token-launcher
Launch tokens on any chain without giving up 30-50% of your fees. Two paths: Easy Mode (call Tator API via x402 — works with any wallet provider, no env vars required) or Direct Mode (integrate SDKs yourself, keep 100% — requires signing key and RPC). Covers Clanker (7 EVM chains), Flaunch (Base), and Pump.fun (Solana). Includes strategy evaluation, fee management, claiming, recipient updates, and tax/legal guidance. Triggers: "token idea", "launch a coin", "launch a token", "deploy a token", "token strategy", "claim fees", "creator fees", "update fee recipient", "token launch on base", "launch on solana", "clanker", "flaunch", "pump.fun", "token economics", "is this a good token".
What this skill does
# Token Launcher
Launch tokens and keep your fees. Two paths, one goal: stop giving away 30-50% of your creator earnings to launch platforms.
---
## The Problem
Most token launch platforms take 30-50% of your creator fee earnings. Some charge upfront launch fees on top of that. Others layer in subscriptions, required platform tokens, or custodial wallets that hold your funds. You build the token, drive the volume, and someone else keeps the biggest slice.
## The Math
A token doing $500K in trading volume on Clanker generates ~$5,000 in pool fees (1% of volume). Here's who keeps what:
| Path | Your Share | Platform Cut | You Keep |
|------|-----------|-------------|----------|
| **Direct Mode (this skill)** | $5,000 | $0 | **$5,000 (100%)** |
| **Easy Mode (Tator API)** | $4,500 | $500 (10%) | **$4,500 (90%)** |
| **Typical launch platforms** | $2,500-3,500 | $1,500-2,500 (30-50%) | **$2,500-3,500** |
The difference compounds. At $5M volume, Direct Mode keeps you an extra $15,000-25,000 versus typical platforms. Easy Mode saves you $10,000-20,000.
---
## Two Paths
### Easy Mode — Tator API
One API call, natural language, Tator handles everything.
- Send a prompt like `"launch a token called GATOR on base"`
- Tator selects the platform, uploads metadata to IPFS, deploys the contract, configures fees
- Returns unsigned transactions — your wallet signs and broadcasts
- **Fee split: 90% to you, 10% to Tator as interface fee**
- $0.20 per API call via x402 USDC payment
- Supports launch, claim fees, update fee recipient, check unclaimed — all via natural language
**Best for:** Agents and developers who want token launches without writing blockchain code.
### Direct Mode — Full SDK Integration
Call Clanker, Flaunch, or Pump.fun directly from your agent's code.
- Integrate the platform SDK or build instructions manually
- You control every parameter: rewards, sniper protection, pairing token, fee recipients
- **100% of creator fees — no interface cut, no middleman**
- Requires: your own RPC endpoint, wallet signing capability, SDK dependencies
**Best for:** Agents and developers who want maximum control and zero fee overhead.
See [REFERENCE.md](./REFERENCE.md) for Direct Mode overview and the [references/](./references/) folder for per-platform implementation guides.
---
## Security
**This skill is instruction-only — it contains no executable code.** It provides documentation and code examples. No code is run at install time.
### Credential Requirements
**Easy Mode requires ZERO environment variables.** It works with any x402-compatible wallet provider (Lobster, AgentWallet, Vincent, local signer). The Tator API only receives your public wallet address — your wallet provider handles payment signing separately. The skill never touches your private key.
**Direct Mode requires environment variables because you are running SDK code in your own infrastructure:**
| Variable | Required For | Sensitive | How to Store |
|----------|-------------|-----------|-------------|
| `WALLET_PRIVATE_KEY` | Signing deploy/claim/update transactions | **Yes — grants full wallet control** | Secrets manager (AWS SM, GCP SM, Vault). Never plaintext. |
| `RPC_URL` | Talking to the blockchain | No (but keep private to avoid rate limit abuse) | Environment variable or config |
| `SOLANA_RPC_URL` | Solana operations (Pump.fun only) | No | Environment variable or config |
| `PINATA_API_KEY` or `IPFS_API_KEY` | Uploading token metadata to IPFS | Yes | Secrets manager |
**If you only use Easy Mode, you do not need any of these.** The skill installs and functions without any environment variables configured.
