Sol Incinerator logo

Sol Incinerator

Organization
sendaifun
sol-incinerator

SOL Incinerator SDK for burning tokens, NFTs, and closing accounts

Overview

Publishersendaifun
Repositoryskills
Skill namesol-incinerator
Stars
128
Forks
81
Bundled files
4
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by sendaifun on GitHub. Read the source before you install it.

Installation

Install the Sol Incinerator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/sendaifun/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/sol-incinerator .claude/skills/sol-incinerator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sol Incinerator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sol Incinerator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sol Incinerator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Sol-Incinerator Burn + Close API v2 Guide

A practical integration guide for Sol-Incinerator's HTTP API. The main user-facing outcomes are burning tokens, burning NFTs, and closing token accounts, while still supporting advanced batch cleanup and relay workflows.

Live API base URL: https://v2.api.sol-incinerator.com

Overview

Sol-Incinerator API v2 provides:

  • Autonomous API key provisioning via POST /api-keys/generate
  • Burn/close transaction building for SPL Token, Token-2022, and NFT account patterns
  • Instruction-only endpoints when you want full client-side transaction assembly
  • Preview/summary endpoints to estimate reclaimed rent and fees before execution
  • Transaction relay endpoints to broadcast already-signed payloads
  • Partner/referral monetization inputs with built-in validation

Core Endpoint Groups

GroupEndpoints
Public discoveryGET /, /openapi.json, /.well-known/api-catalog, /llms*, /DOCS.md
Public auth bootstrapPOST /api-keys/generate
Burn + close (API key required)/burn, /burn-instructions, /close, /close-instructions, /batch/close-all*
Relay + confirmation (API key required)/transactions/send, /transactions/send-batch, /transactions/status

Quick Start

1) Generate API key (no user input)

typescript
const baseUrl = 'https://v2.api.sol-incinerator.com';

const keyResp = await fetch(`${baseUrl}/api-keys/generate`, {
  method: 'POST',
  headers: { 'content-type': 'application/json' },
  body: JSON.stringify({ label: 'autonomous-agent' }),
});

if (!keyResp.ok) {
  throw new Error(`API key generation failed: ${keyResp.status}`);
}

const { apiKey } = await keyResp.json() as { apiKey: string };

2) Run preview-first flow

typescript
const headers = {
  'content-type': 'application/json',
  'x-api-key': apiKey,
};

const previewResp = await fetch(`${baseUrl}/burn/preview`, {
  method: 'POST',
  headers,
  body: JSON.stringify({
    userPublicKey,
    assetId,
    burnAmount: '1',
  }),
});

3) Build, sign, submit

  1. Call /burn, /close, or /batch/close-all.
  2. Decode base58 serialized transaction(s) and sign locally with the wallet keypair.
  3. Submit through your wallet/RPC flow, or use /transactions/send and /transactions/send-batch.
  4. Poll /transactions/status if needed.

Core Integration Rules

Auth

  • Send API key in either:
    • x-api-key: ak_xxx.yyy (recommended for server agents)
    • Authorization: Bearer ak_xxx.yyy
  • Core routes return 401 when key is missing or invalid.

Required body fields

  • Single-asset routes (/burn, /close, previews, instructions):
    • userPublicKey
    • assetId
  • Batch routes (/batch/close-all*):
    • userPublicKey

Optional body fields used often

  • feePayer (public key)
  • asLegacyTransaction (boolean)
  • priorityFeeMicroLamports (integer)
  • autoCloseTokenAccounts (boolean, burn flows)
  • burnAmount (positive integer in atomic units; use string for large values)
  • offset, limit (batch pagination/windowing)

Partner + referral validation

  • partnerFeeAccount and partnerFeeBps are all-or-nothing.
  • partnerFeeBps must be integer 0..9800.
  • referralCode must be 2-20 lowercase alphanumeric.
  • referralCode cannot be combined with partner fee fields.

Endpoint Selection

  • Use /burn/preview or /close/preview before execution when:
    • the user needs fee visibility
    • assets may be frozen/invalid/non-empty
  • Use /burn and /close when:
    • you want ready-to-sign transaction payloads
  • Use /burn-instructions and /close-instructions when:
    • your app assembles transactions client-side
  • Use /batch/close-all/preview first for wallet cleanup UX
  • Use /batch/close-all/summary for lightweight dashboard counts
  • Use /transactions/send-batch for multi-tx close-all pipelines

Example Workflow (Agent)

  1. Generate an API key with POST /api-keys/generate.
  2. Run preview endpoint for target operation.
  3. If preview is acceptable, request executable transaction payload.
  4. Sign transaction locally.
  5. Submit signed payload.
  6. Confirm completion via /transactions/status.
  7. Store operation metadata (signature, fees, lamports reclaimed).

Guidelines

  • DO run preview before destructive operations.
  • DO pass burnAmount as a string for large atomic values.
  • DO validate user/asset pubkeys before submitting.
  • DO keep private keys local; only send signed transactions to relay endpoints.
  • DON'T combine referralCode with partner fee fields.
  • DON'T send unsigned payloads to relay routes.
  • DON'T assume base64 encoding for relay payloads unless explicitly set encoding: "base64" (default is base58).

Resources

Skill Structure

sol-incinerator/
├── SKILL.md                          # This file
├── resources/
│   └── api-reference.md              # Endpoint matrix and request notes
├── examples/
│   └── basic/
│       └── http-flow.ts              # Close-account + token/NFT burn examples
├── templates/
│   └── sol-incinerator-client.ts     # Ready-to-use TypeScript client
└── docs/
    └── troubleshooting.md            # Common errors and fixes

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sol Incinerator AI skill do?

SOL Incinerator SDK for burning tokens, NFTs, and closing accounts

Why use Sol Incinerator on TypingMind?

Because you install it once and use it with any model. Sol Incinerator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sol Incinerator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sendaifun/skills/tree/main/skills/sol-incinerator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sol Incinerator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sol Incinerator?

As many as you like. As long as a model supports skills, you can use Sol Incinerator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sol Incinerator AI skill free?

Yes. It is published on GitHub by sendaifun under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