Files

feat(skills): modernize capability-writing with Anthropic best practices

Updates capability-writing skill with progressive disclosure structure based on
Anthropic's January 2025 documentation. Implements Haiku-first approach (12x
cheaper, 2-5x faster than Sonnet).

Key changes:
- Add 5 core principles: conciseness, progressive disclosure, script bundling,
  degrees of freedom, and Haiku-first model selection
- Restructure with best-practices.md, templates/, examples/, and reference/
- Create 4 templates: user-invocable skill, background skill, agent, helper script
- Add 3 examples: simple workflow, progressive disclosure, with scripts
- Add 3 reference docs: frontmatter fields, model selection, anti-patterns
- Update create-capability to analyze complexity and recommend structures
- Default all new skills/agents to Haiku unless justified

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

2026-01-11 18:10:53 +01:00

1.4 KiB

Raw Blame History

name, description, model, argument-hint, user-invocable

name	description	model	argument-hint	user-invocable
skill-name	Clear description of what this skill does and when to use it. Use when [specific trigger conditions] or when user says /skill-name.	haiku	<required-param> [optional-param]	true

Skill Title

@~/.claude/skills/relevant-background-skill/SKILL.md

Brief intro explaining the skill's purpose (1-2 sentences max).

Process

First step: Clear action with specific command or instruction
- command or tool to use
- What to look for or validate
Second step: Next action
- Specific details
- Expected output
Ask for approval before significant actions
- Show what will be created/modified
- Wait for user confirmation
Execute the approved actions
- Run commands/create files
- Handle errors gracefully
Present results with links and summary
- Structured output (table or list)
- Links to created resources

Guidelines

Keep responses concise
Use structured output (tables, lists)
No preambles or sign-offs
Validate inputs before acting

Output Format

Use this structure for responses:

```

Summary

[1-2 sentences]

Results

Item	Status	Link
...	...	...

Next Steps

... ```

1.4 KiB Raw Blame History