MCPInstall

integrating-jupiter

Comprehensive guidance for integrating Jupiter APIs (Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing). Use for endpoint selection, integration flows, error handling, and production hardening.

Installs
818
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/jup-ag/agent-skills --skill integrating-jupiter
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads integrating-jupiter automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Jupiter API Integration

Single skill for all Jupiter APIs, optimized for fast routing and deterministic execution.

Base URL: https://api.jup.ag Auth: x-api-key from developers.jup.ag (required for Jupiter REST endpoints)

Use/Do Not Use

Use when:

  • The task requires choosing or calling Jupiter endpoints.
  • The task involves swap, lending, perps, orders, pricing, portfolio, send, studio, lock, or routing.
  • The user needs debugging help for Jupiter API calls.

Do not use when:

  • The task is generic Solana setup with no Jupiter API usage.
  • The task is UI-only with no API behavior decisions.
  • The agent context is not DeFi/crypto (generic triggers like buy, sell, trade assume a DeFi domain).

Triggers: swap, quote, gasless, best route, buy, sell, trade, convert, token exchange, jupiter api, jup.ag, ultra, metis, ultra swap, ultra api, ultra-api.jup.ag, lend, borrow, earn, yield, apy, deposit, liquidation, perps, leverage, long, short, position, futures, margin trading, limit order, trigger, price condition, dca, recurring, scheduled swaps, token metadata, token search, verification, shield, price, valuation, price feed, portfolio, positions, holdings, prediction markets, market odds, event market, invite transfer, send, clawback, create token, studio, claim fee, vesting, distribution lock, unlock schedule, dex integration, rfq integration, routing engine, status page, health check, service health, accumulate, auto-buy

Developer Quickstart

import { Connection, Keypair, VersionedTransaction } from '@solana/web3.js';

const API_KEY = process.env.JUPITER_API_KEY!;  // from developers.jup.ag
if (!API_KEY) throw new Error('Missing JUPITER_API_KEY');
const BASE = 'https://api.jup.ag';
const headers = { 'x-api-key': API_KEY };

async function jupiterFetch<T>(path: string, init?: RequestInit): Promise<T> {
  const res = await fetch(`${BASE}${path}`, {
    ...init,
    headers: { ...headers, ...init?.headers },
  });
  if (res.status === 429) throw { code: 'RATE_LIMITED', retryAfter: Number(res.headers.get('Retry-After')) || 10 };
  if (!res.ok) {
    const raw = await res.text();
    let body: any = { message: raw || `HTTP_${res.status}` };
    try {
      body = raw ? JSON.parse(raw) : body;
    } catch {
      // keep text fallback body
    }
    throw { status: res.status, ...body };
  }
  return res.json();
}

// Sign and send any Jupiter transaction
async function signAndSend(
  txBase64: string,
  wallet: Keypair,
  connection: Connection,
  additionalSigners: Keypair[] = []
): Promise<string> {
  const tx = VersionedTransaction.deserialize(Buffer.from(txBase64, 'base64'));
  tx.sign([wallet, ...additionalSigners]);
  const sig = await connection.sendRawTransaction(tx.serialize(), {
    maxRetries: 0,
    skipPreflight: true,
  });
  return sig;
}

Token Amounts & Decimals

Every Jupiter amount field is in the token's smallest unit (raw integer) — never a human/UI value.

  • Common decimals: SOL & wSOL = 9, USDC & USDT = 6. Canonical mints: SOL So11111111111111111111111111111111111111112, USDC EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v.
  • Convert human → raw: raw = Math.round(human * 10 ** decimals). Examples: 1 SOL → 1_000_000_000, 100 USDC → 100_000_000. slippageBps is basis points: 0.5% = 50, 1% = 100.
  • Read decimals per-mint on-chain with getMint(connection, mintPubkey) from @solana/spl-token — never hardcode (decimals vary by token), and do not call the Price API just to discover decimals.

