Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Bnb Chain Ai Mining

ASecurity

Mine AIT (Proof of AI Work) on BNB Chain. Install, configure, start/stop mining entirely from OpenClaw. No terminal or manual file edits required.

19 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgonodegitapi

Works with

terminalapi

Security Analysis

A92/100
mediumUses curl or wget to download content
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill bnb-chain-ai-mining --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Bnb Chain Ai Mining?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Bnb Chain Ai Mining
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-bnb-chain-ai-mining/badge)](https://www.skillsdirectory.com/skills/rondoflow-bnb-chain-ai-mining)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: bnb-chain-ai-mining
description: "Mine AIT (Proof of AI Work) on BNB Chain. Install, configure, start/stop mining entirely from OpenClaw. No terminal or manual file edits required."
category: "Community"
author: community
version: "1.0.2"
icon: puzzle
---

# AI Mine (PoAIW) — OpenClaw Skill

This skill lets users **install**, **configure**, and **start/stop** AIT mining entirely from OpenClaw. All actions are performed by the agent via Exec; the user never needs to open a terminal or edit files manually.

**Supported user intents (English trigger phrases):**

- **Install** — e.g. "install AIT mining", "set up AIT miner", "install the miner"
- **Configure** — e.g. "configure AIT mining", "configure mining", "set up my keys"
- **Start mining** — e.g. "start mining", "start AIT mining", "begin mining"
- **Stop mining** — e.g. "stop mining", "stop AIT mining"
- **Mining status** — e.g. "mining status", "status", "how is mining doing"
- **Balance** — e.g. "AIT balance", "check balance", "my AIT balance"

**Conventions:**

- `AIMINE_DIR`: base directory for the repo; default `~/PoAIW`. Miner directory is `$AIMINE_DIR/miner`.
- Port for the miner web API: `3000` (localhost only).
- Keys: user can set `PRIVATE_KEY` and either `OPENAI_KEY` or `OPENAI_API_KEY` in OpenClaw skill config (env injection), or provide them once in chat. The miner accepts both env var names for the OpenAI key. Then the agent runs init with those values.

---

## When the user wants to INSTALL the miner

Run (use AIMINE_DIR if set, else default to $HOME/PoAIW):

```
AIMINE_DIR=${AIMINE_DIR:-$HOME/PoAIW}
[ -d "$AIMINE_DIR/.git" ] || git clone https://github.com/AIMineRes/PoAIW.git "$AIMINE_DIR"
cd "$AIMINE_DIR/miner" && npm install
```

Do not ask the user to open a terminal or run these manually.

---

## When the user wants to CONFIGURE mining

The user must have provided wallet private key and OpenAI API key (either in OpenClaw skill config as PRIVATE_KEY and OPENAI_KEY or OPENAI_API_KEY, or in the conversation). If users get "invalid API key", have them check: no leading/trailing spaces, key starts with sk-, and if using OpenClaw config try setting OPENAI_API_KEY (some UIs use that name).

- **If keys are in environment** (e.g. injected by OpenClaw skill config): run  
  `cd "$AIMINE_DIR/miner" && npx ts-node src/index.ts init --from-env`  
  (ensure AIMINE_DIR is set or use $HOME/PoAIW/miner).

- **If the user provided keys in the message**: run  
  `cd "$AIMINE_DIR/miner" && npx ts-node src/index.ts init --private-key <key> --openai-key <key>`  
  using the keys they provided. Do not echo the keys back in full.

Do not ask the user to manually edit .env or openclaw.json.

---

## When the user wants to START mining

Run the one-shot script so that the web server is started in the background if needed, then the API is called. Do **not** tell the user to "run npm run web first".

```
cd "${AIMINE_DIR:-$HOME/PoAIW}/miner" && node scripts/start-mining.js
```

If AIMINE_DIR is not set, use $HOME/PoAIW (or equivalent on the host). The script will start the web server on port 3000 if it is not already listening, wait a few seconds, then POST to http://127.0.0.1:3000/api/start.

---

## When the user wants to STOP mining

Run:

```
curl -s -X POST http://127.0.0.1:3000/api/stop
```

---

## When the user wants MINING STATUS

Run:

```
curl -s http://127.0.0.1:3000/api/status
```

Then summarize the JSON (miningActive, blocksMined, tokenBalance, bnbBalance, hashRate) in a short reply.

---

## When the user wants AIT BALANCE (wallet / mining stats)

Run:

```
cd "${AIMINE_DIR:-$HOME/PoAIW}/miner" && npx ts-node src/index.ts balance
```

Summarize the output for the user.

---

## Summary

- **Install**: clone repo into AIMINE_DIR (default ~/PoAIW), then `cd miner && npm install`.
- **Configure**: `ai-mine init --from-env` (if keys in env) or `ai-mine init --private-key ... --openai-key ...` (if user gave keys in chat).
- **Start**: `node scripts/start-mining.js` in the miner directory (no need for user to run npm run web).
- **Stop**: `curl -s -X POST http://127.0.0.1:3000/api/stop`.
- **Status**: `curl -s http://127.0.0.1:3000/api/status`.
- **Balance**: `npx ts-node src/index.ts balance` in the miner directory.

Always use the miner directory as `$AIMINE_DIR/miner` with AIMINE_DIR defaulting to ~/PoAIW when not set.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →