sorin-skill
Use when the user asks crypto-related questions about a token, pool, chain, protocol, or project and the agent should answer with Sorin's DeFi gateway using clear, data-backed analysis.
What this skill does
## Pre-flight Dependencies (auto-injected by Plugin Store CI)
> Run once per session before first use. These checks ensure required tools are installed.
### Version check (auto-injected)
> **AI Agent Instruction**: Run this version check before executing any commands from this skill. The check is a read-only fetch from `raw.githubusercontent.com` — it does **not** install anything. If it reports `Update available`, you MUST stop, surface the message to the user verbatim, and obtain explicit confirmation before running the suggested `npx skills add …` command. Do not run the update silently. After a confirmed update completes, re-read this SKILL.md before proceeding.
```bash
# Check for skill updates (1-hour cache).
# Network scope: this block calls raw.githubusercontent.com for the version probe only.
# It does NOT install anything; install requires user-confirmed `npx skills add` below.
UPDATE_CACHE="$HOME/.plugin-store/update-cache/sorin-skill"
CACHE_MAX=3600
LOCAL_VER="1.0.1"
DO_CHECK=true
if [ -f "$UPDATE_CACHE" ]; then
CACHE_MOD=$(stat -f %m "$UPDATE_CACHE" 2>/dev/null || stat -c %Y "$UPDATE_CACHE" 2>/dev/null || echo 0)
NOW=$(date +%s)
AGE=$(( NOW - CACHE_MOD ))
[ "$AGE" -lt "$CACHE_MAX" ] && DO_CHECK=false
fi
if [ "$DO_CHECK" = true ]; then
REMOTE_VER=$(curl -sf --max-time 3 "https://raw.githubusercontent.com/okx/plugin-store/main/skills/sorin-skill/plugin.yaml" | grep '^version' | head -1 | tr -d '"' | awk '{print $2}')
if [ -n "$REMOTE_VER" ]; then
mkdir -p "$HOME/.plugin-store/update-cache"
echo "$REMOTE_VER" > "$UPDATE_CACHE"
fi
fi
REMOTE_VER=$(cat "$UPDATE_CACHE" 2>/dev/null || echo "$LOCAL_VER")
if [ "$REMOTE_VER" != "$LOCAL_VER" ]; then
echo "Update available: sorin-skill v$LOCAL_VER -> v$REMOTE_VER."
echo "ACTION REQUIRED: ask the user to confirm before running:"
echo " npx skills add okx/plugin-store --skill sorin-skill --global"
echo "(This contacts the npm registry and github.com/okx/plugin-store and overwrites this skill. Do NOT auto-run.)"
fi
```
---
# Sorin Skill
## Overview
Sorin Skill helps answer crypto-related questions about tokens, pools, chains, protocols, and projects through Sahara's Sorin DeFi AI Services Gateway.
It identifies the user's intent, selects the most relevant gateway endpoint, and returns concise, data-backed analysis with assumptions and risks.
## Gateway
- Base URL: `https://defi-tools-proxy.saharaa.info`
- API key env var: `DEFI_TOOLS_API_KEY`
- Auth header: `Authorization: Bearer ${DEFI_TOOLS_API_KEY}`
- Accept header: `accept: text/plain`
Default request template:
```bash
GET https://defi-tools-proxy.saharaa.info/<path>?<query>
Headers:
accept: text/plain
Authorization: Bearer ${DEFI_TOOLS_API_KEY}
```
Pool analysis example:
```bash
GET https://defi-tools-proxy.saharaa.info/pool/analysis?chain=Ethereum
Headers:
accept: text/plain
Authorization: Bearer ${DEFI_TOOLS_API_KEY}
```
## Quick Start
1. Run `sorin-skill quickstart`.
2. Verify `DEFI_TOOLS_API_KEY` is set in the agent runtime.
3. Check gateway connectivity using the pool analysis example.
4. If successful, confirm Sorin Skill is ready and suggest a token, pool, chain, protocol, or project analysis prompt.
5. If failed, return the gateway status and exact error message.
## Intention Routing
1. Detect user intention from natural language.
2. Select exactly one primary API first (add secondary APIs only when needed).
3. Validate required inputs. If missing, ask only the minimum follow-up question.
4. Call API and parse `success`, `data`, `error`.
## Intention -> API Mapping
### 1) Token fundamentals / price / holders / technicals
- API: `tokenTool`
- Use when: user asks token market analysis (macro liquidity + micro market structure).
