lp-agent
Run automated liquidity provision strategies on concentrated liquidity (CLMM) DEXs using Hummingbot API.
What this skill does
# lp-agent
This skill helps you run automated liquidity provision strategies on concentrated liquidity (CLMM) DEXs using Hummingbot API.
**Commands** (run as `/lp-agent <command>`):
| Command | Description |
|---------|-------------|
| `start` | Onboarding wizard — check setup status and get started |
| `deploy-hummingbot-api` | Deploy Hummingbot API trading infrastructure |
| `setup-gateway` | Start Gateway, configure network RPC endpoints |
| `add-wallet` | Add or import a Solana wallet |
| `explore-pools` | Find and explore Meteora DLMM pools |
| `select-strategy` | Choose LP Executor or Rebalancer Controller |
| `run-strategy` | Run, monitor, and manage LP strategies |
| `analyze-performance` | Visualize LP position performance |
**New here?** Run `/lp-agent start` to check your setup and get a guided walkthrough.
**Typical workflow:** `start` → `deploy-hummingbot-api` → `setup-gateway` → `add-wallet` → `explore-pools` → `select-strategy` → `run-strategy` → `analyze-performance`
---
## Command: start
Welcome the user and guide them through setup. This is a conversational onboarding wizard — check infrastructure state, interpret results, and walk them through each step.
### Step 1: Welcome & Explain
Introduce yourself and explain what lp-agent does:
> I'm your LP agent — I help you run automated liquidity provision strategies on Meteora DLMM pools (Solana). I can:
>
> - **Deploy infrastructure** — Hummingbot API + Gateway for DEX trading
> - **Manage wallets** — Add Solana wallets, check balances
> - **Explore pools** — Search Meteora DLMM pools, compare APR/volume/TVL
> - **Run strategies** — Auto-rebalancing LP controller or single-position executor
> - **Analyze performance** — Dashboards with PnL, fees, and position history
### Step 2: Check Infrastructure Status
Run these scripts and interpret the JSON output:
```bash
bash scripts/check_api.sh --json # Is Hummingbot API running?
bash scripts/check_gateway.sh --json # Is Gateway running?
python scripts/add_wallet.py list # Any wallets connected?
```
**Interpreting Results:**
| Script | Success Output | Failure Output |
|--------|---------------|----------------|
| `check_api.sh --json` | `{"running": true, "url": "http://localhost:8000", ...}` | `{"running": false, ...}` or connection error |
| `check_gateway.sh --json` | `{"running": true, ...}` | `{"running": false, ...}` |
| `add_wallet.py list` | Shows wallet addresses like `[solana] ABC123...` | `No wallets found.` or empty list `[]` |
### Step 3: Show Progress
Present a checklist showing what's done and what's remaining based on the script outputs:
```
Setup Progress:
[x] Hummingbot API — Running at http://localhost:8000
[x] Gateway — Running
[ ] Wallet — No wallet connected
Next step: Add a Solana wallet so you can start trading.
```
Adapt the checklist to the actual state. If everything is unchecked, start from the top. If everything is checked, skip to the LP lifecycle overview.
### Step 4: Guide Next Action
Based on the first unchecked item, offer to help:
| Missing | What to say |
|---------|-------------|
| Hummingbot API | "Let's deploy the API first — it's the trading backend. Need Docker installed. Want me to run the installer?" → `/lp-agent deploy-hummingbot-api` |
| Gateway | "API is running! Now we need Gateway for DEX connectivity. Want me to start it?" → `/lp-agent setup-gateway` |
| Wallet | See **Adding a Wallet** below |
| All ready | Move to Step 5 |
**Adding a Wallet:**
When wallet is the next step, tell the user:
> Infrastructure is ready. You need a Solana wallet with SOL for transaction fees (~0.06 SOL per LP position).
>
> To add a wallet, run:
> ```
> python scripts/add_wallet.py add
> ```
> You'll be prompted to paste your private key (secure, not saved in shell history).
