Agent skill

Kibibot

by LeoYeAI in LeoYeAI/openclaw-master-skills

Create tokens on-chain, check fee earnings, check Kibi Credit balance, trigger agent credit reload, and interact with KibiBot's Agent API and Kibi LLM Gateway.

MITAuto-check passedAI & LLM Engineering

Install Kibibot

skills CLI

$ npx skills add LeoYeAI/openclaw-master-skills --skill kibibot -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install LeoYeAI/openclaw-master-skills kibibot --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/kibibot .claude/skills/kibibot && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "kibibot" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/kibibot into .claude/skills/kibibot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kibibot", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/kibibot

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add LeoYeAI/openclaw-master-skills --skill kibibot -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install LeoYeAI/openclaw-master-skills kibibot --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/kibibot .agents/skills/kibibot && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "kibibot" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/kibibot into .agents/skills/kibibot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kibibot", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add LeoYeAI/openclaw-master-skills --skill kibibot -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install LeoYeAI/openclaw-master-skills kibibot --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/kibibot .cursor/skills/kibibot && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "kibibot" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/kibibot into .cursor/skills/kibibot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kibibot", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/kibibot

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add LeoYeAI/openclaw-master-skills --skill kibibot -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install LeoYeAI/openclaw-master-skills kibibot --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/kibibot .gemini/skills/kibibot && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "kibibot" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/kibibot into .gemini/skills/kibibot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kibibot", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install LeoYeAI/openclaw-master-skills kibibot

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add LeoYeAI/openclaw-master-skills --skill kibibot -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/kibibot .github/skills/kibibot && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "kibibot" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/kibibot into .github/skills/kibibot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kibibot", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add LeoYeAI/openclaw-master-skills --skill kibibot -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install LeoYeAI/openclaw-master-skills kibibot --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/kibibot .opencode/skills/kibibot && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "kibibot" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/kibibot into .opencode/skills/kibibot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kibibot", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: kibibot
GitHub stars: 2.2k
Token cost: ~5.1k tokens
SKILL.md length: 1,358 words
Files: 3 (incl. references)
Skills in repo: 1,235
Repo updated: Jul 20, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Create tokens on-chain, check fee earnings, check Kibi Credit balance, trigger agent credit reload, and interact with KibiBot's Agent API and Kibi LLM Gateway.

Works in 3 steps: Get your API key → Add Kibi Credits (for AI model access) → Set up Kibi LLM Gateway (optional)
Agent credit reload
SKILL.md covers Setup, What This Skill Can Do and API Reference
Calls curl; reaches llm.kibi.bot and github.com

What it does

Kibibot is an agent skill from LeoYeAI/openclaw-master-skills. Create tokens on-chain, check fee earnings, check Kibi Credit balance, trigger agent credit reload, and interact with KibiBot's Agent API and Kibi LLM Gateway. Use when asked to create a token via KibiBot, check fee earnings across chains and platforms, check KibiBot Kibi Credit balance, check daily token creation quota, reload credits from trading wallet, or make LLM calls through KibiBot's gateway.

Its SKILL.md is about 5.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `_meta.json` and `references/api.md`).

It sits in AI & LLM Engineering, covering Model routing and gateways, Smart contracts and Trading and backtesting. It works with OpenAI and Qwen. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

Agent credit reload
Interact with KibiBots Agent API and Kibi LLM Gateway
Asked to create a token via KibiBot
Check fee earnings across chains and platforms

Example prompts

“/kibibot”

Requirements

A credential in YOUR_KB_API_KEY

Workflow steps

3 steps, taken from the step headings in SKILL.md.

Get your API key
Add Kibi Credits (for AI model access)
Set up Kibi LLM Gateway (optional)

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- llm.kibi.bot
- github.com
- api.kibi.bot
- x.com
Also links to:
- kibi.bot
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Kibibot loads about 5.1k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 103 tokens; SKILL.md has 1,358 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~103
When it runs · the whole SKILL.md, loaded when a task matches: ~5.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~6.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,358 words, ~5,110 tokens.