Intent Router (first step)

User intentAPI familyFirst action
Swap/quoteSwapGET /swap/v2/order -> sign -> POST /swap/v2/execute
Lend/borrow/yieldLendPOST /lend/v1/earn/deposit or /withdraw
Leverage/perpsPerpsOn-chain via Anchor IDL (no REST API yet)
Limit ordersTriggerJWT auth -> POST /trigger/v2/orders/price
DCA/recurring buysRecurringPOST /recurring/v1/createOrder -> sign -> POST /recurring/v1/execute
Token searchTokensGET /tokens/v2/search?query={mint}
Token verification/metadata updateUse jupiter-vrfd skillDefer — not handled by this skill
Price lookupPriceGET /price/v3?ids={mints}
Portfolio/positionsPortfolioGET /portfolio/v1/positions/{address}
Prediction market integrationPrediction MarketsGET /prediction/v1/events -> POST /prediction/v1/orders
Invite send/clawbackSendPOST /send/v1/craft-send -> sign -> send to RPC
Token creation/feesStudioPOST /studio/v1/dbc-pool/create-tx -> upload -> submit
Vesting/distributionLockOn-chain program LocpQgucEQHbqNABEYvBvwoxCPsSbG91A1QaQhQQqjn
DEX/RFQ integrationRoutingChoose DEX (AMM trait) vs RFQ (webhook) path

API Playbooks

Use each block as a minimal execution contract. Fetch the linked refs for full request/response shapes, TypeScript interfaces, and parameter details.

Swap

  • Base URL: https://api.jup.ag/swap/v2

  • Triggers: swap, quote, gasless, best route

  • Fee: Variable by pair — 0 bps (Jupiter tokens/pegged), 2 bps (SOL-Stable), 5 bps (LST-Stable), 10 bps (most pairs), 50 bps (tokens < 24h). Referral fees: 50-255 bps (Jupiter retains 20%).

  • Rate Limit: 50 req/10s base, scales with 24h execute volume (see Rate Limits)

  • Endpoints: /order (GET), /execute (POST), /build (GET, Metis-only raw instructions)

  • Quote vs. execute: For a read-only quote/price preview, call GET /order and omit taker — the response transaction is null and you read outAmount, routePlan[].swapInfo.label, and price-impact fields. Pass taker (then sign + POST /execute) only when you actually intend to swap. There is no separate quote endpoint — /swap/v1/quote is deprecated; use /swap/v2/order for quotes too.

  • Routing: 4 routers compete — Metis (metis), JupiterZ (jupiterz), Dflow (dflow), OKX (okx). The router response field returns one of these values. swapType is aggregator (Metis, Dflow, or OKX) or rfq (JupiterZ). Response mode field: "ultra" (all routers, default params) or "manual" (restricted by optional params). /build uses Metis only.

  • Gasless: Three paths — automatic (Jupiter-covered), JupiterZ (MM-covered), integrator-payer (payer param, Metis-only routing). Eligibility varies by balance, trade size, and parameters used. See Gasless docs for current thresholds and disqualifying params.

  • Gotchas:

    • Signed payloads have ~2 min TTL. Transactions are immutable after receipt.
    • Split order/execute in code and logging. Re-quote before execution when conditions may have changed.
    • Routing impact of optional params: referralAccount + referralFee disable JupiterZ only (Metis/Dflow/OKX remain); payer (integrator gasless) restricts routing to Metis only (disables JupiterZ, Dflow, and OKX); receiver does NOT restrict routing, but must differ from taker (receiver=taker returns 400 "Receiver cannot be same as taker").
    • /build transactions cannot use /execute — self-manage via RPC.
  • Migrating from an older integration? Use the jupiter-swap-migration skill.

  • Refs: Overview | Order & Execute | Build | Gasless | Migration | OpenAPI

    Fees are documented inline on the Order & Execute and Build pages; router competition and the parameter routing-impact matrix are on the Overview and Order & Execute pages.

Common error codes returned by /swap/v2/execute with recommended actions:

CodeCategoryMeaningRetryableAction
0SuccessTransaction confirmed——
-1ExecuteMissing/expired cached orderYesRe-quote and retry
-2ExecuteInvalid signed transactionNoFix transaction signing
-3ExecuteInvalid message bytesNoFix serialization
-1000AggregatorFailed landing attemptYesRe-quote with adjusted params
-1001AggregatorUnknown errorYesRetry with backoff
-1002AggregatorInvalid transactionNoFix transaction construction
-1003AggregatorTransaction not fully signedNoEnsure all required signers
-1004AggregatorInvalid block heightYesRe-quote (stale blockhash)
-2000RFQFailed landingYesRe-quote and retry
-2001RFQUnknown errorYesRetry with backoff
-2002RFQInvalid payloadNoFix request payload
-2003RFQQuote expiredYesRe-quote and retry
-2004RFQSwap rejectedYesRe-quote, possibly different route
429Rate limitRate limitedYesExponential backoff, wait 10s window

