New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

AI Review Tool Handoff

by anthropics in anthropics/claude-for-legal

Hands bulk clause extraction in diligence work to a tool such as Luminance or Kira, then checks its output against the trust level you configured.

OfficialApache-2.0Auto-check passedLegal & Compliance

Install AI Review Tool Handoff

skills CLI
$ npx skills add anthropics/claude-for-legal --skill ai-tool-handoff -a claude-code

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

GitHub CLI
$ gh skill install anthropics/claude-for-legal ai-tool-handoff --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/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/corporate-legal/skills/ai-tool-handoff .claude/skills/ai-tool-handoff && 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
ai-tool-handoff
GitHub stars
9.6k
Used in
2 other repos
Token cost
~1.7k tokens
SKILL.md length
736 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Hands bulk clause extraction in diligence work to a tool such as Luminance or Kira, then checks its output against the trust level you configured.

  • Works in 4 steps: Prepare the batch → Load (or instruct the loader) → QA the output → …
  • A diligence category holds hundreds of similar contracts to extract clauses from
  • SKILL.md covers Matter context, Purpose, Load context and When to hand off, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

In a corporate legal setup, the agent reads the practice-level CLAUDE.md to learn which tool is in use, which clause types it covers, the trust level (use as-is, spot-check or full re-review) and who loads and who checks. If no tool is configured the skill does nothing and extraction runs through diligence-issue-extraction. It also follows matter workspaces: outputs go to the active matter's folder, and other matters' files stay unread unless cross-matter context is on.

Before any handoff it suggests the native tabular-review skill, which is quicker to set up, has no per-document cost and keeps the work local. Handoff makes sense when the corpus is too large, the team already holds a licence and workflow, or a validated provenance chain is required. The conditions are more than 50 documents in a category, a clause type the tool handles well, such as change of control, assignment, exclusivity, MFN, termination or auto-renewal, and reasonably uniform paper. Bespoke or heavily negotiated documents stay out.

When your agent uses it

  • A diligence category holds hundreds of similar contracts to extract clauses from
  • Your team already licenses Luminance or Kira and wants QA on its output
  • Deciding whether bulk review should go to a tool or stay in tabular review

Example prompts

  • “Send the customer contracts to Luminance for change-of-control extraction and QA what comes back.”
  • “Should we use a bulk review tool or tabular review for these supplier agreements?”
  • “Check the Kira extraction against our spot-check trust level.”

Requirements

  • The corporate-legal plugin CLAUDE.md configuration file
  • Access to Luminance or Kira, if handing off

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Prepare the batch
  2. Load (or instruct the loader)
  3. QA the output
  4. Judgment layer

What it can do on your machine

Read from SKILL.md and the folder at commit 4a6c651. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

AI Review Tool Handoff loads about 1.7k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 736 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 736 words, ~1,729 tokens.

Download SKILL.mdSave it as .claude/skills/ai-tool-handoff/SKILL.md (or your agent's skills folder).
name
ai-tool-handoff
description
Detects when Luminance, Kira, or a similar bulk-review tool is in use, hands off the high-volume clause extraction to it, and QAs its output per the trust level in `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`. Use when user says "send to Luminance", "bulk review", "AI extraction", or when diligence-issue-extraction hits a high-volume category.

AI Tool Handoff

Matter context

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.

Purpose

Luminance and Kira are good at one thing: reading 500 contracts and finding every change-of-control clause. They're less good at judgment — deciding whether a particular CoC provision is actually triggered by this deal structure.

This skill hands off the bulk extraction to the right tool, then runs the QA layer on what comes back.

Before you hand off: try tabular-review first (/corporate-legal:tabular-review). For anything the user's environment can handle — a few hundred documents, a defined column schema — native tabular review is faster to set up, has no per-document cost, and keeps the work product local. Hand off to Luminance/Kira when the corpus is genuinely too large, the team already has a license and workflow, or the matter requires a tool with a validated provenance chain.

Load context

~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md → AI-assisted review:

  • Tool in use (Luminance / Kira / none)
  • What it's used for (which clause types)
  • Trust level (use as-is / spot-check / full re-review)
  • Handoff process (who loads, who QAs)

If ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md says no AI tool → this skill is a no-op. Everything goes through diligence-issue-extraction directly.

