts, command-line tools or credentials: Written Consent is instructions for the agent only.
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.
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. Review the folder before installing.
Written Consent is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.1k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Written Consent: Tw Legal RAG (aa0101181514/tw-legal-rag, 328 stars), Design Award Search (SeanJ1ang/design-judge-skills, 712 stars), China Lawyer Analyst (CSlawyer1985/china-lawyer-analyst, 196 stars) and Billing And Litigation Budget (THUYRan/Legal-Skills-Chinese, 874 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,633 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on September 29, 2026.
Source: anthropics/claude-for-legal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.