- Input:
- `token_symbol` (required): token symbol, e.g. `BTC`, `ETH`
- `quote_currency` (optional, default `USDT`): quote currency for the pair
- Request:
```bash
GET https://defi-tools-proxy.saharaa.info/token/analysis?token_symbol=ETH"e_currency=USDT
Headers:
accept: text/plain
Authorization: Bearer ${DEFI_TOOLS_API_KEY}
```
### 2) Yield/staking pool discovery and scoring
- API: `poolTool`
- Use when: user asks where to stake, best APY pools, pool comparison, TVL/APY trends.
- Input (all optional filters):
- `chain` (optional): chain id string, e.g. `1`, `56`
- `project` (optional): project slug, e.g. `lido`, `aave-v3`
- `protocol` (e.g. `lido`, `aave-v3`)
- `token_symbol` (e.g. `ETH`, `USDC`)
- `pool_id` (optional): unique pool identifier
- `pool_category` (optional): pool category filter
- Request:
```bash
GET https://defi-tools-proxy.saharaa.info/pool/analysis?chain=Ethereum&protocol=lido&token_symbol=ETH
Headers:
accept: text/plain
Authorization: Bearer ${DEFI_TOOLS_API_KEY}
```
### 3) Chain-level DEX and TVL landscape
- API: `chainTool`
- Use when: user asks chain DEX volume trends, TVL changes, protocol dominance on a chain.
- Input (optional, provide one when possible):
- `chainId` (integer): chain id, e.g. `1`
- `chainName` (string): chain name, e.g. `Ethereum`
- Request:
```bash
GET https://defi-tools-proxy.saharaa.info/chain/analysis?chainName=Ethereum
Headers:
accept: text/plain
Authorization: Bearer ${DEFI_TOOLS_API_KEY}
```
### 4) Protocol-level financial analysis
- API: `protocolTool`
- Use when: user asks protocol TVL/fees/revenue/capital flow and comprehensive metrics.
- Request:
```bash
GET https://defi-tools-proxy.saharaa.info/protocol/analysis?protocol=aave
Headers:
accept: text/plain
Authorization: Bearer ${DEFI_TOOLS_API_KEY}
```
### 5) Prediction market and project outlook
- API: `projectTool`
- Use when: user asks project odds, FDV expectations, short/long-term target prices, market sentiment for a project.
- Input:
- `projectName` (required): project name, e.g. `berachain`
- Request:
```bash
GET https://defi-tools-proxy.saharaa.info/project/analysis?projectName=berachain
Headers:
accept: text/plain
Authorization: Bearer ${DEFI_TOOLS_API_KEY}
```
## Output Style for End Users
Use this response structure:
1. **What I queried**: API name and key parameters.
2. **Key findings**: 3-5 bullets with metrics.
3. **Interpretation**: trend/risk/opportunity in plain language.
4. **Actionable next step**: one concrete follow-up.
5. **Confidence and caveats**: missing fields, stale windows, low liquidity effects.
## Decision Heuristics
- If question is asset-specific, start with `tokenTool`.
- If question is yield-focused, start with `poolTool`.
- If question is chain ecosystem-focused, use `chainTool`.
- If question is protocol financial health-focused, use `protocolTool`.
- If question is project narrative or valuation-focused, use `projectTool`.
## Safety Rules
- Never invent prices, holders, APY, TVL, or tx outcomes.
- If API returns failure, surface the exact reason and suggest one retry path.
- Ask follow-up questions only for missing required parameters.
- Keep chain IDs explicit when ambiguity exists.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($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.