On success, /execute returns { status: "Success", code: 0, signature, inputAmountResult, outputAmountResult, slot, totalInputAmount, totalOutputAmount }. On failure it returns status: "Failed" with a non-zero code and an error string. inputAmountResult/outputAmountResult are the actual on-chain amounts; reconcile against your quote.


Lend

  • Base URL: https://api.jup.ag/lend/v1
  • Triggers: lend, borrow, earn, liquidation
  • Programs: Earn jup3YeL8QhtSx1e253b2FDvsMNC87fDrgQZivbrndc9, Borrow jupr81YtYssSyPt8jbnGuiWon5f6x9TcDEFxYe3Bdzi
  • SDK: @jup-ag/lend (TypeScript)
  • Endpoints: /earn/deposit (POST), /earn/withdraw (POST), /earn/mint (POST), /earn/redeem (POST), /earn/deposit-instructions (POST), /earn/withdraw-instructions (POST), /earn/tokens (GET), /earn/positions (GET), /earn/earnings (GET)
  • Gotchas: Recompute account state before each state-changing action. Encode risk checks (health factors, liquidation boundaries) as preconditions. All deposit/withdraw/mint/redeem return base64 unsigned VersionedTransaction.
  • For SDK-level integration with @jup-ag/lend and @jup-ag/lend-read, use the jupiter-lend skill.
  • Refs: Overview | Earn | SDK | OpenAPI

Perps


Trigger (Limit Orders)

  • Base URL: https://api.jup.ag/trigger/v2
  • Triggers: limit order, trigger, price condition
  • Min order: 10 USD equivalent
  • Auth: Dual-auth — x-api-key (all requests) + Authorization: Bearer <jwt> (order mutations). JWT obtained via challenge-response: POST /auth/challenge → sign challenge with wallet → POST /auth/verify → receive token. JWT expiry does NOT affect open orders — they continue executing.
  • Endpoints: /auth/challenge (POST, body: walletPubkey + type), /auth/verify (POST, body: type + walletPubkey + base58 signature), /vault (GET), /vault/register (GET), /deposit/craft (POST), /orders/price (POST create, PATCH update), /orders/price/cancel/{orderId} (POST, initiates withdrawal), /orders/price/confirm-cancel/{orderId} (POST, submits signed withdrawal + cancelRequestId), /orders/history (GET, wallet implicit via JWT)
  • Order types: single (one directional trigger), oco (take-profit + stop-loss pair), otoco (entry trigger + OCO). triggerCondition: "above" or "below".
  • Architecture: Off-chain custodial vault (Privy) per wallet. Orders invisible on-chain until execution — MEV-resistant. Triggers on USD price (not pool rate ratios). Partial fills supported.
  • Gotchas:
    • Order creation is 3 steps — GET /vault/register (register if new; returns 409 "Vault already registered" if it exists, which is fine), POST /deposit/craft (returns transaction + requestId; the body MUST include orderType: "price" and orderSubType (single/oco/otoco)), sign deposit tx, then POST /orders/price with depositRequestId + depositSignedTx.
    • Cancellation is two-step — POST /cancel/{orderId} returns transaction + requestId; sign, then POST /confirm-cancel/{orderId} with signedTransaction + cancelRequestId.
    • Create response field is id (not orderId); order history objects use orderState/rawState (no status field).
  • Refs: Overview | Authentication | Create order | Order history | Manage orders | OpenAPI

Recurring (DCA)

  • Base URL: https://api.jup.ag/recurring/v1
  • Triggers: dca, recurring, scheduled swaps
  • Fee: 0.1% on all recurring orders
  • Constraints: Min 100 USD total, min 2 orders, min 50 USD per order
  • Pagination: 10 orders per page
  • Endpoints: /createOrder (POST), /cancelOrder (POST), /execute (POST), /getRecurringOrders (GET)
  • Gotchas: Token-2022 NOT supported. Use params.time for order scheduling; price-based ordering is not supported.
  • Refs: Overview | Create | Get orders | Best Practices | OpenAPI

