Agent Skills are reusable packages that provide AI assistants with domain-specific expertise. Each Skill contains detailed instructions and optional resources—such as templates, playbooks, and reference materials—that the assistant uses autonomously to complete a task. Think of a Skill like an onboarding guide you would create for an intern. It captures how to approach specific types of work: the methodology to follow, the things to check, the format to use for deliverables, and more. Why use Skills Unlike prompts, which are one-off instructions for a single conversation, Skills persist across sessions. You define your methodology once, and the assistant applies it consistently whenever that type of task arises. For legal work, this has practical implications: Consistency across the team. A contract review Skill ensures the same checklist gets applied whether the work is done Monday morning or Friday evening, by you or a colleague. The methodology is encoded in the Skill itself. Knowledge that stays. Expertise that would otherwise exist only in someone's head can be captured and shared. When a senior lawyer develops an effective approach to due diligence or regulatory analysis, that approach can become a Skill that benefits the entire team. Less repetition. Instead of explaining preferences and requirements at the start of each conversation, the Skill provides that context automatically. The agent already knows how you want the work done. What a Skill contains At its core, a Skill is a folder containing a SKILL.md file: The SKILL.md file is a simple text document with a small header—the Skill's name and description—followed by the actual instructions. The agent reads the header to know when the Skill might be relevant, then loads the full instructions when needed. Additional files in the folder provide supporting material. Reference documents might contain jurisdiction-specific guidance. Scripts can automate custom processing logic. Assets might include templates for common deliverables. The format is intentionally simple: readable text files that anyone can edit, version, and share. An open standard Agent Skills were created by Anthropic and initially designed for their Claude model. However, the format became an open standard that other providers are beginning to adopt. The goal is portability: a Skill written today for Claude should work with other AI assistants as they add support for the format. Rather than building workflows locked to a single vendor, Skills aim to be a common language for teaching AI agents how to handle specialized tasks.

The open legal automation ecosystem is growing quickly. More and more practicing lawyers, in-house counsel, law professors, and legal technologists are publishing the workflows they use every day as Agent Skills. Each of these skills is a specific unit of expertise. It captures the working method for one slice of the broad legal domain. As that ecosystem grows, the practical problem becomes finding the right skill at the right moment. Today, Lawve AI collaborates with Anthropic to make expert-built legal skills easier to discover inside Claude as part of Anthropic's Claude for the Legal Industry launch. With the Lawve AI connector, Claude users can search and browse the curated public catalog of practice-specific skills from the Lawve AI community hub, complementing Claude's native legal capabilities. Inside Claude The Lawve AI connector connects Claude to the public catalog so practitioner-authored skills become discoverable from inside a conversation. With the connector, you can: - Search the catalog by topic, jurisdiction, language, or workflow - Apply a Skill inside a Claude conversation - See which Skill was selected, who wrote it, and what it covers - Inspect the full methodology before acting on it Skills are starting points for professional review, not legal advice. Specific by design Skills on Lawve AI are written by people who do the work. Together, the catalog covers ground that's hard to generalize: subspecialty practices, jurisdictional variation, cross-border frameworks, language-specific drafting. The Lawve AI community is open and growing. A practical step Claude for Legal is an important step in making AI more useful for legal professionals. The Lawve AI connector helps users go a step deeper by bringing community-built, practice-specific skills into Claude. The connector is available today in the official Connectors directory.