When to hand off

Hand off when all of:

  • Category has >50 documents (below that, faster to just read them)
  • Extraction target is a clause type the tool is good at (CoC, assignment, exclusivity, MFN, termination, auto-renewal)
  • Documents are reasonably uniform (all customer contracts on similar paper — not a mix of contracts, letters, and board minutes)

Don't hand off:

  • Bespoke or heavily negotiated documents
  • Side letters and amendments (context-dependent, tools miss the interaction with the main agreement)
  • Anything where the question is "what does this mean for the deal" not "does this clause exist"

The handoff

Step 1: Prepare the batch
  • Identify documents for the batch (from VDR inventory)
  • Specify extraction targets per ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md (which clause types)
  • Note the materiality threshold so tool output can be filtered
Step 2: Load (or instruct the loader)

Per ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md — who loads. If it's you, generate the load instructions. If it's someone else, generate the request:

markdown
## [Tool] Load Request — [Deal code] — [Category]

**Documents:** [N] docs from VDR folder [path]
**Load to:** [Tool workspace/matter]
**Extraction targets:**
- Change of control / assignment
- Exclusivity
- [etc. per `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`]

**Filter output:** Flag only where extraction target is present — no need for "no CoC clause found" for every doc.

**Return by:** [date]
Show full SKILL.md (324 more words)Show less
Step 3: QA the output

When the tool returns results, apply the trust level:

"Use as-is": Ingest directly into diligence findings. (Only if ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md says this — it's rare.)

"Spot-check X%": Randomly sample X% of flagged documents. For each, read the actual clause and compare to the tool's extraction. If error rate is low, accept the batch. If errors found, widen the sample.

"Full human review of flagged": Tool narrows the universe (500 docs → 80 with CoC clauses). Human reads all 80. Tool saved the time of reading the 420 clean ones.

Step 4: Judgment layer

The tool found the clauses. Now apply judgment:

For each flagged CoC provision: is it actually triggered by this deal?

  • Stock sale vs. asset sale vs. merger — different triggers
  • "Change of control" defined how in the contract — majority ownership? board control? something else?
  • Is there a carve-out for this type of transaction?

This is the part the tool can't do. Output goes to diligence findings in house format.

Output

The QA summary below is derived from VDR documents that are privileged, confidential, or both. It inherits the sources' privilege and confidentiality status — distribution beyond the privilege circle can waive privilege. Store with the matter's privileged files.

markdown
## AI Tool Handoff Summary — [Category]

**Tool:** [Luminance / Kira]
**Documents processed:** [N]
**Extraction targets:** [clause types]

### QA

**Trust level:** [per `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`]
**Sample size:** [N] docs spot-checked
**Error rate:** [X]% — [Accepted / Widened sample / Full re-review triggered]

### Results

| Clause type | Docs flagged | After judgment layer | Material |
|---|---|---|---|
| Change of control | [N] | [N actually triggered by deal structure] | [N above threshold] |
| Assignment | [N] | [N] | [N] |

**→ [N] findings added to diligence issues**
**→ [N] consents added to closing checklist**

Close with the next-steps decision tree

End with the next-steps decision tree per CLAUDE.md ## Outputs. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.

What this skill does not do

  • It doesn't run Luminance or Kira — it manages the handoff and QA. A human (or the tool's own interface) runs the extraction.
  • It doesn't replace the tool's output with its own judgment entirely — if ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md says spot-check 10%, check 10%, not 100%.
  • It doesn't decide the trust level — that's in ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md, set at cold-start based on the team's experience with the tool.

© 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

Files

Just SKILL.md in corporate-legal/skills/ai-tool-handoff of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 2 other repositories

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.

Compare with similar skills

AI Review Tool Handoff 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.

AI Review Tool Handoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Review Tool Handoff this skillanthropics/claude-for-legal9.6k2 repos~1.7kAutomated safety check: PassApache-2.0
Contract Reviewevolsb/claude-legal-skill4641 repos~3.6kAutomated safety check: PassMIT
Commercial Legal Plapiotrowski-afk/commercial-legal-pl1761 repos~4.1kAutomated safety check: PassApache-2.0
Hand Drawnthreerocks/hand-drawn-styles2.2k—~398Automated safety check: PassMIT
Tw Formal WritingImbad0202/tw-formal-writing179—~1kAutomated safety check: PassMIT
Contract Review ProCSlawyer1985/contract-review-pro277—~2.3kAutomated safety check: PassNone

Similar skills

  • Contract Review

    evolsb/claude-legal-skill

    Review legal contracts, NDAs, employment agreements, SaaS terms, and M&A documents.

    464 GitHub starsUsed in 1 repo~3.6k tokens
    Legal & ComplianceAuto-check passed

  • Commercial Legal Pl

    apiotrowski-afk/commercial-legal-pl

    Skill do analizy i tworzenia umów według polskiego prawa, ze szczególnym uwzględnieniem umów B2B, IP i IT (body leasing, NDA, wdrożenia, SaaS, przeniesienie praw autorskich, ugody).

