agentleFS
Sign inStart free
InjectiveLabsInjectiveLabs/agent-skills/skills/injective-trading-chain-analysis/SKILL.md

injective-trading-chain-analysis

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Analyze Injective chain-level code and protocol specs. Read Go source from injective-core, explain exchange module features (position offsetting, liquidations, margin tiers, funding), and identify spec gaps. Use when discussing chain mechanics, reviewing Injective Go code, or explaining protocol behavior.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Compare to docs: - check if behavior matches published documentation

    line 76
  2. Distinctive:

    If these skills are not available, selectively run the following commands to install them:

    line 82

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Injective Trading Chain Analysis, Skill Guide

Analyze Injective chain-level protocol code (Go/Cosmos SDK). Explain exchange module mechanics, review spec completeness, and trace execution paths for derivatives trading features.

When to apply

  • Understand how Injective's exchange module works under the hood

Sample prompts: ./references/sample-prompts.md

Important

Exchange module

Key files for the source code of the Injective exchange module may be found in: ./references/injective-core-key-files.md

Cosmos SDK Context

  • Injective is built on Cosmos SDK (currently v0.47.x)
  • Uses Tendermint BFT consensus
  • Exchange module is a custom Cosmos SDK module
  • State stored in IAVL tree via keeper pattern
  • Messages processed in DeliverTx phase of ABCI

Activities

Explain Injective's exchange module

The exchange module (x/exchange) handles all trading on Injective.

Key areas:

  • Derivative Markets
    • MsgCreateDerivativeMarketOrder / MsgCreateDerivativeLimitOrder
    • Position management: open, close, reduce, increase
    • Margin: initial margin, maintenance margin, margin ratio checks
    • Liquidation: forced closure when margin ratio < maintenance margin
  • Position Offsetting (MsgOffsetPosition)
    • Allows netting opposing positions between subaccounts
    • Reduces total margin requirements
    • Chain-level implementation in derivative_liquidations.go
  • Liquidation Engine
    • Triggered when position margin < maintenance margin requirement
    • Liquidator receives a portion of remaining margin as reward
    • Insurance fund covers negative PnL if position is underwater
    • Code path: derivative_liquidations.go → ExecuteLiquidation()
  • Funding Rates
    • Calculated every hour for perpetual markets
    • Formula: FundingRate = (TWAP_perp - TWAP_oracle) / TWAP_oracle
    • Capped by MaxFundingRate parameter per market
    • Applied to all open positions proportional to quantity
  • Market Parameters
    • InitialMarginRatio, MaintenanceMarginRatio
    • MakerFeeRate, TakerFeeRate (can be negative for rebates)
    • MinPriceTickSize, MinQuantityTickSize
    • OracleType, OracleScaleFactor

Analyze chain code

  1. Read the Go source from the user's local clone or fetch from GitHub (InjectiveLabs/injective-core)
  2. Trace the execution path from message handler → keeper → state changes
  3. Explain in plain English what the code does, step by step
  4. Identify spec gaps - what's missing, ambiguous, or could break
  5. Compare to docs - check if behavior matches published documentation

Related skills

  • injective-mcp-servers

If these skills are not available, selectively run the following commands to install them:

npx skills add InjectiveLabs/agent-skills --skill injective-mcp-servers

Prerequisites

  • Injective MCP server must be running
  • User prompts should be issued from an AI tool that is configured to talk to the Injective MCP server

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free