**Interpreting add_wallet.py output:**
| Output | Meaning |
|--------|---------|
| `✓ Wallet added successfully` + address | Success — wallet is connected |
| `Enter private key (base58):` then `✓ Wallet added` | Success after prompt |
| `Error: HTTP 400` or validation error | Invalid private key format |
| `Error: Cannot connect to API` | API not running — run `check_api.sh` first |
After wallet is added, verify with `python scripts/add_wallet.py list` — should show the new address.
### Step 5: LP Lifecycle Overview
Once infrastructure is ready (or if user wants to understand the flow first), explain the LP lifecycle:
> **How LP strategies work:**
>
> 1. **Explore pools** (`/lp-agent explore-pools`) — Find a Meteora DLMM pool. Look at volume, APR, and fee/TVL ratio to pick a good one.
>
> 2. **Select strategy** (`/lp-agent select-strategy`) — Choose between:
> - **Rebalancer Controller** (recommended) — Automatically repositions when price moves out of range. Set-and-forget.
> - **LP Executor** — Single fixed position. You control when to close/reopen. Good for testing or limit-order-style LP.
>
> 3. **Run strategy** (`/lp-agent run-strategy`) — Configure parameters (amount, width, price limits) and deploy. Monitor status and stop when done.
>
> 4. **Analyze** (`/lp-agent analyze-performance`) — View PnL dashboard, fees earned, position history. Works for both running and stopped strategies.
>
> Want to explore some pools to get started?
---
## Command: deploy-hummingbot-api
Deploy the Hummingbot API trading infrastructure. This is the first step before using any LP features.
### What Gets Installed
**Hummingbot API** — A personal trading server that exposes a REST API for trading, market data, and deploying bot strategies across CEXs and DEXs.
- Repository: [hummingbot/hummingbot-api](https://github.com/hummingbot/hummingbot-api)
### Usage
```bash
# Check if already installed
bash scripts/deploy_hummingbot_api.sh status
# Install (interactive, prompts for credentials)
bash scripts/deploy_hummingbot_api.sh install
# Install with defaults (non-interactive: admin/admin)
bash scripts/deploy_hummingbot_api.sh install --defaults
# Upgrade existing installation
bash scripts/deploy_hummingbot_api.sh upgrade
# View container logs
bash scripts/deploy_hummingbot_api.sh logs
# Reset (stop and remove everything)
bash scripts/deploy_hummingbot_api.sh reset
```
### Prerequisites
- Docker and Docker Compose
- Git
### Interpreting Output
| Output | Meaning | Next Step |
|--------|---------|-----------|
| `✓ Hummingbot API deployed successfully` | Success | Proceed to `setup-gateway` |
| `✓ Already installed and running` | Already set up | Proceed to `setup-gateway` |
| `Error: Docker not found` | Docker not installed | Install Docker first |
| `Error: Port 8000 already in use` | Another service on port | Stop conflicting service or use different port |
### After Installation
Once the API is running:
1. Swagger UI is at `http://localhost:8000/docs`
2. Default credentials: admin/admin
3. Proceed to `setup-gateway` to enable DEX trading
---
## Command: setup-gateway
Start the Gateway service, check its status, and configure key network parameters like RPC node URLs. Gateway is required for all LP operations on DEXs.
**Prerequisite:** Hummingbot API must be running (`deploy-hummingbot-api`). The script checks this automatically.
> ⚠️ **Custom RPC is required — not optional.** The public Solana RPC is rate-limited and will cause transaction failures that look like "Insufficient funds" or "Transaction simulation failed". Always configure a custom RPC before deploying any bot. Get a free key at https://helius.dev.
### Usage
```bash
# Check Gateway status
bash scripts/setup_gateway.sh --status
# Start Gateway with defaults
bash scripts/setup_gateway.sh
# Start Gateway with custom image (e.g., development build)
bash scripts/setup_gateway.sh --image hummingbot/gateway:development
# Start with custom Solana RPC (recommended to avoid rate limits)
bash scripts/setup_gateway.sh --rpc-url https://your-rpc-endpoint.com
# Configure RPC for a different network
bash sRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.