Tokens

  • Base URL: https://api.jup.ag/tokens/v2
  • Triggers: token metadata, token search, shield
  • Endpoints: /search?query={q} (GET, comma-separate mints, max 100), /tag?query={tag} (GET, verified or lst), /{category}/{interval} (GET, categories: toporganicscore, toptraded, toptrending; intervals: 5m, 1h, 6h, 24h), /recent (GET)
  • Gotchas:
    • Use mint address as primary identity; treat symbol/name as convenience.
    • Primary trust signal is top-level isVerified (boolean) plus organicScore (0-100) and organicScoreLabel (high/medium/low).
    • Secondary risk flag: audit.isSus — a boolean present ONLY when true (a safe token has no isSus key at all), so check it defensively as token.audit?.isSus === true, never read it directly. Verified live on flagged tokens (dev holds ~100% of supply); those also carry isVerified: null and organicScoreLabel: "low". Absence of isSus is NOT proof of safety — not all risky tokens carry the flag.
    • Other conditional audit fields the live API returns: mintAuthorityDisabled, freezeAuthorityDisabled, topHoldersPercentage, devBalancePercentage, devMigrations, devMints (all nullable, any may be absent; devMigrations is returned but missing from the current OpenAPI schema).
  • Refs: Overview | Token info v2 | OpenAPI

Price

  • Base URL: https://api.jup.ag/price/v3
  • Triggers: price, valuation, price feed
  • Limit: Max 50 mint IDs per request
  • Endpoints: /price/v3?ids={mints} (GET, comma-separated)
  • Response: keyed by mint, each value has usdPrice, blockId, decimals, priceChange24h, liquidity, createdAt (some tokens add conditional fields like launchpad, stockData, scaledUiConfig). Price API V3 has NO confidenceLevel field (that was V2).
  • Gotchas: Tokens with unreliable pricing are omitted from the response entirely (not an error, no null placeholder). Fail closed when a requested mint is missing from the response for safety-sensitive actions. Use blockId to check price recency.
  • Refs: Overview | OpenAPI

Portfolio

  • Base URL: https://api.jup.ag/portfolio/v1
  • Status: Beta — Jupiter platforms only
  • Triggers: portfolio, positions, holdings
  • Endpoints: /positions/{address} (GET), /positions/{address}?platforms={ids} (GET), /platforms (GET), /staked-jup/{address} (GET)
  • Gotchas: Treat empty positions as valid state. Response is beta — normalize into stable internal schema. Element types: multiple, liquidity, trade, leverage, borrowlend.
  • Refs: Overview | Jupiter positions | OpenAPI

Prediction Markets

  • Base URL: https://api.jup.ag/prediction/v1
  • Status: Beta (breaking changes possible)
  • Geo-restricted: US and South Korea IPs blocked
  • Price convention: 1,000,000 native units = $1.00 USD
  • Triggers: prediction markets, market odds, event market
  • Deposit mints: JupUSD (JuprjznTrTSp2UFa3ZBUFgwdAmtZCq4MQCwysN55USD), USDC
  • Min order: $5 (5,000,000 native units)
  • Endpoints: /events (GET, returns {data, pagination}), /events/search (GET), /markets/{marketId} (GET), /orderbook/{marketId} (GET, returns {yes, no, yes_dollars, no_dollars}), /orders (POST, requires isBuy boolean + ownerPubkey), /orders/status/{orderPubkey} (GET), /positions (GET, ?ownerPubkey=), /positions/{positionPubkey} (DELETE), /positions/{positionPubkey}/claim (POST), /history (GET), /leaderboards (GET)
  • Gotchas:
    • Check position.claimable before claiming. Winners get $1/contract.
    • Markets are FLAT — fields like provider, marketId, result, resolveAt, outcomes, clobTokenIds live at the top level, not nested under metadata.
    • Contracts are fractional: use contractsMicro (1,000,000 = 1 contract) or contractsDecimal, not the legacy whole-number contracts.
  • Refs: Overview | Events | Positions | OpenAPI

