full-lp-workflow
Full LP workflow from opportunity scanning to position entry. Autonomously finds the best LP opportunity, designs a strategy, assesses risk, executes any needed swaps, enters the position, and reports portfolio impact. Use when user has capital and wants end-to-end LP management. Most complex multi-agent orchestration in the system.
What this skill does
# Full LP Workflow
## Overview
This is the most complex multi-agent orchestration in the system. It turns a single intent -- "I have $20K, find me the best yield" -- into a fully researched, risk-assessed, optimally-structured LP position through a 6-agent pipeline.
**Why this is 10x better than calling agents individually:**
1. **End-to-end automation**: Manually, you'd need to scan opportunities, research pools, design a strategy, assess risk, potentially swap tokens, add liquidity, and verify -- each requiring different tools and expertise. This does it all in one command.
2. **Intelligent pipeline with compound context**: Each agent builds on all prior agents' findings. The lp-strategist doesn't just get a token pair -- it gets the opportunity-scanner's full analysis of why this pool is optimal. The risk-assessor evaluates the actual strategy designed by the lp-strategist, not a generic assessment.
3. **Two user confirmation points**: Before spending any money (swap) and before committing capital (LP entry), the skill pauses for explicit user approval. You stay in control.
4. **Conditional swap step**: If you don't hold the right tokens for the LP position, the skill automatically handles the token swap -- but only after showing you exactly what it plans to do.
5. **Portfolio impact reporting**: After entering the position, the portfolio-analyst shows you exactly how your portfolio changed, with ongoing monitoring instructions.
6. **Failure recovery at every stage**: If any agent fails mid-pipeline, you see what was accomplished and get recovery suggestions.
## When to Use
Activate when the user says anything like:
- "I have $20K, find the best LP opportunity and enter"
- "Autonomous LP: find yield and enter position"
- "Full LP workflow with $10,000"
- "Find me the best yield and set up a position"
- "I want to LP but don't know where -- find the best option"
- "Put $5K to work in Uniswap -- find the best opportunity"
- "End-to-end LP: scan, strategize, and enter"
- "What's the best LP opportunity right now? Set it up for me"
**Do NOT use** when the user already knows which pool they want (use `manage-liquidity` instead), just wants strategy comparison without execution (use `lp-strategy`), or just wants to scan without entering (use `scan-opportunities`).
## Parameters
| Parameter | Required | Default | How to Extract |
| --------------- | -------- | ---------- | ------------------------------------------------------------------ |
| capital | Yes | -- | Total capital to deploy: "$20,000", "10 ETH", "$5K" |
| chain | No | all | Target chain or "all" for cross-chain scan |
| riskTolerance | No | moderate | "conservative", "moderate", "aggressive" |
| pairPreference | No | -- | Optional token pair preference: "ETH/USDC", "stablecoin pairs" |
| excludeTokens | No | -- | Tokens to exclude: "PEPE, SHIB" (avoid memecoins, etc.) |
| capitalToken | No | auto-detect| What token the capital is in: "USDC", "ETH", auto-detect from wallet |
If the user doesn't provide capital amount, **ask for it** -- never guess how much to deploy.
## Workflow
```
FULL LP WORKFLOW PIPELINE
┌─────────────────────────────────────────────────────────────────────┐
│ │
│ Step 1: SCAN (opportunity-scanner) │
│ ├── Scan LP opportunities across chains │
│ ├── Filter by risk tolerance and capital size │
│ ├── Rank top 3-5 by risk-adjusted yield │
│ └── Output: Ranked Opportunity List │
│ │ │
│ ▼ USER CHOICE POINT │
│ ┌───────────────────────────────────────────────────┐ │
│ │ Present top opportunities to user. │ │
│ │ User picks one OR accepts recommendation (#1). │ │
│ └───────────────────────────────────────────────────┘ │
│ │ │
│ ▼ │
│ │
│ Step 2: STRATEGIZE (lp-strategist) │
│ ├── Design optimal strategy for chosen opportunity │
│ ├── Version, fee tier, range width, rebalance plan │
│ ├── Conservative/moderate/optimistic APY estimates │
│ └── Output: LP Strategy Recommendation │
│ │ │
│ ▼ │
│ │
│ Step 3: RISK CHECK (risk-assessor) │
│ ├── Receives: opportunity data + strategy details │
│ ├── Evaluates: IL, slippage, liquidity, smart contract │
│ ├── Decision: APPROVE / CONDITIONAL / VETO / HARD_VETO │
│ └── Output: Risk Assessment Report │
│ │ │
│ ▼ CONDITIONAL GATE │
│ ┌───────────────────────────────────────────────────┐ │
│ │ APPROVE / COND. APPROVE → Continue │ │
│ │ VETO / HARD_VETO → STOP with full report │ │
│ └───────────────────────────────────────────────────┘ │
│ │ │
│ ▼ │
│ │
│ Step 4: SWAP IF NEEDED (trade-executor) -- CONDITIONAL │
│ ├── Check wallet balances vs required tokens │
│ ├── If tokens needed: calculate swap amounts │
│ ├── USER CONFIRMATION #1: "Swap X for Y to prepare for LP?" │
│ ├── Execute swap(s) if confirmed │
│ └── Output: Swap result OR "tokens already held" │
│ │ │
│ ▼ │
│ │
│ Step 5: ENTER POSITION (liquidity-manager) │
│ ├── USER CONFIRMATION #2: "Add liquidity with these params?" │
│ ├── Handle approvals (Permit2) │
│ ├── Add liquidity at recommended range │
│ ├── Wait for transaction confirmation │
│ └── Output: Position ID, amounts deposited, tick range │
│ │ │
│ ▼ │
│ │
│ Step 6: CONFIRM & REPORT (portfolio-analyst) │
│ ├── Verify position was created successfully │
│ ├── Show portfolio impact (before vs after) │
│ ├── Monitoring instructions │
│ └── Output: Portfolio Report + Next Steps │
│ │
└──────────────────Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.