Download SKILL.mdSave it as .claude/skills/kibibot/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: kibibot
description: Create tokens on-chain, check fee earnings, check Kibi Credit balance, trigger agent credit reload, and interact with KibiBot's Agent API and Kibi LLM Gateway. Use when asked to create a token via KibiBot, check fee earnings across chains and platforms, check KibiBot Kibi Credit balance, check daily token creation quota, reload credits from trading wallet, or make LLM calls through KibiBot's gateway.

KibiBot Skill

Create tokens on-chain, earn trading fees, and use KibiBot's Kibi LLM Gateway — all from natural language commands.

Version: 1.5.0
Provider: KibiBot
Auth: API key required — get yours at kibi.bot/settings/api-keys
Install: install the kibibot skill from https://github.com/KibiAgent/skills/tree/main/kibibot

Setup

Step 1 — Get your API key

Go to kibi.bot/settings/api-keys → Create API Key → copy the kb_... key.

Permissions: Base API is always included. Enable Kibi LLM Gateway if you want to use AI models. Enable Agent Reload if you want the agent to top up your Kibi Credits automatically from your trading wallet.

Step 2 — Add Kibi Credits (for AI model access)

Go to kibi.bot/credits → Add Credit.
Minimum $1 to start. Credits are consumed per token used.

Step 3 — Set up Kibi LLM Gateway (optional)

This step registers KibiBot as your agent's AI model provider, so your agent thinks using Claude/GPT/Gemini billed to your Kibi Credits — instead of paying Anthropic/OpenAI directly. It's separate from the Agent API skill.

OpenClaw users: follow the config below. If you're using LangChain, CrewAI, or any OpenAI-compatible framework, point your base_url to https://llm.kibi.bot/v1 with your kb_... API key instead.

OpenClaw users — add KibiBot as an LLM provider in ~/.openclaw/openclaw.json:

