Learn what Agent Skills are and how they give AI assistants domain-specific legal expertise
Agent Skills are reusable packages that provide AI assistants with domain-specific expertise.
Each Skill contains detailed instructions and optional resources (templates, playbooks, etc.) 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:
nda-review/
├── SKILL.md # Required: instructions and metadata
├── scripts/ # Optional: executable code
├── references/ # Optional: detailed documentation
└── assets/ # Optional: templates, playbooks, examples
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 a 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.