Choose Your Setup Getting started with Skills requires two simple choices: which AI agent to use and from which platform to run it. | Provider | AI Agent | Platforms | Plans | | --------- | --------- | -------------------------------------------------------------------------- | --------------------------------- | | Anthropic | Claude | VS Code, Claude Code (CLI), Claude Web (Chat), Claude Desktop (Cowork) | → | | OpenAI | GPT-Codex | VS Code, Codex CLI, Codex Desktop | → | | Google | Gemini | VS Code, Gemini CLI | → | | Mistral | Devstral | VS Code, Vibe CLI | → | | Manus | Manus | Manus Web | → | This guide focuses on the friendly interfaces suited for non-tech users only. Advanced users can always use the CLI tool of any provider. On the Web Using Manus [v] Zero setup. No software to install. Visit a website and start working. [x] Limited file access. Only a limited number of files can be uploaded per conversation. Manus cannot browse or access local folders on your computer directly. 1. Download a Skill you like from the Hub. 2. Log in to manus.im. Click the settings icon in the bottom left corner, then "Skills". 3. Click "+ Add Upload a skill" and upload the downloaded Skill file. 4. Click on "New task" in the left sidebar and start working with Manus. Using Claude Chat [v] Zero setup. No software to install. Visit a website and start working. [x] Limited file access. Only a limited number of files can be uploaded per conversation. Claude cannot browse or access local folders on your computer directly. 1. Download a Skill you like from the Hub. 2. Log in to claude.ai. Click the profile icon in the bottom left corner, then "Settings". 3. Go to "Capabilities" and make sure that "Code execution and file creation" is turned on. 4. Scroll to the "Skills" section, click "+ Add", and upload the downloaded Skill file. 5. Click on "New chat" in the left sidebar and start working with Claude. On Desktop Using Codex [v] Direct access to local files. The desktop application of Codex can browse, read, search, edit, or create documents on your computer. 1. Download a Skill you like from the Hub. 2. Download the Codex app. Once logged in, click "New thread" in the left sidebar. 3. Click "+ Add photos & files" in the bottom left of the input box and upload the downloaded Skill file. 4. Enter the following message and click the send button: "Install the attached skill into my library". 5. Once installed, start working with Codex. Using Claude Cowork [v] Direct access to local files. The desktop application of Claude can browse, read, search, edit, or create documents on your computer. 1. Download a Skill you like from the Hub. 2. Download the Claude app. Once logged in, click on the icon in the bottom left corner, then "Settings". 3. Go to "Capabilities" and make sure that "Code execution and file creation" is turned on. 4. Scroll to the "Skills" section, click "+ Add", and upload the downloaded Skill file. 5. In the Cowork tab, click "New task" in the left sidebar and start working with Claude. Using VS Code w/ Lawve AI [v] Open-source and customizable. VS Code is a highly customizable, open-source editor. Customize layouts, pick your theme, and install extensions from a vast marketplace. Switch between Claude, Codex, or other models with no lock-in — using your existing subscriptions or pay-per-use API access. For strict data control, connect to regional cloud providers. [v] Simplified Lawve AI preset. VS Code can look intimidating for non-technical users. This guide includes a preset that streamlines the interface, pre-installs extensions and Skills for legal work, and sets up AI agents automatically. No terminal commands required. 1. Download the VS Code app. 2. Import the Lawve AI preset: a. Click the gear icon in the bottom left corner, then "Profile (Default) Profiles". b. Click the down chevron next to "New Profile", then "Import Profile...". c. Paste the following link: <copyhttps://gist.github.com/ant-louis/e79a61a5d1fa5c05b802e00661f8885e</copy d. Hover over the new "Lawve AI" profile and click the checkmark to activate it. e. Press Enter, then click "Create". 3. Click on "Open Folder" in the left sidebar and select your working directory. Start working with your favorite AI agent in the right panel.

Skills capture methodologies and expertise in a format AI agents can follow consistently. For example, how a particular firm reviews contracts, what a specific checklist covers, or how certain documents should be formatted. The easiest way to create Skills is through conversation with your preferred AI agent. Invoke the skill-creator Skill, describe your workflow naturally, and let the agent handle the formatting and structure. No technical expertise required. How to start 1. Start a new chat and describe the intended Skill: - "I want to create a skill for reviewing NDAs" - "I need a skill that follows our due diligence checklist" - "Help me create a skill for drafting GDPR-compliant privacy policies" 2. Answer the AI agent's questions about the process. The goal is to provide enough detail that someone capable but unfamiliar could follow the approach. Specific answers produce more effective Skills. 3. Upload materials that demonstrate the approach (templates, checklists, examples, etc.). The AI agent uses these to understand the methodology. How to test Testing involves describing a task the Skill should address. "Using [skill name]" appears in the agent's thinking when the Skill activates. If something is off, the agent can update the Skill based on feedback. How to improve Skills improve through use. Starting simple and refining based on real tasks works better than trying to anticipate everything upfront. - Start with evaluation. Run the Skill on real-world scenarios and observe where the AI agent struggles or produces unexpected results. Pay attention to whether it triggers when expected, whether it follows the right steps, and whether the output matches standards. - Iterate and refine. When the AI agent goes off track, ask it to reflect on what went wrong and suggest updates. When it handles a task well, ask it to capture that approach. Let the agent adjust accordingly by invoking the self-improvement Skill. What makes a good Skill? Effective Skills typically contain: - Context: When the workflow applies, what triggers it, what falls outside its scope. - Process: The steps followed, what gets checked, what gets flagged, how output is structured. - Examples: Documents showing the preferred approach or format. - Reference materials: Policy guides, checklists, templates, playbooks, style guides, regulatory requirements.

