# Superlazy Skill Creator

> Create or improve skills with minimal tokens. Use when the user wants a new skill, wants to edit/optimize an existing skill, or wants a workflow captured as a skill.

- **Type:** Skill
- **Install:** `agentstack add skill-starchybomb-superlazy-superlazy-skill-creator`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [StarchyBomb](https://agentstack.voostack.com/s/starchybomb)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [StarchyBomb](https://github.com/StarchyBomb)
- **Source:** https://github.com/StarchyBomb/superlazy/tree/main/skills/superlazy-skill-creator

## Install

```sh
agentstack add skill-starchybomb-superlazy-superlazy-skill-creator
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Superlazy Skill Creator

SUPERLAZY mode: output ≤3 lines (questions / user-actions / ✅❌); minimal code, full quality; do the work, never narrate it.

## Structure
```
skill-name/
├── SKILL.md            # frontmatter: name, description (required)
└── references|scripts|assets/   # only if genuinely needed
```
Progressive disclosure: description always in context (~100 words) → body loads on trigger → resources load on demand. Push bulk content DOWN a level; scripts execute without being read.

## Token rules (this is the skill's whole point)
- **description** carries ALL triggering info — what it does + when to use, phrased "pushy" (models undertrigger): list concrete user phrases/contexts that must trigger it.
- Body budget ≤100 lines: every line must change model behavior. Delete rationale, motivation, examples that restate rules, tables that repeat prose. Imperative voice only.
- One rule stated once. If you write "in other words" — delete the sentence before it.
- If the skill makes the model produce user-facing output, embed the superlazy output contract line in it.

## Process
1. Missing intent (trigger phrases? output format? edge cases?) → ONE batched question.
2. Draft → self-test: run 2-3 realistic prompts against it, check it triggers and behaves.
3. Iterate on failures. `✅ ` when it passes.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [StarchyBomb](https://github.com/StarchyBomb)
- **Source:** [StarchyBomb/superlazy](https://github.com/StarchyBomb/superlazy)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-starchybomb-superlazy-superlazy-skill-creator
- Seller: https://agentstack.voostack.com/s/starchybomb
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.