- create-skill: superseded by native /skill command and official docs - orchestrator: superseded by native Agent Teams (/agent-teams) - notediscovery: redundant with cognitive-memory MCP (superior local-first implementation) All moved to _archive/ for historical reference. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1.5 KiB
1.5 KiB
| name | description |
|---|---|
| skill-name | Clear description of what skill does and when to use. USE WHEN user says 'trigger phrase', 'another phrase', or requests this capability. |
Skill Name
When to Activate This Skill
- User requests X
- User says "trigger phrase"
- Task involves Y capability
- Related intent Z
Core Workflow
[Main instructions in imperative form - verb-first, actionable steps]
Step 1: [Action]
[Specific instructions]
Step 2: [Action]
[Specific instructions]
Key Commands / Tools
# Primary command
command-example --flag value
# Alternative usage
command-example -u "url" --option
Common Patterns
Pattern 1: [Use Case Name]
[Instructions for this specific use case]
# Example command
command "input" -p pattern
Pattern 2: [Use Case Name]
[Instructions for another use case]
# Example command
command -f file.txt --process
Examples
# Example 1: Basic usage
command "simple input" -p basic
# Example 2: Advanced usage
cat file.txt | command -p advanced --output result.json
# Example 3: With URL
command -u "https://example.com" -p pattern
Options / Configuration
--flag1: What it does--flag2: What it does-p pattern: Pattern selection
Supplementary Resources
For advanced usage: read ${PAI_DIR}/docs/[resource].md
For related tools: read ${PAI_DIR}/docs/[tool].md
Key Principles
- Principle 1 - Brief explanation
- Principle 2 - Brief explanation
- Principle 3 - Brief explanation