Agent skill

Lp Math

by agiprolabs in agiprolabs/claude-trading-skills

AMM liquidity provision mathematics including constant-product, concentrated liquidity, price impact, and LP share calculations

MITAuto-check passed

Install Lp Math

skills CLI

$ npx skills add agiprolabs/claude-trading-skills --skill lp-math -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install agiprolabs/claude-trading-skills lp-math --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lp-math .claude/skills/lp-math && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "lp-math" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/lp-math into .claude/skills/lp-math/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lp-math", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/lp-math

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add agiprolabs/claude-trading-skills --skill lp-math -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install agiprolabs/claude-trading-skills lp-math --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/lp-math .agents/skills/lp-math && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "lp-math" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/lp-math into .agents/skills/lp-math/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lp-math", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add agiprolabs/claude-trading-skills --skill lp-math -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install agiprolabs/claude-trading-skills lp-math --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/lp-math .cursor/skills/lp-math && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "lp-math" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/lp-math into .cursor/skills/lp-math/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lp-math", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/agiprolabs/claude-trading-skills.git --path skills/lp-math

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add agiprolabs/claude-trading-skills --skill lp-math -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install agiprolabs/claude-trading-skills lp-math --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/lp-math .gemini/skills/lp-math && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "lp-math" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/lp-math into .gemini/skills/lp-math/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lp-math", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install agiprolabs/claude-trading-skills lp-math

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add agiprolabs/claude-trading-skills --skill lp-math -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/lp-math .github/skills/lp-math && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "lp-math" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/lp-math into .github/skills/lp-math/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lp-math", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add agiprolabs/claude-trading-skills --skill lp-math -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install agiprolabs/claude-trading-skills lp-math --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/lp-math .opencode/skills/lp-math && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "lp-math" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/lp-math into .opencode/skills/lp-math/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lp-math", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: lp-math
GitHub stars: 410
Token cost: ~2.5k tokens
SKILL.md length: 831 words
Files: 5 (incl. scripts, references)
Skills in repo: 68
Repo updated: Sep 3, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

AMM liquidity provision mathematics including constant-product, concentrated liquidity, price impact, and LP share calculations

Works in 7 steps: Constant Product AMM (xy = k) → Concentrated Liquidity (CLMM) → Price Impact → …
SKILL.md covers 1. Constant Product AMM (xy = k), 2. Concentrated Liquidity (CLMM), 3. Price Impact and 4. LP Share Calculations, plus 3 more sections
Runs Python scripts from its folder

What it does

Lp Math is an agent skill from agiprolabs/claude-trading-skills. AMM liquidity provision mathematics including constant-product, concentrated liquidity, price impact, and LP share calculations

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/amm_formulas.md`, `references/pool_mechanics.md` and `scripts/amm_calculator.py`).

It works with Circle USDC. The repository describes itself as: 68 trading, DeFi, and quantitative finance Agent Skills. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ other tools. The licence is MIT.

Example prompts

“/lp-math”

Requirements

Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

Constant Product AMM (xy = k)
Concentrated Liquidity (CLMM)
Price Impact
LP Share Calculations
Fee Accrual
Solana Pool Types
Practical Decision Framework

What it can do on your machine

Read from SKILL.md and the folder at commit 981e1d7. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lp Math loads about 2.5k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 34 tokens; SKILL.md has 831 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~34
When it runs · the whole SKILL.md, loaded when a task matches: ~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~5.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from agiprolabs/claude-trading-skills at commit 981e1d7, republished under its MIT licence (© agiprolabs). 831 words, ~2,497 tokens.

Download SKILL.mdSave it as .claude/skills/lp-math/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.

name: lp-math
description: AMM liquidity provision mathematics including constant-product, concentrated liquidity, price impact, and LP share calculations

LP Math — AMM Liquidity Provision Mathematics

Automated Market Makers (AMMs) replace traditional orderbooks with liquidity pools. Instead of matching buyers and sellers, a mathematical formula determines prices based on reserve ratios. Liquidity providers (LPs) deposit both assets into a pool and earn fees from every trade.

