v1.2.0 to v1.2.0

1 added, 1 removed. Audit A to A.

---
name: skill-creator
display-name: Skill Creator
description: Create, modify, test, and improve skills - scaffold new SKILL.md files with proper frontmatter, generate handler.js implementations, run test evaluations, and optimize skill descriptions for better triggering
version: 1.2.0
category: system
user-invocable: true
tags: [skill, creator, scaffold, meta, generator, template, test, improve, optimize, eval]
capabilities: [skill-scaffolding, handler-generation, skill-testing, description-optimization, description-optimization-loop, template-management]
- execution-capabilities: [data:result, data:task, filesystem:read, filesystem:write, host:electron, host:environment, host:logger, host:process, host:skill-registry, process:cwd, process:execute, runtime:random, runtime:time, system:inspect]
+ execution-capabilities: [data:result, data:task, filesystem:read, filesystem:write, host:electron, host:environment, host:filesystem, host:logger, host:process, host:skill-registry, process:cwd, process:execute, runtime:random, runtime:time, system:inspect]
handler: ./handler.js
os: [win32, darwin, linux]
tools: [skill-scaffold, skill-test, skill-optimize, skill-validate]
instructions: |
Use this skill when the user wants to create a new skill, modify an existing
skill, test a skill with sample inputs, or optimize skill triggering. Follows
the Agent Skills open standard with YAML frontmatter + Markdown body. Generates
both SKILL.md and handler.js with proper structure. Makes descriptions slightly
"pushy" for better triggering accuracy. Use optimize-description for LLM-driven
eval loop that auto-improves and writes back the best description.
examples:
- input: "create a skill for data validation"
action: create
- input: "test the smart-search skill with sample queries"
action: test
- input: "optimize the description of browser-automation"
action: optimize
- input: "validate my-skill SKILL.md format"
action: validate
author: ChainlessChain
license: MIT
---
# Skill Creator
Create, test, and improve skills for the Agent Skills system.
## Usage
```
/skill-creator create <name> "<description>"
/skill-creator test <skill-name> "<test input>"
/skill-creator optimize <skill-name>
/skill-creator optimize <skill-name> --advanced [--iterations N]
/skill-creator optimize-description <skill-name> [--iterations N]
/skill-creator validate <skill-path>
/skill-creator list-templates
```
## Skill Anatomy
```
skill-name/
├── SKILL.md (required) YAML frontmatter + Markdown instructions
└── handler.js (required) init() + execute() exports
```
### SKILL.md Structure
```yaml
---
name: my-skill # Unique identifier (lowercase, hyphens)
display-name: My Skill # Human-readable name
description: What + When # CRITICAL: include what it does AND when to use it
version: 1.0.0
category: development # knowledge|automation|development|system|media|productivity
user-invocable: true
tags: [relevant, keywords]
capabilities: [what-it-can-do]
handler: ./handler.js
os: [win32, darwin, linux]
tools: [tool-names]
instructions: |
When to use this skill and how
examples:
- input: "example command"
action: action-name
---
# Skill Title
## Usage
## Actions
## Examples
```
### handler.js Structure
```javascript
module.exports = {
async init(skill) {
/* load dependencies */
},
async execute(task, context = {}, skill) {
const input = task.input || task.args || "";
// Parse input, execute action, return result
return { success: true, action, result, message };
},
};
```
## Writing Tips
- **Description**: Include both what + when. Be slightly "pushy" for better triggering
- **Keep SKILL.md under 500 lines**; use reference files for more
- **Progressive Disclosure**: Metadata always loaded, body loaded on trigger
- **Examples are crucial**: Include 2-4 realistic usage examples
- **Test early**: Create test cases after initial draft
## Actions
| Action | Description |
| ---------------------- | -------------------------------------------------------------------------------------------------------------------- |
| `create` | Scaffold SKILL.md + handler.js from name/description |
| `test` | Run skill with sample input and verify output |
| `optimize` | Quick heuristic check on description (length, keywords) |
| `optimize-description` | LLM-driven eval loop: generate 20 queries → 60/40 split → iterate up to 5× → write best description back to SKILL.md |
| `validate` | Check SKILL.md format and required fields |