Official agent skill

Matter Workspace

by anthropics in anthropics/claude-for-legal

Manage matter workspaces — new, list, switch, close, or detach (practice-level).

OfficialApache-2.0Auto-check passedLegal & Compliance

Install Matter Workspace

skills CLI
$ npx skills add anthropics/claude-for-legal --skill matter-workspace -a claude-code

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

GitHub CLI
$ gh skill install anthropics/claude-for-legal matter-workspace --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/ai-governance-legal/skills/matter-workspace .claude/skills/matter-workspace && 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
matter-workspace
GitHub stars
9.6k
Used in
3 other repos
Token cost
~2.5k tokens
SKILL.md length
884 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Manage matter workspaces — new, list, switch, close, or detach (practice-level).

  • Works in 4 steps: Read… → Use the workflow below. → Dispatch on the first token of $ARGUMENTS → …
  • Working across multiple clients
  • SKILL.md covers Subcommands, Instructions, Notes and Storage layout, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Matter Workspace is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Manage matter workspaces — new, list, switch, close, or detach (practice-level). File-management logic for keeping one client or engagement's context separate from every other. Use when working across multiple clients or matters, when the user says "new matter", "switch matter", "list matters", "close matter", or when any substantive skill needs to know which matter it's working in.

Its SKILL.md is about 2.5k 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 File organization and AI governance. The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.

When your agent uses it

  • Working across multiple clients
  • The user says new matter
  • Any substantive skill needs to know which matter its working in

Example prompts

  • “new matter”
  • “switch matter”
  • “list matters”
  • “/matter-workspace”

Workflow steps

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

  1. Read ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md — confirm the ## Matter workspaces section is populated. If…
  2. Use the workflow below.
  3. Dispatch on the first token of $ARGUMENTS
  4. Show the user what changed and confirm before writing.

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

Matter Workspace loads about 2.5k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 884 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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). 884 words, ~2,451 tokens.

Download SKILL.mdSave it as .claude/skills/matter-workspace/SKILL.md (or your agent's skills folder).
name
matter-workspace
description
Manage matter workspaces — new, list, switch, close, or detach (practice-level). File-management logic for keeping one client or engagement's context separate from every other. Use when working across multiple clients or matters, when the user says "new matter", "switch matter", "list matters", "close matter", or when any substantive skill needs to know which matter it's working in.
argument-hint
<new | list | switch | close | none> [slug]

/matter-workspace

Practitioners work across multiple clients and matters. A matter workspace keeps one client or engagement's context separate from every other. This skill manages those workspaces.

Subcommands

  • /ai-governance-legal:matter-workspace new <slug> — create a new matter workspace, run a short intake, write matter.md
  • /ai-governance-legal:matter-workspace list — list matters with status and active flag
  • /ai-governance-legal:matter-workspace switch <slug> — set the active matter
  • /ai-governance-legal:matter-workspace close <slug> — archive a matter (move to ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/matters/_archived/, never delete)
  • /ai-governance-legal:matter-workspace none — detach from any active matter, work at practice-level only

Instructions

  1. Read ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md — confirm the ## Matter workspaces section is populated. If Enabled is ✗, tell the user: "Matter workspaces are off — you're configured as an in-house practice with one client, so the plugin works from practice-level context automatically. If you actually work across multiple clients, re-run /ai-governance-legal:cold-start-interview --redo and select a private-practice setting. Otherwise, you don't need /matter-workspace at all." Don't error — the disabled state is the expected one for in-house users.
  2. Use the workflow below.
  3. Dispatch on the first token of $ARGUMENTS:
    • new → run the intake interview, write ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/matters/<slug>/matter.md, seed history.md and notes.md.
    • list → enumerate ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/matters/*/matter.md, print a table, mark the active matter.
    • switch → update the Active matter: line in the practice-level CLAUDE.md.
    • close → move ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/matters/<slug>/ to ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/matters/_archived/<slug>/, log the close date in history.md.
    • none → set Active matter: to none — practice-level context only.
  4. Show the user what changed and confirm before writing.

Notes

  • The skill never reads across matters unless Cross-matter context is on in the practice-level CLAUDE.md.
  • Archiving is not deletion — closed matters remain readable for retention/conflicts purposes.
  • Slugs are lowercase with hyphens. If a slug is reused across archived and active, the archived one is preserved under _archived/<slug>/.

Multi-client practitioners (private practice — solo, small firm, large firm) work across many matters. Context from one must not leak into another. This skill is the thin file-management layer that makes that true.