Understanding the math behind AMMs is essential for:

Evaluating whether providing liquidity is profitable after impermanent loss
Estimating price impact before executing large trades
Comparing capital efficiency across pool types (constant product vs concentrated)
Calculating expected fee revenue for a given pool position

Related skills: See impermanent-loss for IL calculations, yield-analysis for LP yield modeling, liquidity-analysis for pool depth assessment.

1. Constant Product AMM (xy = k)

The foundational AMM model used by Raydium V4 and most Solana DEXes.

Core Invariant

x * y = k

Where:

x = reserve amount of token X (e.g., SOL)
y = reserve amount of token Y (e.g., USDC)
k = constant product (increases over time from fees)

Spot Price

P = x / y    (price of Y in terms of X)
P = y / x    (price of X in terms of Y)

For a pool with 100 SOL and 10,000 USDC: price of SOL = 10,000 / 100 = 100 USDC.

Trade Execution

When a trader swaps Δx of token X into the pool:

python

# Output amount (before fees)
delta_y = y * delta_x / (x + delta_x)

# With fee (e.g., 0.3%)
delta_y_after_fee = delta_y * (1 - fee_rate)

# New reserves
x_new = x + delta_x
y_new = y - delta_y_after_fee

The key insight: larger trades get worse prices because each unit moves the ratio further.

Inverse Calculation

To get a specific output amount Δy, the required input is:

python

delta_x = x * delta_y / (y - delta_y)

Price After Trade

python

price_new = y_new / x_new

Worked Example

Pool: 100 SOL / 10,000 USDC (k = 1,000,000), fee = 0.3%

Buy 5 SOL worth of USDC:

Gross output: 10,000 * 5 / (100 + 5) = 476.19 USDC
Fee: 476.19 * 0.003 = 1.43 USDC
Net output: 474.76 USDC
Effective price: 474.76 / 5 = 94.95 USDC/SOL (vs spot 100)
Price impact: (100 - 94.95) / 100 = 5.05%
New reserves: 105 SOL / 9,525.24 USDC
New k: 105 * 9,525.24 = 1,000,150.2 (k increased from fees)

See references/amm_formulas.md for complete derivations.

2. Concentrated Liquidity (CLMM)

Used by Orca Whirlpool, Raydium CLMM, and Meteora DLMM. Liquidity is only active within a chosen price range [P_lower, P_upper].

Key Concepts

L = sqrt(x * y)           # Liquidity within the active range
price_at_tick = 1.0001^tick  # Tick-to-price conversion

Capital Efficiency

Concentrating liquidity in a narrow range provides more depth per dollar:

python

# Capital efficiency ratio
efficiency = sqrt(P_upper / P_lower) / (sqrt(P_upper / P_lower) - 1)

# Example: ±5% range around $100 SOL
P_lower, P_upper = 95, 105
efficiency = sqrt(105/95) / (sqrt(105/95) - 1)  # ≈ 20.5x

A ±5% range is ~20x more capital-efficient than full-range, but the position goes 100% into one asset if price moves outside the range.

Position Value

For a CLMM position with liquidity L in range [P_lower, P_upper] at current price P:

python

if P <= P_lower:
    # All in token X (below range)
    value_x = L * (1/sqrt(P_lower) - 1/sqrt(P_upper))
    value_y = 0
elif P >= P_upper:
    # All in token Y (above range)
    value_x = 0
    value_y = L * (sqrt(P_upper) - sqrt(P_lower))
else:
    # In range — holds both tokens
    value_x = L * (1/sqrt(P) - 1/sqrt(P_upper))
    value_y = L * (sqrt(P) - sqrt(P_lower))

Range Strategy Comparison

Range	Efficiency	IL Risk	Fee Capture	Best For
±2%	~50x	Very high	High if in range	Stablecoins, tight pegs
±5%	~20x	High	Good for trending	Active management
±25%	~4x	Moderate	Consistent	Semi-passive
±100%	~2x	Low	Lower per $	Passive, volatile pairs
Full range	1x	Baseline	Always earning	Set and forget

See references/amm_formulas.md for full CLMM derivations.

