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

1.1 KiB

Raw Blame History

name, description, user-invocable

name	description	user-invocable
skill-name	What this skill teaches and when to use it. Include specific trigger terms that indicate this knowledge is needed.	false

Skill Name

Brief description of the domain or knowledge this skill covers (1-2 sentences).

Core Concepts

Fundamental ideas Claude needs to understand:

Key concept 1
Key concept 2
Key concept 3

Patterns and Templates

Reusable structures and formats:

Pattern 1: Common Use Case

``` Example code or structure ```

Pattern 2: Another Use Case

``` Another example ```

Guidelines

Rules and best practices:

Guideline 1
Guideline 2
Guideline 3

Examples

Example 1: Simple Case

``` Concrete example showing the skill in action ```

Example 2: Complex Case

``` More advanced example ```

Common Mistakes

Pitfalls to avoid:

Mistake 1: Why it's wrong and what to do instead
Mistake 2: Why it's wrong and what to do instead

Reference

Quick-reference tables or checklists:

Command	Purpose	Example
...	...	...

1.1 KiB Raw Blame History