Arm the zero rung: cut temporary automatic skills while manual summon remains available, or cut all skills.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add gaia-research/gaia-skill-heaven --skill skill-zero --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Skill Zero?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gaia-research-skill-zero)More formats (shields.io, HTML) on the badges page.
---
name: skill-zero
description: "Arm the zero rung: cut temporary automatic skills while manual summon remains available, or cut all skills."
disable-model-invocation: true
---
# Skill Zero
Set the routing posture to `zero`. A session sits at exactly one rung.
```text
zero · low · med · high · xhigh · max · ultra
```
The default `temporary` cut means temporary automatic summoning is cut while manual `/summon` remains available. If the user explicitly requested the `all` cut, all skill summons, including manual `/summon`, are cut.
Already-loaded skills cannot be evicted mid-session. This setting changes summoning routing; it does not empty or restart the running session. Do not call the `summon` tool from this skill.
No rung carries a count and no summon is capped. Invocation metadata still distinguishes human-led Skill Heaven skills from model-led Skill Hell skills; zero changes whether either surface may summon, not the source classification.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...