json

{
  "models": {
    "mode": "merge",
    "providers": {
      "kibi": {
        "baseUrl": "https://llm.kibi.bot",
        "apiKey": "YOUR_KB_API_KEY",
        "api": "openai-completions",
        "models": [
          { "id": "kibi-haiku",        "name": "Kibi Haiku",            "api": "anthropic-messages", "contextWindow": 200000,  "maxTokens": 4096  },
          { "id": "kibi-sonnet",       "name": "Kibi Sonnet",           "api": "anthropic-messages", "contextWindow": 1000000, "maxTokens": 128000 },
          { "id": "kibi-opus",         "name": "Kibi Opus",             "api": "anthropic-messages", "contextWindow": 1000000, "maxTokens": 128000 },
          { "id": "kibi-gpt4o",        "name": "Kibi GPT-4o",           "contextWindow": 128000,     "maxTokens": 16384 },
          { "id": "kibi-gpt4o-mini",   "name": "Kibi GPT-4o Mini",      "contextWindow": 128000,     "maxTokens": 16384 },
          { "id": "kibi-gemini-flash", "name": "Kibi Gemini Flash",     "contextWindow": 1048576,    "maxTokens": 8192  },
          { "id": "kibi-gemini-pro",   "name": "Kibi Gemini Pro",       "contextWindow": 1048576,    "maxTokens": 8192  },
          { "id": "kibi-deepseek-v3",  "name": "Kibi DeepSeek V3.2",   "contextWindow": 163840,     "maxTokens": 16384 },
          { "id": "kibi-qwen3-coder",  "name": "Kibi Qwen3 Coder",     "contextWindow": 262144,     "maxTokens": 65536 },
          { "id": "kibi-qwen3-plus",   "name": "Kibi Qwen3.5 Plus",    "contextWindow": 1000000,    "maxTokens": 16384 },
          { "id": "kibi-qwen3-flash",  "name": "Kibi Qwen3.5 Flash",   "contextWindow": 1000000,    "maxTokens": 16384 },
          { "id": "kibi-kimi-k2",      "name": "Kibi Kimi K2.5",       "contextWindow": 262144,     "maxTokens": 16384 },
          { "id": "kibi-minimax-m2",   "name": "Kibi MiniMax M2.5",    "contextWindow": 196608,     "maxTokens": 16384 },
          { "id": "kibi-minimax-m3",   "name": "Kibi MiniMax M2.7",    "contextWindow": 204800,     "maxTokens": 16384 },
          { "id": "kibi-seed-lite",    "name": "Kibi Seed 2.0 Lite",   "contextWindow": 262144,     "maxTokens": 16384 },
          { "id": "kibi-seed-mini",    "name": "Kibi Seed 2.0 Mini",   "contextWindow": 262144,     "maxTokens": 16384 }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "models": {
        "kibi/kibi-haiku":        { "alias": "kibi-haiku" },
        "kibi/kibi-sonnet":       { "alias": "kibi-sonnet" },
        "kibi/kibi-opus":         { "alias": "kibi-opus" },
        "kibi/kibi-gpt4o":        { "alias": "kibi-gpt4o" },
        "kibi/kibi-gpt4o-mini":   { "alias": "kibi-gpt4o-mini" },
        "kibi/kibi-gemini-flash": { "alias": "kibi-gemini-flash" },
        "kibi/kibi-gemini-pro":   { "alias": "kibi-gemini-pro" },
        "kibi/kibi-deepseek-v3":  { "alias": "kibi-deepseek-v3" },
        "kibi/kibi-qwen3-coder":  { "alias": "kibi-qwen3-coder" },
        "kibi/kibi-qwen3-plus":   { "alias": "kibi-qwen3-plus" },
        "kibi/kibi-qwen3-flash":  { "alias": "kibi-qwen3-flash" },
        "kibi/kibi-kimi-k2":      { "alias": "kibi-kimi-k2" },
        "kibi/kibi-minimax-m2":   { "alias": "kibi-minimax-m2" },
        "kibi/kibi-minimax-m3":   { "alias": "kibi-minimax-m3" },
        "kibi/kibi-seed-lite":    { "alias": "kibi-seed-lite" },
        "kibi/kibi-seed-mini":    { "alias": "kibi-seed-mini" }
      }
    }
  }
}

Note: The agents.defaults.models block is required — it allowlists the models and registers aliases so both the model dropdown picker and /model command work correctly. The alias must match the model id exactly.

Set as default model (optional):

json

{
  "agents": {
    "defaults": {
      "model": {
        "primary": "kibi/kibi-sonnet"
      }
    }
  }
}

Then restart OpenClaw:

openclaw gateway restart

Switch models using the dropdown picker or /model command:

/model kibi-haiku
/model kibi-sonnet
/model kibi-opus
/model kibi-gpt4o
/model kibi-gpt4o-mini
/model kibi-gemini-flash
/model kibi-gemini-pro
/model kibi-deepseek-v3
/model kibi-qwen3-coder
/model kibi-qwen3-plus
/model kibi-qwen3-flash
/model kibi-kimi-k2
/model kibi-minimax-m2
/model kibi-minimax-m3
/model kibi-seed-lite
/model kibi-seed-mini

Available Models

Model ID	Provider	Context
`claude-haiku-4-5`	Anthropic	200k
`claude-sonnet-4-6`	Anthropic	1M
`claude-opus-4-6`	Anthropic	1M
`gpt-4o`	OpenAI	128k
`gpt-4o-mini`	OpenAI	128k
`gemini-2.5-flash`	Google	1M
`gemini-2.5-pro`	Google	1M
`deepseek-v3.2`	DeepSeek	164k
`qwen3-coder`	Alibaba	262k
`qwen3.5-plus`	Alibaba	1M
`qwen3.5-flash`	Alibaba	1M
`kimi-k2.5`	Moonshot	262k
`minimax-m2.5`	MiniMax	192k
`minimax-m2.7`	MiniMax	200k
`seed-2.0-lite`	ByteDance	262k
`seed-2.0-mini`	ByteDance	262k

Verify by asking your agent: "what's my KibiBot Kibi Credit balance?"

