Snoozer10/synthesize-skills / .agents/skills/skill-creator
skill-creator
VerifiedUse when authoring, scaffolding, validating, or packaging new reusable AI-agent skills across multiple agent ecosystems.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.4 KB |
| scripts/init_skill.py | script | 3.6 KB |
SKILL.md
View on GitHub---
name: skill-creator
description: Use when authoring, scaffolding, validating, or packaging new reusable AI-agent skills across multiple agent ecosystems.
---
# skill-creator
Standardized scaffolding and authoring toolkit for cross-host AI-agent skills.
## Quickstart
Initialize a new skill with valid metadata, directory layout, and starter files:
```bash
# Scaffold a new skill in .agents/skills
python scripts/init_skill.py my-new-skill --desc "Use when performing tasks with my new skill." --keywords "tools, tasks, automation"
```
```powershell
# Windows PowerShell invocation
python scripts/init_skill.py my-new-skill --desc "Use when performing tasks with my new skill." --keywords "tools, tasks, automation"
```
## Operations
### 1. Scaffolding Structure
Running `init_skill.py` creates a directory conforming to the agentskills.io standard:
- `SKILL.md` with YAML frontmatter (`name`, `description`).
- `scripts/` directory for execution utilities.
- `references/` directory for supplementary documentation.
### 2. Validation Pre-Flight
Always validate newly scaffolded or edited skills before committing:
```bash
python scripts/validate.py .agents/skills/my-new-skill
```
### 3. Multi-Host Compilation
Once the skill passes validation, compile adapters across host directories:
```bash
python scripts/manifest.py
python scripts/compile_adapters.py
```
## Keywords
skill-creator, scaffold, authoring, agentskills, init_skill, skills-engine
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |