agentleFS
Sign inStart free
eigent-aieigent-ai/agent-skills/skills/pdf-and-documents/legal-work-plugin/SKILL.md

legal-work-plugin

Skill27 starsChanged 8 months agoApache-2.0View on GitHub

In-house legal workflows for contract review against playbooks, NDA triage with GREEN/YELLOW/RED ratings, compliance briefings, and vendor checks. Use when the user invokes /review-contract, /triage-nda, /legal-risk-assessment, or /vendor-check for organisation-standard legal analysis.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If no playbook exists, run a quick intake:

    line 62
  2. Distinctive:

    When playbook conflicts with user's stated priorities, ask which takes precedence.

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Legal Work Plugin

Anthropic's knowledge work plugin suite — legal plugin for in-house counsel workflows.

Source Repository

Connects to Slack, Box, Egnyte, Jira, and Microsoft 365 when configured.

/review-contract

Reviews incoming contracts against the organisation's negotiation playbook.

Workflow:

  1. Load or ask for the negotiation playbook (standard terms, liability caps, IP, termination, etc.).
  2. Compare each clause to playbook standards.
  3. Flag deviations by severity.
  4. Classify each issue: blocker / negotiate / accept.
  5. Draft redline language for blockers in house style.
  6. Produce business impact summary alongside legal analysis.

Pair with /legal-risk-assessment for scored output and escalation recommendation.

Example prompts:

  • Review this vendor MSA [paste]. Flag playbook deviations. Classify as blocker/negotiate/accept; draft redlines for blockers.
  • Review-contract then legal-risk-assessment — severity breakdown (critical/high/medium/low) and escalation: can legal sign off or needs CFO?
  • /vendor-check [vendor name] — status of existing agreements, renewals, open issues, prior accepted deviations.

/triage-nda

Rapid first-pass NDA screening before lawyer review.

Output:

  • GREEN — sign as-is
  • YELLOW — negotiate specific clauses
  • RED — escalate to counsel

Includes key reason, routing recommendation, and clauses that triggered the flag.

Example prompts:

  • Triage this NDA from a new partner [paste]. GREEN/YELLOW/RED? What triggered the rating?
  • Batch triage 5 NDAs [paste sequentially]. Rating per NDA; flag only those needing human review. Output as table.
  • Triage NDA then brief — signing with [company] tomorrow. Triage + 5-minute briefing on conversation watchpoints.

Playbook Setup

If no playbook exists, run a quick intake:

  • Standard liability cap formula
  • Acceptable indemnification scope
  • IP ownership defaults
  • Termination rights
  • Data processing requirements
  • Non-compete / non-solicit policy

Store answers for consistent future reviews.

Guardrails

  • Decision support only — not a substitute for licensed counsel.
  • When playbook conflicts with user's stated priorities, ask which takes precedence.
  • For RED NDAs, always list specific clauses and suggested fallback language.
  • Batch triage: use a consistent table format for quick scanning.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free