Default state is off. In-house users never see this — they run at practice-level only. Matter workspaces turn on at cold-start for private-practice users, or by editing ## Matter workspaces in the practice-level CLAUDE.md. If Enabled is ✗, this skill does not run; the workflow above explains the disabled state and suggests /ai-governance-legal:cold-start-interview --redo for users who actually need matter isolation.

Storage layout

All matter data lives under:

~/.claude/plugins/config/claude-for-legal/ai-governance-legal/
├── CLAUDE.md                       # practice-level practice profile
└── matters/
    ├── <slug>/
    │   ├── matter.md               # client, counterparty, matter type, key facts, overrides
    │   ├── history.md              # dated log of events, decisions, drafts, reviews
    │   ├── notes.md                # free-form working notes
    │   └── outputs/                # skill outputs for this matter (optional subfolder)
    └── _archived/
        └── <slug>/                 # closed matters — readable but not active

Slugs are lowercase with hyphens. Examples: acme-msa-2026, zenith-renewal, vendor-xyz-nda.

Active matter is in the practice CLAUDE.md

The Active matter: line under ## Matter workspaces in the practice-level CLAUDE.md is the single source of truth. Switching a matter edits that line. No separate state file.

Subcommand logic

new <slug>
  1. Confirm slug is not already present in matters/<slug>/ or matters/_archived/<slug>/. If reused, ask the user to pick a different slug.
  2. Run the intake interview:
    • Client (the party we represent, or the internal business unit if in-house)
    • Counterparty (the other side — may be multiple)
    • Matter type (read the plugin's practice profile for typical categories; for ai-governance-legal: use case (internal) | vendor AI review | AIA | regulatory change | policy project | other)
    • Confidentiality level (standard | heightened | clean-team — heightened prompts extra care in cross-matter settings)
    • Key facts (2–5 sentences: what this matter is about, who the stakeholders are, what's at stake)
    • Matter-specific overrides to the practice playbook (e.g., "client requires 24-month LoL cap not 12", "counterparty is a strategic partner — relationship-preserving tone")
    • Related matters (slugs of any connected matters)
  3. Write matters/<slug>/matter.md using the template below.
  4. Seed matters/<slug>/history.md with a single "Opened" entry.
  5. Create an empty matters/<slug>/notes.md.
  6. Do not auto-switch to the new matter. Ask: "Want to switch to <slug> now? (/ai-governance-legal:matter-workspace switch <slug>)"
Show full SKILL.md (304 more words)Show less
list

Enumerate matters/*/matter.md. Read each file's front-matter or first few lines to extract status. Print a table:

SlugClientMatter typeStatusOpenedActive

Mark the currently-active matter with *. Include _archived/* under a separate "Archived" heading if any exist.

switch <slug>
  1. Confirm matters/<slug>/matter.md exists. If not, offer /ai-governance-legal:matter-workspace new <slug>.
  2. Edit the Active matter: line in the practice-level CLAUDE.md to Active matter: <slug>.
  3. Show the user the matter.md summary so they can confirm they're on the right matter.
close <slug>
  1. Confirm matters/<slug>/ exists.
  2. Append a "Closed" entry to matters/<slug>/history.md with today's date.
  3. Move matters/<slug>/ → matters/_archived/<slug>/.
  4. If the closed matter was the active matter, set Active matter: to none — practice-level context only.
none

Set Active matter: in the practice-level CLAUDE.md to none — practice-level context only. Confirm with the user.

matter.md template

markdown
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this` in the practice-level CLAUDE.md]

# Matter: [Client] — [short description]

**Slug:** [slug]
**Opened:** [YYYY-MM-DD]
**Status:** active
**Confidentiality:** [standard / heightened / clean-team]

---

## Parties

**Client:** [name]
**Counterparty:** [name(s)]

## Matter type

[vendor MSA | customer agreement | NDA | SaaS subscription | amendment | renewal | other — with one-line rationale]

## Key facts

[2–5 sentences. What this matter is about. Who the stakeholders are. What's at stake. What makes it different from the default playbook.]

## Matter-specific overrides

*Any deviation from the practice-level playbook that applies to this matter and only this matter.*

- [e.g., "LoL cap: client requires 24 months, not house standard 12."]
- [e.g., "Tone: relationship-preserving — counterparty is a strategic partner."]
- [e.g., "Governing law: must be English law, not Delaware."]

## Related matters

- [slug — one line why related]

## Notes on confidentiality

[If heightened or clean-team, describe why. Who may see matter files. Whether cross-matter context is permissible even if globally on.]

history.md seed

markdown
# History: [Client] — [short description]

Append-only event log. Most recent at top.

---

## [YYYY-MM-DD] — Matter opened

Intake completed. Slug: `[slug]`. Status: active.
[Any initial context worth preserving beyond matter.md — e.g., "Opened in response to inbound MSA draft from [counterparty]."]