What This Skill Can Do

Kibi LLM Gateway

Use KibiBot-hosted AI models billed against your Kibi Credits. Same API key for LLM calls and agent actions.

Check balance: "what's my KibiBot Kibi Credit balance?"
Add credits: "I need to top up KibiBot credits" → agent links to kibi.bot/credits
Reload credits: "reload my KibiBot credits from my trading wallet" (requires Agent Reload permission + configured on Credits page)
Model info: "what models does KibiBot support?"

Token Creation

Create tokens on Base, BSC, or Solana — KibiBot handles wallet creation, gas sponsorship, and on-chain deployment.

"launch a token called MOON on Base"
"create a meme coin named PEPE with ticker $PEPE on BSC"
"make a test token called DEMO on Base Sepolia"

Token creation is async. After calling the API, poll the job status endpoint until complete (usually 30–60 seconds).

Created Tokens

"what tokens have I created on KibiBot?"
"show my KibiBot token portfolio"

Quota

"how many free token launches do I have left today?"
"what's my KibiBot quota per chain?"

Wallet Balances

"what's my KibiBot wallet balance?"
"show my ETH, BNB, SOL and stablecoin balances on KibiBot"

Fee Earnings

Check creator fee earnings across all chains and platforms — data is read from pre-computed DB cache (fast, no on-chain calls).

"what are my KibiBot fee earnings?"
"show my fee earnings summary across all chains"
"what have I earned from my flap tokens on BSC?"
"what are my fee earnings on Base?"
"how much have I earned from my pumpfun tokens on Solana?"
"how much has token 0x... earned on flap?"
"what are the fees for my pumpfun token [mint address]?"

Token Lookup

"what's the price of $MOON on KibiBot?"
"look up token 0x... on Base"

Account

"show me my KibiBot profile"
"what's my KibiBot Twitter username and wallet address?"

Skills

"what can KibiBot do?" → calls GET /agent/v1/skills

API Reference

Base URL: https://api.kibi.bot/agent/v1
Auth header: X-Api-Key: kb_...

GET /me

Returns user profile, wallet addresses, and account info.

Response:

json

{
  "twitter_user_id": "...",
  "twitter_username": "...",
  "profile_image_url": "...",
  "followers_count": 1234,
  "joined_at": "2025-01-01T00:00:00Z"
}

GET /skills

List all available KibiBot Agent API capabilities with examples. No auth required.

Response:

json

{
  "skills": [
    {
      "name": "token_create",
      "description": "Deploy a new token on Base, BSC, or Solana",
      "example": "POST /agent/v1/token/create {\"name\": \"MyToken\", \"symbol\": \"MTK\", \"chain\": \"base\"}"
    }
  ],
  "total": 9
}

POST /token/create

Create a token on-chain (async). Returns a job_id to poll.

Request:

json

{
  "name": "MOON",
  "symbol": "MOON",
  "chain": "base",
  "description": "To the moon",
  "source_url": "https://x.com/user/status/123",
  "image_url": "https://...",
  "platform": "basememe"
}

chain: base | bsc | solana
source_url (optional): Twitter/X post URL — tweet image used as token image if image_url not provided
image_url (optional): HTTP/HTTPS URL or IPFS URI — overrides source tweet image
platform (optional): basememe | clanker | flap | fourmeme | pumpfun — defaults to chain default if omitted

Response (202 Accepted):

json

{
  "job_id": 12345,
  "status": "pending",
  "chain": "base",
  "quota": {
    "chain": "base",
    "free_used_today": 1,
    "free_limit": 3,
    "sponsored_remaining": 2
  }
}

Pre-check errors:

403 insufficient_followers — need minimum followers to create tokens
402 insufficient_balance — free quota used, trading wallet balance too low
429 daily_cap_exceeded — absolute daily cap reached across all chains

GET /jobs/{job_id}

Poll token creation status.