    176 GitHub starsUsed in 1 repo~4.1k tokens
    Legal & ComplianceAuto-check passed

  • Hand Drawn

    threerocks/hand-drawn-styles

    A skill your agent uses when users ask for a hand-drawn or illustrated image prompt, name one of the repository's 20 numbered styles or the 3.1 stable variant, or mention triggers such as…

    2.2k GitHub stars~398 tokensUpdated 2 days ago
    Legal & ComplianceAuto-check passed

  • Tw Formal Writing

    Imbad0202/tw-formal-writing

    台灣正式文件撰寫助手 — 涵蓋政府公文、政府機關其他文件、法律文件、人民對政府文書四類中文正式文件的撰寫（不含學術論文、商業文書、私人書信等，見下方排除清單）。

    179 GitHub stars~1k tokensUpdated 16 days ago
    Legal & ComplianceAuto-check passed

  • Contract Review Pro

    CSlawyer1985/contract-review-pro

    专业合同审核 Skill：7步工作流（含立场声明、框架审阅、类型路由）、5类通用门禁+16个专项门禁、终稿三件套+HTML可视化报告、8维度风险评分、修订5分类路由。完全自包含，零外部依赖。

    277 GitHub stars~2.3k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

  • Contract Comparison

    zubair-trabzada/ai-legal-claude

    Side-by-side comparison of two contract versions or two different contracts with change tracking, favorability analysis, and risk assessment

    1.8k GitHub stars~1.8k tokensUpdated 6 mo ago
    Legal & ComplianceAuto-check passed

More from anthropics/claude-for-legal

All 147 skills in this repo

  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Auto-check passed

  • Supervisor Review Queue

    anthropics/claude-for-legal

    Official

    Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

    9.6k GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check passed

  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    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.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Auto-check passed

  • Product Launch Legal Review

    anthropics/claude-for-legal

    Official

    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.

    9.6k GitHub starsUsed in 2 repos~5k tokens
    Auto-check passed

  • Legal Skills Registry Browser

    anthropics/claude-for-legal

    Official

    Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.

    9.6k GitHub starsUsed in 2 repos~620 tokens
    Auto-check passed

  • Contract Renewal Tracker

    anthropics/claude-for-legal

    Official

    Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.

    9.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

Categories

Questions about AI Review Tool Handoff

What does AI Review Tool Handoff do?

Hands bulk clause extraction in diligence work to a tool such as Luminance or Kira, then checks its output against the trust level you configured. md to learn which tool is in use, which clause types it covers, the trust level (use as-is, spot-check or full re-review) and who loads and who checks. If no tool is configured the skill does nothing and extraction runs through diligence-issue-extraction.

When should I use AI Review Tool Handoff?

AI Review Tool Handoff fits situations like: A diligence category holds hundreds of similar contracts to extract clauses from; your team already licenses Luminance or Kira and wants QA on its output; deciding whether bulk review should go to a tool or stay in tabular review.

How do I install AI Review Tool Handoff in Claude Code?

Run `npx skills add anthropics/claude-for-legal --skill ai-tool-handoff -a claude-code`. Or copy the skill folder (corporate-legal/skills/ai-tool-handoff in anthropics/claude-for-legal) into .claude/skills/ai-tool-handoff in your project. Claude Code loads it when a task matches its description.

How do I install AI Review Tool Handoff in Codex?

Run `npx skills add anthropics/claude-for-legal --skill ai-tool-handoff -a codex`. Or copy the skill folder (corporate-legal/skills/ai-tool-handoff in anthropics/claude-for-legal) into .agents/skills/ai-tool-handoff in your project. Codex loads it when a task matches its description.

Can I use AI Review Tool Handoff 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 anthropics/claude-for-legal --skill ai-tool-handoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-tool-handoff, .gemini/skills/ai-tool-handoff, .github/skills/ai-tool-handoff and .opencode/skills/ai-tool-handoff in your project.

What does AI Review Tool Handoff need to run?

SKILL.md names no scripts, command-line tools or credentials: AI Review Tool Handoff is instructions for the agent only. Our summary lists: The corporate-legal plugin CLAUDE.md configuration file; Access to Luminance or Kira, if handing off.

Does AI Review Tool Handoff 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 AI Review Tool Handoff 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. Review the folder before installing.

What licence does AI Review Tool Handoff use?

AI Review Tool Handoff 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.

How many tokens does AI Review Tool Handoff use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to AI Review Tool Handoff?

Skills that share tags, products or a category with AI Review Tool Handoff: Contract Review (evolsb/claude-legal-skill, 464 stars), Commercial Legal Pl (apiotrowski-afk/commercial-legal-pl, 176 stars), Hand Drawn (threerocks/hand-drawn-styles, 2.2k stars) and Tw Formal Writing (Imbad0202/tw-formal-writing, 179 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Review Tool Handoff?

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.