3. Price Impact

Constant Product Impact

python

# Price impact as a fraction
price_impact = delta_x / (x + delta_x)

# As percentage of pool
pool_fraction = trade_value / pool_tvl

# Rule of thumb: impact ≈ 2 * pool_fraction for constant product

Multi-Hop Impact

For a route through multiple pools, compound the impacts:

python

def multi_hop_impact(hops: list[dict]) -> float:
    """Calculate total price impact across route legs.

    Args:
        hops: List of {reserve_in, trade_amount} for each leg.

    Returns:
        Total price impact as a fraction.
    """
    remaining = 1.0
    for hop in hops:
        leg_impact = hop["trade_amount"] / (hop["reserve_in"] + hop["trade_amount"])
        remaining *= (1 - leg_impact)
    return 1 - remaining

Impact Thresholds

Impact	Assessment	Action
< 0.1%	Negligible	Proceed normally
0.1–0.5%	Low	Acceptable for most trades
0.5–2%	Moderate	Consider splitting across pools
2–5%	High	Split trade, use TWAP
> 5%	Severe	Reduce size or find deeper pools

Initial Deposit (Empty Pool)

python

shares = sqrt(x_deposited * y_deposited)

The first depositor sets the ratio and receives shares equal to the geometric mean.

Show full SKILL.md (331 more words)Show less

Subsequent Deposits

python

shares_minted = min(
    x_added / x_reserve,
    y_added / y_reserve
) * total_shares

Deposits must be proportional to the current reserve ratio. Any excess of one token is not used (or returned, depending on implementation).

Withdrawal

python

x_out = (shares_burned / total_shares) * x_reserve
y_out = (shares_burned / total_shares) * y_reserve

You always receive both tokens in the current ratio.

python

share_value = pool_tvl / total_shares
your_value = your_shares * share_value

5. Fee Accrual

Fees accumulate inside the pool, increasing k:

python

# Before trade: k = x * y
# After trade with fee:
# k_new = (x + delta_x) * (y - delta_y_net) > k
# The difference is the fee retained in the pool

# Fee APR estimation
daily_volume = 500_000  # USD
fee_rate = 0.003        # 0.3%
daily_fees = daily_volume * fee_rate  # $1,500
tvl = 2_000_000         # $2M pool
fee_apr = (daily_fees * 365) / tvl    # 27.4%

For CLMM positions, fee earnings depend on:

Whether price stays within your range (out-of-range = no fees)
Your share of active liquidity in that range
Total volume routed through the pool

python

# CLMM fee estimation
your_liquidity = 50_000     # Your L
total_liquidity = 1_000_000  # Total L in your tick range
your_share = your_liquidity / total_liquidity  # 5%
your_daily_fees = daily_fees * your_share  # $75

6. Solana Pool Types

Raydium V4 (Constant Product)

Model: Standard xy = k
Fee: 0.25% (0.22% to LP, 0.03% to RAY buyback)
Best for: New token launches, volatile pairs
Note: Integrated with OpenBook for limit order flow

Orca Whirlpool (Concentrated Liquidity)

Model: Concentrated liquidity with tick spacing
Fee tiers: 0.01%, 0.05%, 0.3%, 1%
Position: Represented as NFT (each position is unique)
Best for: Major pairs (SOL/USDC), stablecoin pairs

Raydium CLMM

Model: Concentrated liquidity (similar to Uniswap V3)
Tick spacing: 1, 10, 60, 200
Fee tiers: 0.01%, 0.05%, 0.25%, 1%
Best for: Pairs with predictable ranges

Meteora DLMM (Dynamic Liquidity Market Maker)

Model: Discrete bins instead of continuous ticks
Strategies: Spot (uniform), Curve (concentrated), Bid-Ask (around current price)
Fees: Dynamic, adjusting based on volatility
Best for: Active LPs who rebalance frequently

See references/pool_mechanics.md for detailed mechanics and comparison.

