// Create effective skills for OpenCode agents. Load FIRST before writing any SKILL.md. Provides required format, naming conventions, progressive disclosure patterns, and validation. Use when building, reviewing, or debugging skills.
| name | build-skill |
| description | Create effective skills for OpenCode agents. Load FIRST before writing any SKILL.md. Provides required format, naming conventions, progressive disclosure patterns, and validation. Use when building, reviewing, or debugging skills. |
Skills extend agent capabilities with specialized knowledge, workflows, and tools.
Minimal viable skill in 30 seconds:
mkdir my-skill && cat > my-skill/SKILL.md << 'EOF'
---
name: my-skill
description: Does X when Y happens. Use for Z tasks.
---
# My Skill
Instructions go here.
EOF
Place in .opencode/skills/ (project) or ~/.config/opencode/skills/ (global).
What are you building?
โโ Instructions only โ Simple skill (SKILL.md only)
โ Example: code-review guidelines, commit message format
โ
โโ Domain knowledge โ Reference-heavy skill (+ references/)
โ Example: API docs, database schemas, company policies
โ
โโ Repeatable automation โ Script-heavy skill (+ scripts/)
โ Example: PDF processing, data validation, file conversion
โ
โโ Complex multi-step workflow โ Multi-file skill (all directories)
โ Example: release process, deployment pipeline
โ
โโ Large platform โ Progressive skill
Example: AWS, GCP, Cloudflare (60+ products)
Create a skill when:
| Scenario | Do Instead |
|---|---|
| Single-use instructions | AGENTS.md or inline in conversation |
| Model already knows domain | Don't add redundant context |
| < 3 steps, no reuse | Inline instructions |
| Highly variable workflow | Higher-freedom guidelines |
| Just want to store files | Use regular directories |
| Task | Files to Read |
|---|---|
| New skill from scratch | anatomy.md โ frontmatter.md |
| Optimize existing skill | progressive-disclosure.md |
| Add scripts/resources | bundled-resources.md |
| Find skill pattern | patterns.md |
| Debug/fix skill | gotchas.md |
| File | Purpose |
|---|---|
| anatomy.md | Skill directory structures |
| frontmatter.md | YAML spec, naming, validation |
| progressive-disclosure.md | Token-efficient design |
| bundled-resources.md | scripts/, references/, assets/ |
| patterns.md | Real-world skill patterns |
| gotchas.md | Common mistakes + fixes |
| Script | Purpose |
|---|---|
scripts/init_skill.sh | Scaffold new skill |
scripts/validate_skill.sh | Validate skill structure |
scripts/package_skill.sh | Create distributable zip |
Before using a skill:
--- (line 1, no blank lines)name: field present, matches directory namedescription: includes what + when to use--- after frontmatterRun: ./scripts/validate_skill.sh ./my-skill
| Priority | Location |
|---|---|
| 1 | .opencode/skills/<name>/ (project) |
| 2 | ~/.config/opencode/skills/<name>/ (global) |
| 3 | .claude/skills/<name>/ (Claude-compat) |
Discovery walks up from CWD to git root. First-wins for duplicate names.