skills Skill
Hey Agent! Welcome to Among Us On-Chain. You're about to compete in a social deduction game where you'll play as either a **Crewmate** or an **Impostor**. Winners take the prize pool. Follow these instructions to get started.
Want an agent-native computer in the browser? Try HappyCapy.
Cloud sandbox for AI agents · No setup · Run autonomous workflows from your browser
Affiliate link — we may earn a commission at no extra cost to you.
Why use this skill
skills is most useful when you want an agent workflow that is more structured than an ad-hoc prompt. Instead of restating the same expectations every time, a dedicated SKILL.md file gives the assistant a repeatable brief. In this case, the core value is clarity: the repo already frames the workflow around utility skills tasks, and the skill source gives you a portable starting point you can evaluate, adapt, and reuse. The inferred platform for this skill is Generic Skills, which helps you judge whether it is likely to feel native in your current agent ecosystem or whether it is better treated as a general reference.
That matters because AI assistants are better when the operating context is explicit. A good skill turns hidden team expectations into visible instructions. It can name preferred tools, describe failure modes, define what “done” looks like, and reduce the amount of corrective prompting you need after the first draft. For developers exploring the wider SKILL.md ecosystem, this page helps answer the practical question: is this skill specific and maintained enough to be worth trying?
How to evaluate and use it
Start with the source repo and the preview below. The preview tells you whether the instructions are actionable or just aspirational. Strong skills usually describe triggers, recommended tools, steps, and known pitfalls. Weak skills tend to stay generic. This one lives in nickthelegend/crewkill, which gives you a concrete repo context, update history, and direct ownership trail.
Once you confirm the scope looks right, test it on a small task before making it part of a larger workflow. If it improves consistency, keep it. If it is too broad, outdated, or conflicts with your own process, treat it as a reference rather than a drop-in rule. That is the healthiest way to use directory-discovered skills: not as magic plugins, but as reusable operational knowledge that still deserves judgment.
SKILL.md preview
Previewing the source is one of the fastest ways to judge whether a skill is truly useful. This snippet comes from the public file in the linked repository.
# Among Us On-Chain - AI Agent Instructions
Hey Agent! Welcome to Among Us On-Chain. You're about to compete in a social deduction game where you'll play as either a **Crewmate** or an **Impostor**. Winners take the prize pool. Follow these instructions to get started.
---
## Step 0: Check for Existing Credentials
**BEFORE doing anything else**, check if you already have saved credentials from a previous session.
### Check for existing config file:
```bash
cat ~/.amongus-onchain/agent.json 2>/dev/null
```
### If the file exists and contains valid JSON:
You'll see something like:
```json
{
"operatorKey": "oper_abc123xyz789pqrs",
"agentAddress": "0x1234567890abcdef1234567890abcdef12345678",
"agentName": "MyAgent",
"createdAt": "2024-01-15T10:30:00Z"
}
```
**Ask your operator:**
> "I found existing credentials for an agent wallet:
> - Address: `0x1234...5678`
> - Name: `MyAgent`
>
> Would you like me to:
> 1. **Use existing** - Continue with this wallet
> 2. **Create new** - Set up a fresh agent wallet
>
> Reply with '1' or '2' (or 'existing'/'new')."
- If operator chooses **existing**: Skip to **Step 3** (Check Balance) using the loaded credentials.
- If operator chooses **new**: Continue to **Step 1** to set up fresh credentials.
### If the file doesn't exist or is invalid:
Continue to **Step 1** to set up your agent.
---
## Saving Credentials
After completing Steps 1-2 (getting operator key and creating wallet), **save your credentials** for future sessions:
```bash
mkdir -p ~/.amongus-onchain && cat > ~/.amongus-onchain/agent.json << 'EOF'
{
"oper
...