Vendor Check logo

Vendor Check

OrganizationPopular
anthropics
vendor-check

Check the status of existing agreements with a vendor across all connected systems — CLM, CRM, email, and document storage — with gap analysis and upcoming deadlines. Use when onboarding or renewing a vendor, when you need a consolidated view of what's signed and what's missing (MSA, DPA, SOW), or when checking for approaching expirations and surviving obligations.

Overview

Publisheranthropics
Repositoryknowledge-work-plugins
Skill namevendor-check
Stars
25.9K
Forks
3K
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by anthropics on GitHub. Read the source before you install it.

Installation

Install the Vendor Check AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/anthropics/knowledge-work-plugins/tree/main/legal/skills/vendor-check
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/anthropics/knowledge-work-plugins.git /tmp/knowledge-work-plugins
mkdir -p .claude/skills
cp -r /tmp/knowledge-work-plugins/legal/skills/vendor-check .claude/skills/vendor-check
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vendor Check in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Vendor Check on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Vendor Check is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/vendor-check -- Vendor Agreement Status

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Check the status of existing agreements with a vendor across all connected systems. Provides a consolidated view of the legal relationship.

Important: This command assists with legal workflows but does not provide legal advice. Agreement status reports should be verified against original documents by qualified legal professionals.

Invocation

/vendor-check [vendor name]

If no vendor name is provided, prompt the user to specify which vendor to check.

Workflow

Step 1: Identify the Vendor

Accept the vendor name from the user. Handle common variations:

  • Full legal name vs. trade name (e.g., "Alphabet Inc." vs. "Google")
  • Abbreviations (e.g., "AWS" vs. "Amazon Web Services")
  • Parent/subsidiary relationships

Ask the user to clarify if the vendor name is ambiguous.

Step 2: Search Connected Systems

Search for the vendor across all available connected systems, in priority order:

CLM (Contract Lifecycle Management) -- If Connected

Search for all contracts involving the vendor:

  • Active agreements
  • Expired agreements (last 3 years)
  • Agreements in negotiation or pending signature
  • Amendments and addenda
CRM -- If Connected

Search for the vendor/account record:

  • Account status and relationship type
  • Associated opportunities or deals
  • Contact information for vendor's legal/contracts team
Email -- If Connected

Search for recent relevant correspondence:

  • Contract-related emails (last 6 months)
  • NDA or agreement attachments
  • Negotiation threads
Documents (e.g., Box, Egnyte, SharePoint) -- If Connected

Search for:

  • Executed agreements
  • Redlines and drafts
  • Due diligence materials
Chat (e.g., Slack, Teams) -- If Connected

Search for recent mentions:

  • Contract requests involving this vendor
  • Legal questions about the vendor
  • Relevant team discussions (last 3 months)

Step 3: Compile Agreement Status

For each agreement found, report:

FieldDetails
Agreement TypeNDA, MSA, SOW, DPA, SLA, License Agreement, etc.
StatusActive, Expired, In Negotiation, Pending Signature
Effective DateWhen the agreement started
Expiration DateWhen it expires or renews
Auto-RenewalYes/No, with renewal term and notice period
Key TermsLiability cap, governing law, termination provisions
AmendmentsAny amendments or addenda on file

Step 4: Gap Analysis

Identify what agreements exist and what might be missing:

## Agreement Coverage

[CHECK] NDA -- [status]
[CHECK/MISSING] MSA -- [status or "Not found"]
[CHECK/MISSING] DPA -- [status or "Not found"]
[CHECK/MISSING] SOW(s) -- [status or "Not found"]
[CHECK/MISSING] SLA -- [status or "Not found"]
[CHECK/MISSING] Insurance Certificate -- [status or "Not found"]

Flag any gaps that may be needed based on the relationship type (e.g., if there is an MSA but no DPA and the vendor handles personal data).

Step 5: Generate Report

Output a consolidated report:

## Vendor Agreement Status: [Vendor Name]

**Search Date**: [today's date]
**Sources Checked**: [list of systems searched]
**Sources Unavailable**: [list of systems not connected, if any]

## Relationship Overview

**Vendor**: [full legal name]
**Relationship Type**: [vendor/partner/customer/etc.]
**CRM Status**: [if available]

## Agreement Summary

### [Agreement Type 1] -- [Status]
- **Effective**: [date]
- **Expires**: [date] ([auto-renews / does not auto-renew])
- **Key Terms**: [summary of material terms]
- **Location**: [where the executed copy is stored]

### [Agreement Type 2] -- [Status]
[etc.]

## Gap Analysis

[What's in place vs. what may be needed]

## Upcoming Actions

- [Any approaching expirations or renewal deadlines]
- [Required agreements not yet in place]
- [Amendments or updates that may be needed]

## Notes

[Any relevant context from email/chat searches]

Step 6: Handle Missing Sources

If key systems are not connected via MCP:

  • No CLM: Note that no CLM is connected. Suggest the user check their CLM manually. Report what was found in other systems.
  • No CRM: Skip CRM context. Note the gap.
  • No Email: Note that email was not searched. Suggest the user search their email for "[vendor name] agreement" or "[vendor name] NDA".
  • No Documents: Note that document storage was not searched.

Always clearly state which sources were checked and which were not, so the user knows the completeness of the report.

Notes

  • If no agreements are found in any connected system, report that clearly and ask the user if they have agreements stored elsewhere
  • For vendor groups (e.g., a vendor with multiple subsidiaries), ask whether the user wants to check a specific entity or the entire group
  • Flag any agreements that are expired but may still have surviving obligations (confidentiality, indemnification, etc.)
  • If an agreement is approaching expiration (within 90 days), highlight this prominently

Frequently asked questions

What does the Vendor Check AI skill do?

Check the status of existing agreements with a vendor across all connected systems — CLM, CRM, email, and document storage — with gap analysis and upcoming deadlines. Use when onboarding or renewing a vendor, when you need a consolidated view of what's signed and what's missing (MSA, DPA, SOW), or when checking for approaching expirations and surviving obligations.

Why use Vendor Check on TypingMind?

Because you install it once and use it with any model. Vendor Check is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Vendor Check in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anthropics/knowledge-work-plugins/tree/main/legal/skills/vendor-check. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Vendor Check?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Vendor Check?

As many as you like. As long as a model supports skills, you can use Vendor Check with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Vendor Check AI skill free?

Yes. It is published on GitHub by anthropics under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