amaniagent · open agent tooling

skills

A skill is executable trust – you install someone's instructions *and their scripts* into an agent that can touch your files, your keys, your machine. A supply chain needs a gate — and good skills to run behind it. Here are both.

🛡️ security 7 Skills
answer-verifier dependency-auditor mcp-auditor prompt-injection-detector repo-auditor settings-auditor skill-auditor

Score any skill, repo, or agent answer 0–8 with file:line evidence, before you trust it.

⚡ token-efficiency 4 Skills
context-optimization context-thrift lean-replies output-sandbox

Keep context and replies lean.

🔎 rag 1 Skill
composable-wiki-rag

Retrieval over a composable wiki.

🧠 memory 1 Skill
layered-agent-memory

Layered memory for agents.

🍎 apple 7 Skills
app-integration app-planning-per-platform apple-fitness healthkit metal-shaders widgets xcode-mcp

Skills for the Apple platforms.

🧡 swift 5 Skills
embedded-swift react-native-to-swift repo-to-swift-native swift-on-android swift-vapor

Swift beyond the app: embedded, Android, Vapor, ports.

🛠️ workflow 3 Skills
grill-me superpowers-tdd superpowers-writing-plans

How the work gets done: plans, TDD, being grilled.

🔧 tools-services 15 Skills
cli-anything-browser cli-anything-chromadb cli-anything-exa cli-anything-mermaid cli-anything-obsidian cli-anything-ollama cli-anything-zotero github-org-automation use-cli-anything use-crawl4ai use-gortex use-hermes use-n8n use-ntfy use-tailscale

The biggest category: CLI bridges and service hookups.

🌐 web 2 Skills
seo-white-hat web3-wallet-integration

SEO without tricks, and wallet integration on the web.

🌱 iot 1 Skill
led-grow-controller

Controlling an LED grow light.

How to spot a malicious skill or repo reports.j‑amani.de