Skills, connectors, and plugins all extend what an AI agent can do, but they solve different problems. The simplest way to distinguish them is to ask three questions: - A Skill answers: How should the agent perform this work? - A connector answers: Which external information and actions can the agent access? - A plugin answers: How can a complete capability be packaged, installed, and maintained? They are not competing formats. A useful agent workflow often combines all three. The short version | | Skill | Connector | Plugin | | -------------------- | ------------------------------------------------------ | ---------------------------------------------------------- | ------------------------------------------------------------------------ | | Purpose | Package expertise and a repeatable method | Connect the agent to external systems | Distribute a complete set of capabilities | | Think of it as | A playbook | A secure bridge | An installable toolkit | | Typical contents | Instructions, references, templates, examples, scripts | Tools and data exposed through a defined interface | Skills, connector configurations, commands, hooks, scripts, and settings | | Use it when | The agent needs to follow a consistent process | The agent needs current data or must act in another system | Several components should be installed and versioned together | A Skill packages expertise General-purpose agents are capable, but they do not automatically know your professional methodology, preferred structure, fallback positions, or quality standards. A Skill provides that missing guidance. An Agent Skill is an organized folder of files that packages procedural knowledge. Its main file explains what the Skill is for and how the agent should approach the task. The folder can also include clause libraries, templates, examples, checklists, reference material, or small supporting scripts. For example, an NDA review Skill might tell the agent to: 1. Identify which party the user represents. 2. Compare each clause with the firm's preferred positions. 3. Flag unusual confidentiality exclusions and term lengths. 4. Explain the practical risk of each deviation. 5. Produce comments and proposed drafting in a consistent format. The Skill does not need access to a remote system to be useful. It can work with a document the user provides. Its purpose is to make the agent's execution more consistent and closer to the method of a domain expert. Because Skills are folders, they are easy to inspect and move. Teams can version them in Git, store them in a shared drive, adapt them to a particular practice, or zip and share them without adopting a new proprietary format. A connector gives the agent access A connector links an agent to information or actions outside the current conversation. On Lawve, connectors generally use the Model Context Protocol, or MCP, an open standard for connecting AI applications to external tools and data. A connector might let an agent: - Search legislation, case law, or regulatory decisions. - Retrieve a document from SharePoint, Google Drive, iManage, or NetDocuments. - Read matter information from a practice-management system. - Create a task, update a record, or save an approved document. The connector defines what the agent is allowed to request and how the external system responds. Authentication and permissions are managed at that boundary, so the agent only receives the access granted to it. What a connector does not provide is the professional method. Access to a case-law database does not tell the agent which authorities are persuasive, how to assess conflicting decisions, or how to present the conclusion. That methodology belongs in a Skill. The distinction is therefore simple: a Skill tells the agent what to do and how to do it; a connector gives it the information or actions needed to carry out the work. A plugin packages a complete capability A plugin is an installable and versioned package for distributing a broader capability. Depending on the AI application it targets, a plugin can bundle Skills, connector configurations, commands, hooks, scripts, and related settings behind one manifest. Imagine a legal team wants to distribute a complete privacy-notice review workflow. Installing each part separately would require users to locate the right Skill, configure the correct legal-source connector, add supporting commands, and keep every component compatible as they evolve. A plugin can assemble those pieces once and distribute them as one named version. Everyone who installs that version receives the same setup, and an update can be released as a new version with clear release notes. A plugin is not a new form of intelligence. The underlying Skill still provides the method, and the connector still provides access. The plugin is the delivery and maintenance layer that keeps the pieces together. Plugin formats can vary between AI applications, so compatibility matters. Before installing one, check which host it supports, what it contains, which external systems it connects to, and what permissions it requests. How they work together Consider an agent that reviews a supplier agreement and records the result in the firm's matter system. The Skill contains the review methodology: the clauses to identify, the firm's preferred positions, the risk scale, and the expected output. The connector retrieves the agreement and relevant matter information, searches an approved precedent library, and saves the final review to the correct record. The plugin packages the Skill, connector configuration, commands, and supporting settings so the whole workflow can be installed consistently across the team. Removing any one layer changes the result: - Without the Skill, the agent has access but no reliable review method. - Without the connector, the agent can follow the method but needs the user to provide and move the information manually. - Without the plugin, the workflow can still work, but every user must assemble and maintain its components separately.