Response:

json

{
  "job_id": 12345,
  "status": "completed",
  "chain": "base",
  "token_address": "0x...",
  "error": null,
  "created_at": "2026-01-01T00:00:00Z",
  "completed_at": "2026-01-01T00:01:00Z"
}

Status values: pending | processing | completed | failed

GET /token/{address}

Get token info by address.

Query: ?chain=base (optional — searches all chains if omitted)

Response:

json

{
  "token_address": "0x...",
  "name": "MOON",
  "symbol": "MOON",
  "chain": "base",
  "platform": "basememe",
  "creator_twitter_username": "...",
  "price_usd": "0.0001234",
  "market_cap_usd": "12340",
  "volume_24h_usd": "500",
  "creator_reward_usd": "1.23",
  "created_at": "2026-01-01T00:00:00Z"
}

GET /tokens/created

Get paginated list of tokens you have created.

Query: ?page=1&page_size=20

Response:

json

{
  "tokens": [
    {
      "token_address": "0x...",
      "name": "MOON",
      "symbol": "MOON",
      "chain": "base",
      "platform": "basememe",
      "created_at": "2026-01-01T00:00:00Z"
    }
  ],
  "total": 5,
  "page": 1,
  "page_size": 20,
  "has_more": false
}

GET /balance/credits

Get Kibi Credit balance and agent reload configuration.

Response:

json

{
  "balance_usd": "4.92",
  "balance_usd_cents": 492,
  "agent_reload": {
    "enabled": true,
    "amount_usd": 5.0,
    "daily_limit_usd": 100.0,
    "chains": ["base"]
  }
}

agent_reload is null if not configured. enabled: false means agent reload is off.

Show full SKILL.md (561 more words)Show less

POST /balance/credits/reload

Trigger a Kibi Credit reload from the trading wallet.

Requirements:

User must have enabled Agent Reload at kibi.bot/credits
The API key must have reload_enabled = true
The API key must have llm_enabled = true
Trading wallet must have sufficient USDC/USDT on at least one configured chain
Daily reload limit must not be exceeded

This is manually triggered by the agent — there is no automatic background polling. Call this endpoint when the agent determines a credit reload is needed (e.g. before a long task).

Response:

json

{
  "success": true,
  "amount_usd": "5.00",
  "tx_hash": "0x...",
  "new_balance_usd": "9.92",
  "daily_used_usd": "5.00",
  "daily_remaining_usd": "95.00"
}

Errors:

403 — reload not enabled for user or key
429 — daily limit would be exceeded
400 — insufficient stablecoin balance on all configured chains
500 — transaction failed

POST /balance/credits/reload/disable

Emergency kill switch — agent disables its own reload permission. Cannot be re-enabled by the agent (human must re-enable via dashboard).

Use this if the agent detects unexpected reload behaviour or wants to self-limit spending.

Response: 204 No Content

GET /balance/wallet

Get on-chain wallet balances across all chains (main + trading wallets).

Response:

json

{
  "evm_main": {
    "address": "0x...",
    "balance_eth": "0.050000",
    "balance_bnb": "0.100000",
    "balance_usdc_base": "10.000000",
    "balance_usdt_bsc": "5.000000"
  },
  "evm_trading": {
    "address": "0x...",
    "balance_eth": "0.010000",
    "balance_bnb": "0.005000",
    "balance_usdc_base": "0.000000",
    "balance_usdt_bsc": "0.000000"
  },
  "solana_main": {
    "address": "...",
    "balance_sol": "0.500000",
    "balance_usdc_solana": "5.000000"
  },
  "solana_trading": {
    "address": "...",
    "balance_sol": "0.050000",
    "balance_usdc_solana": "0.000000"
  }
}

Any field may be null if the wallet is not set up or the RPC is unavailable. Check *_error fields (e.g. eth_error: "rpc_unavailable") for failure reasons.