Send

  • Base URL: https://api.jup.ag/send/v1
  • Status: Beta
  • Triggers: invite transfer, send, clawback
  • Supported tokens: SOL, USDC, memecoins
  • Endpoints: /craft-send (POST), /craft-clawback (POST), /pending-invites (GET), /invite-history (GET)
  • Gotchas: Dual-sign requirement — sender + recipient keypair (derived from invite code). Claims only via Jupiter Mobile (no API claiming). Never expose invite codes.
  • Refs: Overview | Invite code | Craft send | OpenAPI

Studio

  • Base URL: https://api.jup.ag/studio/v1
  • Status: Beta
  • Triggers: create token, studio, claim fee
  • Endpoints: /dbc-pool/create-tx (POST), /dbc-pool/submit (POST, multipart/form-data), /dbc-pool/addresses/{mint} (GET), /dbc/fee (POST), /dbc/fee/create-tx (POST)
  • Flow: create-tx -> upload image to presigned URL -> upload metadata to presigned URL -> sign -> submit via /dbc-pool/submit
  • Gotchas: Must submit via /dbc-pool/submit (not externally) for token to get a Studio page on jup.ag. Error codes: 403 = not authorized for pool, 404 = proxy account not found.
  • Refs: Overview | Create token | Claim fee | OpenAPI

Lock

  • Program ID: LocpQgucEQHbqNABEYvBvwoxCPsSbG91A1QaQhQQqjn
  • Triggers: vesting, distribution lock, unlock schedule
  • Integration: On-chain program only (no REST API)
  • Source: github.com/jup-ag/jup-lock
  • UI: lock.jup.ag
  • Security: Audited by OtterSec and Sec3
  • Gotchas: No REST API. Use instruction scripts from the repo's cli/src/bin/instructions directory.
  • Refs: Lock overview

Routing

  • Triggers: dex integration, rfq integration, routing engine
  • Engines: Juno (meta-aggregator), Metis (multi-hop DEX routing, powers the Swap API; formerly called Iris), JupiterZ (RFQ market maker quotes)
  • DEX Integration (into Metis): Free, no fees. Prereqs: code health, security audit, market traction. Implement jupiter-amm-interface crate. Critical: No network calls in implementation (accounts are pre-batched and cached). Ref impl: github.com/jup-ag/rust-amm-implementation
  • RFQ Integration (JupiterZ): Market makers host webhook at /jupiter/rfq/quote (POST, 250ms), /jupiter/rfq/swap (POST), /jupiter/rfq/tokens (GET). Reqs: 95% fill rate, 250ms response, 55s expiry. SDK: github.com/jup-ag/rfq-webhook-toolkit
  • Market Listing: Instant routing for tokens < 30 days old. Normal routing (checked every 30 min) requires < 30% loss on $500 round-trip OR < 20% price impact comparing $1k vs $500.
  • Refs: DEX integration | RFQ integration | Market listing

Rate Limits

Swap API (dynamic, volume-based):

24h Execute VolumeRequests per 10s window
$050
$10,00051
$100,00061
$1,000,000165

Quotas recalculate every 10 minutes. Pro plan does NOT increase Swap API limits.

Other APIs: Managed at portal level. Check portal rate limits.

On HTTP 429: Exponential backoff with jitter: delay = min(baseDelay * 2^attempt + random(0, jitter), maxDelay). Wait for 10s sliding window refresh. Do NOT burst aggressively.

Production Hardening

  1. Auth: Fail fast if x-api-key is missing or invalid.
  2. Timeouts: 5s for quotes, 30s for executions, plus total operation timeout.
  3. Retries: Only transient/network/rate-limit failures with exponential backoff + jitter.
  4. Idempotency: Swap /execute accepts same signedTransaction + requestId for up to 2 min without duplicate execution.
  5. Validation: Validate mint addresses, amount precision, and wallet ownership before calls.
  6. Safety: Enforce slippage and max-amount guardrails from app config.
  7. Observability: Log requestId, API family, endpoint, latency, status, and error code.
  8. UX resilience: Return actionable states (retry, adjust params, insufficient balance, rate limited).
  9. Consistency: Reconcile async states (submitted vs confirmed vs failed) before final user success.
  10. Freshness: Re-fetch referenced docs when behavior differs from expected flow.

