OpenWriterControle/plugins/claude-code/scripts/context/openagents-repo/guides/creating-skills.md
Darren Hinde a8fc9c7715
feat(plugin): enhance context management and skill invocation (#239)
* fix(shellcheck): declare and assign separately in router.sh (SC2155)

* feat(plugin): enhance context management and skill invocation

- Update .context-manifest.json to include profile and detailed source information.
- Revise context-scout.md to clarify context root discovery and navigation.
- Modify commands to replace deprecated skills with updated ones (brainstorming → approach, systematic-debugging → debugger).
- Streamline install-context.md for clarity and remove interactive profile selection.
- Improve oac-status.md to provide a more comprehensive status report.
- Add OAC system paths to session-start.sh for better context management.
- Remove obsolete skills and improve documentation for existing commands.
2026-02-23 12:12:29 +00:00

83 lines
1.8 KiB
Markdown

<!-- Context: openagents-repo/guides | Priority: high | Version: 1.0 | Updated: 2026-02-15 -->
# Creating Skills
**Purpose**: Step-by-step guide to create Agent Skills
---
## Quickstart
1. **Create directory**:
```bash
mkdir -p ~/.claude/skills/my-skill
```
2. **Create SKILL.md** with frontmatter:
```yaml
---
name: my-skill
description: What it does and when to use it
---
Instructions for Claude...
```
3. **Verify**: Ask Claude "What Skills are available?"
4. **Test**: Ask Claude something matching the description
---
## Writing Good Descriptions
The description determines when Claude uses the skill. Include:
- **What it does**: List specific capabilities
- **When to use**: Include trigger terms users would say
```yaml
# Bad
description: Helps with documents
# Good
description: Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
```
---
## Progressive Disclosure
Keep `SKILL.md` under 500 lines. Use supporting files for details:
```
my-skill/
├── SKILL.md # Overview (required)
├── reference.md # Detailed docs (loaded when needed)
├── examples.md # Usage examples
└── scripts/
└── helper.py # Utility script (executed, not loaded)
```
Reference in SKILL.md:
```markdown
For complete API details, see reference.md (example file)
```
---
## Key Points
- Skills are loaded automatically (no restart needed)
- Use `claude --debug` to see loading errors
- Skills cannot spawn subagents
- Use allowed-tools to restrict capabilities
---
## Related
- `../concepts/agent-skills.md` - Skills overview
- `../lookup/skill-metadata.md` - All metadata fields
- `../examples/skills/` - Example skills
**Reference**: https://docs.anthropic.com/en/docs/claude-code/skills