7. Practical Decision Framework

Should You LP?

1. Calculate expected fee APR
2. Estimate impermanent loss for expected price movement
3. Net return = fee APR - IL
4. Compare to simply holding the assets

Which Pool Type?

Stablecoin pair     → CLMM with tight range (±0.5%)
Major pair (SOL/USDC) → CLMM with moderate range (±10-25%)
New/volatile token  → Constant product (full range)
Active management   → Meteora DLMM with dynamic rebalancing

Position Sizing for LP

python

# Never LP more than you can afford to lose to IL
max_lp_allocation = portfolio_value * 0.20  # 20% max in any single pool

# For volatile pairs, reduce further
volatility_adjustment = 1 - (annualized_vol / 2)  # Scale down for vol
adjusted_allocation = max_lp_allocation * max(0.1, volatility_adjustment)

Files

References

references/amm_formulas.md — Complete mathematical derivations for constant product and concentrated liquidity AMMs
references/pool_mechanics.md — Solana-specific pool mechanics for Raydium, Orca, and Meteora

Scripts

scripts/amm_calculator.py — Constant product AMM calculator with trade simulation, LP shares, and fee accrual
scripts/clmm_calculator.py — Concentrated liquidity calculator with position valuation, capital efficiency, and range comparison

Quick Reference

Formula	Expression
Constant product	`x * y = k`
Spot price	`P = y / x`
Trade output	`Δy = y * Δx / (x + Δx)`
Required input	`Δx = x * Δy / (y - Δy)`
Price impact	`Δx / (x + Δx)`
Initial LP shares	`sqrt(x * y)`
Subsequent shares	`min(Δx/x, Δy/y) * total`
Fee APR	`(daily_fees * 365) / TVL`
CLMM efficiency	`sqrt(P_u/P_l) / (sqrt(P_u/P_l) - 1)`
Tick to price	`1.0001^tick`

Files

SKILL.md and 4 other files (scripts, references) in skills/lp-math of agiprolabs/claude-trading-skills.

SKILL.md
references/amm_formulas.md
references/pool_mechanics.md
scripts/amm_calculator.py
scripts/clmm_calculator.py

Open the folder on GitHubat commit 981e1d7

Compare with similar skills

Lp Math next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lp Math compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Lp Math this skillagiprolabs/claude-trading-skills	410	—	~2.5k	Automated safety check: Pass	MIT	1 mo ago
Agentic Walletcoinbase/agentic-wallet-skills	127	3 repos	~1k	Automated safety check: Pass	MIT	2 mo ago
Minara Crypto Trading and WalletMinara-AI/minara-skills	358	1 repos	~5.7k	Automated safety check: Pass	None	21 days ago
Kleros IPFS Uploadinternet-court/internet-court-skill	6.4k	—	~4.9k	Automated safety check: Notes	MIT	1 mo ago
Polymarket TradingBlockRunAI/ClawRouter	6.6k	—	~1.4k	Automated safety check: Pass	MIT	3 days ago
Predexon Prediction Market DataBlockRunAI/ClawRouter	6.6k	—	~4.7k	Automated safety check: Pass	MIT	3 days ago