GET /fees/summary

Get total fee earnings across all chains in a single call. All data is pre-computed — fast, no on-chain calls.

Response:

json

{
  "bsc": {
    "chain_id": 56,
    "token_count": 12,
    "total_earned_bnb": 0.053
  },
  "base": {
    "chain_id": 8453,
    "token_count": 7,
    "basememe_total_earned_eth": "0.0290",
    "basememe_claimable_eth": "0.0145",
    "clanker_claimable_weth_eth": "0.0080"
  },
  "solana": {
    "chain_id": 101,
    "token_count": 4,
    "total_earnings_sol": 0.05,
    "total_claimable_sol": 0.012
  }
}

GET /fees/earnings

Get per-platform fee breakdown for a specific chain.

Query: ?chain=bsc | ?chain=base | ?chain=solana

BSC response:

json

{
  "chain": "bsc",
  "chain_id": 56,
  "flap": { "total_earned_bnb": 0.042, "earning_token_count": 3 },
  "fourmeme": { "total_earned_bnb": 0.011, "earning_token_count": 1 }
}

Base response:

json

{
  "chain": "base",
  "chain_id": 8453,
  "basememe": { "total_earned_eth": "0.0290", "claimable_eth": "0.0145", "token_count": 5 },
  "clanker": { "claimable_weth_eth": "0.0080", "token_count": 2 }
}

Solana response:

json

{
  "chain": "solana",
  "chain_id": 101,
  "pumpfun": { "total_earnings_sol": 0.05, "total_claimable_sol": 0.012, "earning_token_count": 4 }
}

GET /fees/token

Get fee earnings for a specific token.

Query: ?chain=bsc&platform=flap&token_address=0x...

chain: bsc | base | solana
platform: flap | fourmeme (BSC) · pumpfun (Solana)
token_address: contract address (EVM) or mint address (Solana)

Note: basememe and clanker do not support per-token fee tracking — a helpful redirect message is returned instead.

BSC/Flap response:

json

{
  "token_address": "0x...",
  "token_name": "MyToken",
  "token_symbol": "MTK",
  "platform": "flap",
  "chain": "bsc",
  "earned_bnb": 0.021
}

Solana/Pumpfun response:

json

{
  "mint": "AbcDef...",
  "token_name": "MyToken",
  "token_symbol": "MTK",
  "platform": "pumpfun",
  "chain": "solana",
  "actual_sol": 0.05,
  "distributable_sol": 0.012,
  "total_sol": 0.062,
  "is_graduated": true
}

Returns 404 if token not found or not owned by the authenticated user.

GET /quota

Get daily token creation quota and trading wallet readiness per chain.

Response:

json

{
  "chains": [
    {
      "chain": "base",
      "free_used_today": 1,
      "free_limit": 3,
      "sponsored_remaining": 2,
      "can_create_paid": true,
      "trading_wallet_balance": "0.010000 ETH",
      "trading_wallet_address": "0x..."
    },
    {
      "chain": "bsc",
      "free_used_today": 0,
      "free_limit": 3,
      "sponsored_remaining": 3,
      "can_create_paid": false,
      "trading_wallet_balance": "0.000000 BNB",
      "trading_wallet_address": "0x..."
    },
    {
      "chain": "solana",
      "free_used_today": 0,
      "free_limit": 3,
      "sponsored_remaining": 3,
      "can_create_paid": true,
      "trading_wallet_balance": "0.050000 SOL",
      "trading_wallet_address": "..."
    }
  ]
}

Kibi LLM Gateway Reference

Base URL: https://llm.kibi.bot
Auth: X-Api-Key: kb_... or Authorization: Bearer kb_...

