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.
Install
$ agentstack add skill-starchybomb-superlazy-superlazy-skill-creator ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-starchybomb-superlazy-superlazy-skill-creator) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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 neededProgressive 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
- Missing intent (trigger phrases? output format? edge cases?) → ONE batched question.
- Draft → self-test: run 2-3 realistic prompts against it, check it triggers and behaves.
- 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
- Source: StarchyBomb/superlazy
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.