Similar skills

Agentic Wallet
coinbase/agentic-wallet-skills
Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol to discover paid services, pay for API…
127 GitHub starsUsed in 3 repos~1k tokens
Backend & APIsAuto-check passed
Minara Crypto Trading and Wallet
Minara-AI/minara-skills
Drives the Minara CLI for crypto swaps, perps, limit orders, wallet transfers, deposits and withdrawals, plus AI market analysis.
358 GitHub starsUsed in 1 repo~5.7k tokens
Business, Finance & HRAuto-check passed
Kleros IPFS Upload
internet-court/internet-court-skill
Uploads one Kleros-related file per paid request to IPFS through the Kleros x402 gateway for 0.01 USDC on Base, returning a CID that Kleros contracts can reference.
6.4k GitHub stars~4.9k tokensUpdated 1 mo ago
Backend & APIsAuto-check: notes
Polymarket Trading
BlockRunAI/ClawRouter
A skill your agent uses when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools).
6.6k GitHub stars~1.4k tokensUpdated 3 days ago
Business, Finance & HRAuto-check passed
Predexon Prediction Market Data
BlockRunAI/ClawRouter
Reads structured prediction market data for Polymarket, Kalshi and other venues through a local BlockRun gateway: markets, search, leaderboards, wallet analytics and odds.
6.6k GitHub stars~4.7k tokensUpdated 3 days ago
Business, Finance & HRAuto-check passed
Payment
second-state/payment-skill
Request and receive payments. An agent skill from second-state/payment-skill.
220 GitHub stars~1.5k tokensUpdated 7 mo ago
Auto-check passed

Questions about Lp Math

What does Lp Math do?

AMM liquidity provision mathematics including constant-product, concentrated liquidity, price impact, and LP share calculations. Lp Math is an agent skill from agiprolabs/claude-trading-skills.

How do I install Lp Math in Claude Code?

Run `npx skills add agiprolabs/claude-trading-skills --skill lp-math -a claude-code`. Or copy the skill folder (skills/lp-math in agiprolabs/claude-trading-skills) into .claude/skills/lp-math in your project. Claude Code loads it when a task matches its description.

How do I install Lp Math in Codex?

Run `npx skills add agiprolabs/claude-trading-skills --skill lp-math -a codex`. Or copy the skill folder (skills/lp-math in agiprolabs/claude-trading-skills) into .agents/skills/lp-math in your project. Codex loads it when a task matches its description.

Can I use Lp Math in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agiprolabs/claude-trading-skills --skill lp-math -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lp-math, .gemini/skills/lp-math, .github/skills/lp-math and .opencode/skills/lp-math in your project.

What does Lp Math need to run?

Going by SKILL.md and its folder, Lp Math needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Lp Math access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Lp Math safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Lp Math use?

Lp Math is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lp Math use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.2k tokens, read only when the agent opens those files.

What are the alternatives to Lp Math?

Skills that share tags, products or a category with Lp Math: Agentic Wallet (coinbase/agentic-wallet-skills, 127 stars), Minara Crypto Trading and Wallet (Minara-AI/minara-skills, 358 stars), Kleros IPFS Upload (internet-court/internet-court-skill, 6.4k stars) and Polymarket Trading (BlockRunAI/ClawRouter, 6.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lp Math?

agiprolabs (a GitHub user) maintains it in agiprolabs/claude-trading-skills, which has 410 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on September 3, 2026.

Source: agiprolabs/claude-trading-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Lp Math

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

LP Math — AMM Liquidity Provision Mathematics

1. Constant Product AMM (xy = k)

Core Invariant

Spot Price

Trade Execution

Inverse Calculation

Price After Trade

Worked Example

2. Concentrated Liquidity (CLMM)

Key Concepts

Capital Efficiency

Position Value

Range Strategy Comparison

3. Price Impact

Constant Product Impact

Multi-Hop Impact

Impact Thresholds

4. LP Share Calculations

Initial Deposit (Empty Pool)

Subsequent Deposits

Withdrawal

Share Value

5. Fee Accrual

6. Solana Pool Types

Raydium V4 (Constant Product)

Orca Whirlpool (Concentrated Liquidity)

Raydium CLMM

Meteora DLMM (Dynamic Liquidity Market Maker)

7. Practical Decision Framework

Should You LP?

Which Pool Type?

Position Sizing for LP

Files

References

Scripts

Quick Reference

Files

Compare with similar skills

Similar skills

More from agiprolabs/claude-trading-skills

Related

Questions about Lp Math