agent-authority-charter-builder-arkadiy-miteiko
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how the agent can be suspended, revoked, or escalated.
npx skills add lawve-ai/awesome-legal-skills --skill agent-authority-charter-builder-arkadiy-miteiko --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Creates a structured governance artifact called an Agent Authority Charter before deployment of an enterprise or regulated AI agent. It covers agent identity, delegation source, operational scope, permitted and prohibited actions, human approval rules, escalation triggers, evidence and audit requirements, suspension/revocation/kill-switch conditions, and deployment-readiness determination.
How it works
The skill guides users through drafting a formal charter by enumerating core sections: charter metadata, agent identity, authority source, institutional role classification, operational scope, capability vs. authority matrix, permitted actions, prohibited actions, human approval rules, and escalation logic. It requires documenting delegation sources, authority tiers per action, evidence baselines, and suspension/revocation conditions. It instructs producing a deployment-readiness determination and a charter suitable for stakeholders in legal, compliance, risk, security, audit, and technical teams. Tools mentioned include the declared tool "claude-code" for implementation tasks. The workflow emphasizes Step-by-Step drafting across nine sections and a final required output format, ensuring conservative classification and explicit escalation triggers.
When to use it
Use this skill when you need to define the authority and governance for an AI agent before deployment, document agent permissions, prepare for regulatory or internal reviews, distinguish between agent types, define human approvals, escalation, or kill-switch requirements, and assess safe deployment within enterprise or regulated environments.
What it can touch
The skill specifies inputs and artifacts to craft but does not enumerate executable touchpoints beyond structuring the charter. It references a tool named "claude-code" as a declared tool to assist in implementation tasks. The output artifact is the Agent Authority Charter with sections enumerated under Required Output Format.
Caveats
The skill is a drafting aid for governance; it explicitly states not to provide legal conclusions or replace qualified counsel reviews. It requires careful completion of inputs like organization context, agent identity, delegation source, operational scope, and human approvals. It does not itself grant deployment authority and defers to institutional processes for final authorization.
# Agent Authority Charter Builder ## Purpose This Skill helps legal, compliance, risk, product, operations, and AI governance teams create an Agent Authority Charter before an AI agent is deployed into an enterprise or regulated workflow. The purpose is not to decide whether an AI system is generally ethical, safe, or compliant. The purpose is narrower and more operational: Define what institutional authority the agent has before it acts. The Skill converts a proposed AI agent use case into a structured, reviewable governance artifact covering: - agent identity; - principal and delegation source; - operational scope; - permitted actions; - prohibited actions; - human approval rules; - escalation triggers; - evidence and audit requirements; - suspension, revocation, and kill-switch conditions; - deployment-readiness determination. The final output should be suitable for review by legal, compliance, risk, security, business, audit, and technical stakeholders. ## Core Principle An AI agent should not be governed only by what it can technically do. It must be governed by what the institution has authorized it to do. The charter must answer: 1. Who authorized the agent? 2. What is the a
- Purpose
- Core Principle
- When to Use This Skill
- When Not to Use This Skill
- Required Inputs
- 1. Organization Context
- 2. Agent Identity
- 3. Principal and Delegated Authority
- 4. Operational Scope
- 5. Permitted Actions
- 6. Prohibited Actions
- 7. Action Tiers
- Drafting Workflow
- Step 1 — Identify the Agent’s Institutional Role
What does the agent-authority-charter-builder-arkadiy-miteiko skill do?
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how the agent can be suspended, revoked, or escalated.
How do I install it?
Run `npx skills add lawve-ai/awesome-legal-skills --skill agent-authority-charter-builder-arkadiy-miteiko --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From lawve-ai/awesome-legal-skills, a repository with 618 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.