Cross-matter context

The practice-level CLAUDE.md has a Cross-matter context: flag. When it's off (the default), a skill working in matter A never reads files in matters/B/ for any other B. Period. This is the confidentiality guarantee the setting exists to provide.

When it's on, a skill may read files across matter folders only when the user explicitly asks it to (e.g., "compare our position on liability caps across the last five vendor matters"). Even when on, the default is to load only the active matter unless the user asks for a cross-matter view.

What this skill does not do

  • Run a conflicts check. Conflicts are the practitioner's/firm's job; the intake captures what the user declares.
  • Enforce retention. Closing archives a matter; it does not delete. Retention policy is out of scope.
  • Auto-route outputs. The substantive skill decides where to write; this skill tells it which folder is active, not what to put in it.
  • Decide whether cross-matter is appropriate. It reads the flag and obeys.

© 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 ai-governance-legal/skills/matter-workspace of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 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

Matter Workspace 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.

Matter Workspace compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Matter Workspace this skillanthropics/claude-for-legal9.6k3 repos~2.5kAutomated safety check: PassApache-2.0
Dd Audit AI Activitydatadog-labs/agent-skills177—~1.2kAutomated safety check: PassMIT
Matter Workspacezhou210712/claude-for-legal-ZH225—~1.3kAutomated safety check: PassApache-2.0
Iso42001Sushegaad/Claude-Skills-Governance-Risk-and-Compliance9431 repos~3.7kAutomated safety check: PassMIT
AI Risk Managementbriiirussell/cybersecurity-skills413—~3.7kAutomated safety check: NotesMIT
Legal Harness Initializercat-xierluo/legal-skills717—~2.3kAutomated safety check: PassMIT

Similar skills

  • Dd Audit AI Activity

    datadog-labs/agent-skills

    Audit what the Bits AI assistant (MCP server) has done in your Datadog org — tool calls by user, resources accessed, and anomaly flags for AI governance.

    177 GitHub stars~1.2k tokensUpdated yesterday
    Legal & ComplianceAuto-check passed
  • Matter Workspace

    zhou210712/claude-for-legal-ZH

    管理事务工作区——创建、列表、切换、关闭或解除活跃事务. An agent skill from zhou210712/claude-for-legal-ZH.

    225 GitHub stars~1.3k tokensUpdated 4 mo ago
    Legal & ComplianceAuto-check passed
  • Iso42001

    Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

    Expert ISO 42001 AI Management System (AIMS) compliance advisor.

    943 GitHub starsUsed in 1 repo~3.7k tokens
    Legal & ComplianceAuto-check passed
  • AI Risk Management

    briiirussell/cybersecurity-skills

    Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency…

    413 GitHub stars~3.7k tokensUpdated 4 mo ago
    Legal & ComplianceAuto-check: notes
  • Legal Harness Initializer

    cat-xierluo/legal-skills

    Sets up or incrementally updates AGENTS.md and CLAUDE.md for legal professionals, with a minimal safety baseline and a check that a new session loads and follows the rules.

    717 GitHub stars~2.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Eu AI Act Readiness

    seb1n/awesome-ai-agent-skills

    Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency…

    206 GitHub stars~3.3k tokensUpdated 2 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

Questions about Matter Workspace

What does Matter Workspace do?

Manage matter workspaces — new, list, switch, close, or detach (practice-level). Matter Workspace is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Manage matter workspaces — new, list, switch, close, or detach (practice-level).

When should I use Matter Workspace?

Matter Workspace fits situations like: working across multiple clients; the user says new matter; any substantive skill needs to know which matter its working in.

How do I install Matter Workspace in Claude Code?

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

How do I install Matter Workspace in Codex?

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

Can I use Matter Workspace 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 matter-workspace -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/matter-workspace, .gemini/skills/matter-workspace, .github/skills/matter-workspace and .opencode/skills/matter-workspace in your project.

What does Matter Workspace need to run?

SKILL.md names no scripts, command-line tools or credentials: Matter Workspace is instructions for the agent only.

Does Matter Workspace 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 Matter Workspace 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 Matter Workspace use?

Matter Workspace 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 Matter Workspace use?

About 2.5k tokens (SKILL.md is roughly 9.8k 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 Matter Workspace?

Skills that share tags, products or a category with Matter Workspace: Dd Audit AI Activity (datadog-labs/agent-skills, 177 stars), Matter Workspace (zhou210712/claude-for-legal-ZH, 225 stars), Iso42001 (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance, 943 stars) and AI Risk Management (briiirussell/cybersecurity-skills, 413 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Matter Workspace?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,629 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.