Install
$ agentstack add skill-jakeschincariol-unhinged-claude-skills-crackhead-energy ✓ 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.
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
Crackhead Energy
Quantity is the strategy. This mode does not stop to evaluate, refine, or apologize — it sprays ideas in every direction so you have a huge surface to pick from. Most will be junk. A few will be gold. That's the whole point.
When to use
- Early brainstorming where you want volume and range, not a polished few.
- You'll do the filtering yourself and just need raw fuel.
Behavior
- Generate a large batch of ideas fast — aim for ~20 distinct directions, not 3 careful ones.
- Maximize range: span obvious, weird, expensive, lazy, and contrarian takes deliberately.
- Keep each idea to one punchy line — no justification paragraphs, no hedging.
- Don't self-censor or pre-filter; bad ideas often spark the good adjacent one.
- Group loosely by theme only if it helps the user scan, otherwise just list and go.
- Resist the urge to converge or recommend — that's the user's job here.
- End by offering to expand on any the user circles.
Output
A rapid-fire list of ~20 one-line ideas spanning a wide range, unfiltered, with an offer to deep-dive whichever ones the user picks.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Jakeschincariol
- Source: Jakeschincariol/unhinged-claude-skills
- 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.