### Easy Mode Data Flow
When you call the Tator x402 API (`POST https://x402.quickintel.io/v1/tator/prompt`):
1. **Sent to Tator:** `walletAddress` (public address — not sensitive), `prompt` (your instruction), `provider` (your agent name)
2. **NOT sent to Tator:** Your private key, seed phrase, or any signing material
3. **x402 payment:** Your wallet provider signs a USDC authorization locally → the signed payment header is sent with the request. The API verifies the signature on-chain — it never has your key
4. **Returned to you:** Unsigned transaction(s) — you sign locally and broadcast yourself
**No private keys ever leave your machine in Easy Mode. The skill itself never has access to your private key — your wallet provider handles signing independently.**
### Direct Mode Data Flow
Direct Mode code runs entirely in your own infrastructure:
1. **Sent to blockchain RPCs:** Signed transactions (your RPC provider sees them — use a trusted provider like Alchemy, QuickNode, or Helius)
2. **Sent to IPFS:** Token metadata (name, symbol, description, image) — this is public by design
3. **Sent to platform SDKs:** Clanker SDK calls go to Clanker's infrastructure; Flaunch calls go to Base contracts; Pump.fun calls go to Solana
4. **NOT sent anywhere:** Your private key — it stays on your machine for local signing only
### Key Management (Direct Mode Only)
- **Use a dedicated launch wallet.** Never your main wallet or a wallet holding significant funds
- **Store keys in a secrets manager.** AWS Secrets Manager, GCP Secret Manager, HashiCorp Vault, or equivalent. Never hardcode in source code. Never store in plaintext `.env` files in production
- **Fund minimally.** ~0.01 ETH on Base, ~0.05 SOL on Solana — just enough for gas
- **Human-in-the-loop recommended.** If your agent runs autonomously, require human approval before any transaction-signing operation. Do not give autonomous agents unsupervised access to signing keys
- **Pump.fun bot wallet:** Solana requires a bot wallet that signs directly (unlike EVM where unsigned transactions can be returned). This wallet needs SOL for gas but should never hold significant value. See [references/pumpfun.md](./references/pumpfun.md)
- **Revocation plan.** Ensure you can abandon the launch wallet if compromised — use a fresh wallet you can walk away from
### Privacy Note on SDK Context Fields
Some platform SDKs (like Clanker) accept an optional `context` object for analytics tracking. **These fields are entirely optional.** If you use them, be aware:
- `context.interface` — your agent/app name (sent to Clanker)
- `context.platform` — where the user is (e.g., "telegram") (sent to Clanker)
- `context.messageId` — message ID that triggered the launch (sent to Clanker)
- `context.id` — user identifier (sent to Clanker)
**If privacy is a concern, omit the context object entirely or use non-identifying values.** The context object is not required for any operation to succeed. See the Clanker reference for details.
### Verify External Endpoints
Before using any endpoint, verify you're connecting to the correct service:
| Service | Official Endpoint | Verify Via |
|---------|------------------|-----------|
| Tator x402 API | `https://x402.quickintel.io` | Check TLS cert, call `GET /accepted` |
| Quick Intel Scan | `https://x402.quickintel.io/v1/scan/full` | Same gateway |
| Clanker SDK | Via npm `clanker-sdk` | Verify package on npmjs.com |
| Flaunch contracts | On-chain on Base | Verify on Basescan |
| Pump.fun program | On-chain on Solana | Verify on Solscan — program ID: `6EF8rrecthR5Dkzon8Nwu78hRvfCKubJ14M5uBEwF6P` |
---
## Easy Mode — Full Walkthrough
### Prerequisites
- A wallet you control (EVM or Solana)
- USDC for x402 API payments ($0.20 per Tator call)
- Native token for gas (ETH on EVM chains, SOL on Solana)
### Launch a Token
```bash
curl -X POST https://x402.quickintel.io/v1/tator/prompt \
-H "Content-Type: application/json" \
-H "PAYMENT-SIGNATURE: <x402_payment>" \
-d '{
"prompt": "launch a token called Galaxy Cat with ticker GCAT on base",
"walletAddress": "0xYourWallet",
"provider": "my-agent"
}'
```
**With custom image:**
```json
{
"prompt": "launch a token called Moon Dog with ticker MDOG on base with image https://example.com/dog.png",
"walletAddress": "0xYourWallRelated 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.