Install
$ agentstack add skill-aryaniyaps-lamina-lamina-leverage-points ✓ 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
Leverage Points
Small shifts in the right place outperform large UI changes in the wrong place. Intervene on rules, information flows, and goals before rearranging screens.
Decision frameworks
- Low leverage: Parameters and numbers (button color, timeout value, copy tweak) — easy to change, limited structural effect.
- Medium leverage: Information flows — who sees what, when (student sees venue before payment vs after).
- High leverage: Rules and constraints — what is allowed, when, by whom (ticket available only after payment confirmed).
- Highest leverage: Goals and purpose — what the product optimizes for (throughput vs fairness vs compliance).
Checklists
- Before a UI redesign, ask: is this a leverage problem or a presentation problem?
- List current rules governing the failing behavior.
- Identify who lacks information that would change decisions.
- Propose rule changes before screen changes when traps persist.
- Document leverage rationale in
run.jsondomain or scenarios.
Heuristics
- Parameters are weak levers: Changing a timeout rarely fixes a broken workflow.
- Information beats persuasion: Showing "3 seats left" changes behavior more than motivational copy.
- Rules beat reminders: Disable illegal actions rather than warn after the fact.
Anti-patterns
- UI churn without rule change: Redesigning the download screen when availability rules are wrong.
- Hiding high-leverage decisions: Deferring permission model "until later."
Examples
- Ticket download window: Low leverage — bigger download button. High leverage — rule: download enabled only 48h before exam AND payment confirmed. Information flow — student sees countdown to availability.
Related capabilities
- [System Traps](../lamina-system-traps/SKILL.md)
- [Invariants](../lamina-invariants/SKILL.md)
- [Tradeoffs](../lamina-tradeoffs/SKILL.md)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: aryaniyaps
- Source: aryaniyaps/lamina
- License: MIT
- Homepage: https://lamina.dev
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.