Integration Best Practices

  1. Start from the API-specific overview before coding endpoint calls.
  2. Enforce auth as a hard precondition for every request. Ref: Portal setup
  3. Design retry logic around documented rate-limit behavior, not fixed assumptions. Ref: Rate limits
  4. Map all non-success responses to typed app errors using documented response semantics. Ref: API responses
  5. For order-based products (Swap/Trigger/Recurring), separate create/execute/retrieve phases in code and logs.
  6. Treat network/service health as part of runtime behavior (degrade gracefully). Ref: Status page

Cross-Cutting Error Pattern

interface JupiterResult<T> {
  ok: boolean;
  result?: T;
  error?: { code: string | number; message: string; retryable: boolean };
}

async function jupiterAction<T>(action: () => Promise<T>): Promise<JupiterResult<T>> {
  try {
    const result = await action();
    return { ok: true, result };
  } catch (error: any) {
    const code = error?.code ?? error?.status ?? 'UNKNOWN';

    // Rate limit — retry with backoff
    if (code === 429 || code === 'RATE_LIMITED') {
      return { ok: false, error: { code: 'RATE_LIMITED', message: 'Rate limited', retryable: true } };
    }

    // Swap execute errors (negative codes)
    if (typeof code === 'number' && code < 0) {
      const retryable = [-1, -1000, -1001, -1004, -2000, -2001, -2003, -2004].includes(code);
      return { ok: false, error: { code, message: error?.error ?? 'Execute failed', retryable } };
    }

    // Program errors (positive codes like 6001 = slippage)
    if (typeof code === 'number' && code > 0) {
      return { ok: false, error: { code, message: error?.error ?? 'Program error', retryable: false } };
    }

    return { ok: false, error: { code, message: error?.message ?? 'UNKNOWN_ERROR', retryable: false } };
  }
}

async function withRetry<T>(action: () => Promise<T>, maxRetries = 3): Promise<T> {
  for (let attempt = 0; attempt <= maxRetries; attempt++) {
    const result = await jupiterAction(action);
    if (result.ok) return result.result!;
    if (!result.error?.retryable || attempt === maxRetries) throw result.error;
    const delay = Math.min(1000 * 2 ** attempt + Math.random() * 500, 10000);
    await new Promise(r => setTimeout(r, delay));
  }
  throw new Error('Retry exhausted');
}

Complete Working Examples

Production-ready code snippets. Each example uses the jupiterFetch helper from the sections above; apply withRetry around execute calls in production.

  • Swap: End-to-End — Order -> sign -> execute -> confirm flow
  • Lend: USDC Deposit — Deposit into Jupiter Lend earn pool
  • Trigger: Limit Order — Create and execute a limit order
  • Price: Multi-Token Lookup — Fetch prices with confidence filtering

Fresh Context Policy

Always fetch the freshest context from referenced docs/specs before executing a playbook.

  1. Resolve intent with Intent Router.
  2. Before coding, fetch the playbook's linked refs (overview + API-specific docs).
  3. If needed for validation or ambiguity, fetch the OpenAPI spec.
  4. Treat fetched docs as source of truth over cached memory.
  5. If fetched docs conflict with this file, follow fetched docs and note the mismatch.
  6. If docs cannot be fetched, state that context is stale/unverified and continue with best-known guidance.
  7. Keep auth invariant: x-api-key is required for Jupiter REST endpoints (not on-chain-only flows like Perps/Lock).

Operational References

FAQ

What does the integrating-jupiter skill do?

Comprehensive guidance for integrating Jupiter APIs (Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing). Use for endpoint selection, integration flows, error handling, and production hardening.

How do I install integrating-jupiter?

Run npx skills add https://github.com/jup-ag/agent-skills --skill integrating-jupiter in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/integrating-jupiter/ (personal) or .claude/skills/integrating-jupiter/ (project).

Which AI agents can use integrating-jupiter?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is integrating-jupiter safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains integrating-jupiter?

It is published by jup-ag in jup-ag/agent-skills. It has 818 recorded installs.

More from jup-ag/agent-skills

View all →

jupiter-lend

jup-ag/agent-skills

Open the skill to read its SKILL.md instructions.

AI & Agents316 installs

jupiter-swap-migration

jup-ag/agent-skills

Open the skill to read its SKILL.md instructions.

jupiter-vrfd

jup-ag/agent-skills

Open the skill to read its SKILL.md instructions.

AI & Agents245 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs