← Back to list
impermanent-loss Checked
Impermanent loss calculation, modeling, and breakeven analysis for AMM liquidity provision across…
8.9Overall rating
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "impermanent-loss" skill by following the instructions at https://skill123.me/install/impermanent-loss.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/impermanent-loss.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 19 KBAbout this skill
Overview
Impermanent loss calculation, modeling, and breakeven analysis for AMM liquidity provision across pool types
Source
- Repo: https://github.com/agiprolabs/claude-trading-skills
- Path: skills/impermanent-loss
Score breakdown
Trigger
7.0
Description states What (IL calculation, modeling, breakeven for AMM LP across pool types) with good domain keywords (AMM, liquidity provision, breakeven); no When/When-Not in description itself, though SKILL.md carries explicit When IL Is Acceptable / When to Avoid LPing sections.
Structure
9.3
195-line SKILL.md, two references (formulas, breakeven) and two scripts cleanly separated; Files section maps roles; no redundant files.
Workflow
8.8
Calculation/modeling tasks well supported: formulas with worked tables, approximation validity bounds (small moves vs full CLMM formula), Monte Carlo and historical-analysis paths, breakeven framework, and acceptability criteria acting as guards; scripts provide deterministic execution.
Content
9.0
Clean imperative writing, concrete numeric examples throughout; minor conceptual preamble (Why impermanent) is justified context.
Engineering
10.0
Valid frontmatter; scripts have shebangs, stdlib-only with declared 'no external APIs', usage examples; all referenced paths exist.
Security
10.0
6.0 manifest: data reads none; side effects none; network destinations none (scripts explicitly offline); credentials none; persistence none. Capabilities match declared scope. No injection, no secrets, no destructive commands.
Solid quant skill: constant-product and CLMM IL formulas with derivations, concentration-factor approximation with explicit validity bounds, sigma^2/8 breakeven framework, Monte Carlo scenario modeler, and clear When-acceptable/When-to-avoid sections. Scripts are pure-stdlib/pure-numpy offline calculators with argparse and demo modes. Deductions: description is a single generic sentence without when/when-not (boundaries live only in SKILL.md body); a bit of conceptual background at the top. 6.0 manifest: no network, no env/credential reads, no file writes, no persistence; capabilities match declared scope. Analytics only - no trade execution, no advice disclaimers needed; risk framing ('when to avoid LPing') present.