POST /v1/messages (Anthropic format)

Compatible with Claude models via Anthropic Messages API format.

bash

curl https://llm.kibi.bot/v1/messages \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: YOUR_KB_API_KEY" \
  -d '{
    "model": "claude-haiku-4-5",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 100
  }'

POST /v1/chat/completions (OpenAI format)

Compatible with all models via OpenAI Chat Completions format.

bash

curl https://llm.kibi.bot/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: YOUR_KB_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 100
  }'

GET /v1/models

List available models.

GET /v1/models/openclaw

Returns a ready-to-paste OpenClaw provider config block. No auth required.

Error Codes

Code	Meaning
401	Missing or invalid API key
402	Insufficient Kibi Credits (LLM) or trading wallet balance (token creation)
403	Permission denied — feature not enabled for this key or user
404	Resource not found
422	Validation error — check request body
429	Rate limited or daily cap exceeded — wait before retrying
500	Server error — retry

Troubleshooting

402 on LLM calls
Kibi Credits exhausted. Top up at kibi.bot/credits.
Note: Kibi Credits ≠ trading wallet. Topping up one doesn't affect the other.

403 on reload
Either Agent Reload is not enabled for the user (kibi.bot/credits → Agent Reload section), or the API key doesn't have reload_enabled. Check both.

401 Unauthorized
API key missing or invalid. Manage keys at kibi.bot/settings/api-keys.
Ensure you send: X-Api-Key: kb_...

Token creation stuck at pending
Poll GET /agent/v1/jobs/{job_id} — creation usually takes 30–60 seconds.
If still pending after 5 minutes, check the error field.

429 on reload
Daily reload limit exceeded. Check daily_remaining_usd in the balance response.

400 on reload — insufficient balance
No configured chain has enough USDC/USDT in the trading wallet. Check GET /balance/wallet and top up.

Full Documentation

Agent API: kibi.bot/agent
API Keys: kibi.bot/settings/api-keys
Kibi LLM Gateway: kibi.bot/llm
OpenClaw setup: kibi.bot/llm/openclaw
Kibi Credits: kibi.bot/credits

Files

SKILL.md and 2 other files (references) in skills/kibibot of LeoYeAI/openclaw-master-skills.

SKILL.md
_meta.json
references/api.md

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Kibibot next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Kibibot compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Kibibot this skillLeoYeAI/openclaw-master-skills	2.2k	—	~5.1k	Automated safety check: Pass	MIT	2 mo ago
Higress Auto Routerhigress-group/higress	9.5k	—	~954	Automated safety check: Pass	Apache-2.0	2 days ago
Page AgentTommy-yw/RunbookHermes	546	3 repos	~2.3k	Automated safety check: Notes	MIT	4 mo ago
Embeddings via 9Routerdecolua/9router	31k	—	~604	Automated safety check: Pass	MIT	2 days ago
Using Ccproxy APIstarbaser/ccproxy	350	—	~4k	Automated safety check: Pass	Custom licence	2 mo ago
Caching Architecturemajiayu000/litellm-rs	117	—	~2k	Automated safety check: Pass	MIT	yesterday

Similar skills

Higress Auto Router
higress-group/higress
Configure automatic model routing using the get-ai-gateway.sh CLI tool for Higress AI Gateway.
9.5k GitHub stars~954 tokensUpdated 2 days ago
AI & LLM EngineeringAuto-check passed
Page Agent
Tommy-yw/RunbookHermes
Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script tag or npm package and lets end-users of your site drive the UI with…
546 GitHub starsUsed in 3 repos~2.3k tokens
Productivity & AutomationAuto-check: notes
Embeddings via 9Router
decolua/9router
Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.
31k GitHub stars~604 tokensUpdated 2 days ago
AI & LLM EngineeringAuto-check passed
Using Ccproxy API
starbaser/ccproxy
Guides users through ccproxy as an OpenAI-compatible and Anthropic-compatible LLM API server with SDK integration, OAuth authentication, sentinel key substitution, model routing, and troubleshooting.
350 GitHub stars~4k tokensUpdated 2 mo ago
AI & LLM EngineeringAuto-check passed
Caching Architecture
majiayu000/litellm-rs
LiteLLM-RS response caching architecture. An agent skill from majiayu000/litellm-rs.
117 GitHub stars~2k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Streaming Architecture
majiayu000/litellm-rs
LiteLLM-RS Streaming Architecture. An agent skill from majiayu000/litellm-rs.
117 GitHub stars~2.1k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed

