
Build Skill
Create, rename, move, audit, test or refine Agent Zero skills and reusable workflows.
Install
npx skills add agent0ai/agent-zero --skill build-skill -g -a claude-code -y- Repository
- agent0ai/agent-zero19.6k
- Category
- Testing
- Updated
- 3d ago
- License
- See repository
- Context cost
- Lightabout 832 tokens
- Runs scripts
- No, instructions only
What it does
Create, rename, move, audit, test or refine Agent Zero skills and reusable workflows.
Build Skill
Skills are small folders that teach Agent Zero a repeatable workflow. Keep the always-visible metadata precise, keep SKILL.md lean, and move detailed material into scripts, references, or assets only when the task needs it.
Standard Shape
Every skill folder must be named exactly like the skill and contain SKILL.md.
skill-name/
├── SKILL.md
├── scripts/ # optional deterministic helpers
├── references/ # optional details loaded only when needed
└── assets/ # optional output resources or templates
The frontmatter should contain name, description, and optional triggers when lexical discovery needs phrases that do not fit naturally in the description:
---
name: skill-name
description: What the skill does and when to use it.
triggers:
- "user phrase that should surface this skill"
---
Use lowercase letters, digits, and hyphens. Prefer short verb-led names such as build-skill, review-plugin, or host-file-editing.
Workflow
- Identify two or three real user requests that should trigger the skill.
- Decide whether the skill belongs in core
skills/or inside a plugin'splugins/<plugin>/skills/directory. - Write the frontmatter description with the core trigger condition and key context; add
triggersfor short user phrases that should rank highly in skill search or relevant-skill recall. - Keep the body focused on procedure, contracts, failure handling, and the files/scripts to load next.
- Move long examples, schemas, policies, or variant-specific detail to one-level-deep
references/files. - Add scripts only for deterministic or repeatedly rewritten operations, and test representative scripts.
- Validate by searching, loading, and using the skill on a median-user prompt.