Questions about Kibibot

What does Kibibot do?

Create tokens on-chain, check fee earnings, check Kibi Credit balance, trigger agent credit reload, and interact with KibiBot's Agent API and Kibi LLM Gateway. Kibibot is an agent skill from LeoYeAI/openclaw-master-skills. Create tokens on-chain, check fee earnings, check Kibi Credit balance, trigger agent credit reload, and interact with KibiBot's Agent API and Kibi LLM Gateway.

When should I use Kibibot?

Kibibot fits situations like: agent credit reload; interact with KibiBots Agent API and Kibi LLM Gateway; asked to create a token via KibiBot; check fee earnings across chains and platforms.

How do I install Kibibot in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill kibibot -a claude-code`. Or copy the skill folder (skills/kibibot in LeoYeAI/openclaw-master-skills) into .claude/skills/kibibot in your project. Claude Code loads it when a task matches its description.

How do I install Kibibot in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill kibibot -a codex`. Or copy the skill folder (skills/kibibot in LeoYeAI/openclaw-master-skills) into .agents/skills/kibibot in your project. Codex loads it when a task matches its description.

Can I use Kibibot in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill kibibot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kibibot, .gemini/skills/kibibot, .github/skills/kibibot and .opencode/skills/kibibot in your project.

What does Kibibot need to run?

Going by SKILL.md and its folder, Kibibot needs the command-line tools its instructions call (curl). Our summary lists: A credential in YOUR_KB_API_KEY.

Does Kibibot access the network?

SKILL.md names 5 domains. In commands or code: llm.kibi.bot, github.com, api.kibi.bot and x.com; the agent is likely to contact these when it follows the instructions. As links in the text: kibi.bot. This is read from the text; nothing was executed.

Is Kibibot safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Kibibot use?

Kibibot is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kibibot use?

About 5.1k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 994 tokens, read only when the agent opens those files.

What are the alternatives to Kibibot?

Skills that share tags, products or a category with Kibibot: Higress Auto Router (higress-group/higress, 9.5k stars), Page Agent (Tommy-yw/RunbookHermes, 546 stars), Embeddings via 9Router (decolua/9router, 31k stars) and Using Ccproxy API (starbaser/ccproxy, 350 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kibibot?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Kibibot

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

KibiBot Skill

Setup

Step 1 — Get your API key

Step 2 — Add Kibi Credits (for AI model access)

Step 3 — Set up Kibi LLM Gateway (optional)

Available Models

What This Skill Can Do

Kibi LLM Gateway

Token Creation

Created Tokens

Quota

Wallet Balances

Fee Earnings

Token Lookup

Account

Skills

API Reference

GET /me

GET /skills

POST /token/create

GET /jobs/{job_id}

GET /token/{address}

GET /tokens/created

GET /balance/credits

POST /balance/credits/reload

POST /balance/credits/reload/disable

GET /balance/wallet

GET /fees/summary

GET /fees/earnings

GET /fees/token

GET /quota

Kibi LLM Gateway Reference

POST /v1/messages (Anthropic format)

POST /v1/chat/completions (OpenAI format)

GET /v1/models

GET /v1/models/openclaw

Error Codes

Troubleshooting

Full Documentation

Files

Compare with similar skills

Similar skills

More from LeoYeAI/openclaw-master-skills

Related

Questions about Kibibot