/ Verzeichnis / Playground / openskills
● Community Geeksfino ⚡ Sofort

openskills

von Geeksfino · Geeksfino/openskills

Rust runtime with TS/Python bindings for Agent Skills — progressive disclosure, sandboxing, and portability beyond Claude.

openskills is infrastructure, not a single skill: a Rust runtime that loads SKILL.md bundles (metadata first, then body, then scripts/resources) and exposes them to any agent via TS or Python bindings. It adds sandboxing (Seatbelt on macOS, experimental WASM) so skill scripts can't quietly escape. Use it if you're building your own agent or want cross-agent portability for skills.

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

openskills-skill.replay ▶ bereit
0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "openskills-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Geeksfino/openskills",
        "~/.claude/skills/openskills"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "openskills-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Geeksfino/openskills",
        "~/.claude/skills/openskills"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "openskills-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Geeksfino/openskills",
        "~/.claude/skills/openskills"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "openskills-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Geeksfino/openskills",
        "~/.claude/skills/openskills"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "openskills-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Geeksfino/openskills",
        "~/.claude/skills/openskills"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json
{
  "context_servers": {
    "openskills-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/Geeksfino/openskills",
          "~/.claude/skills/openskills"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add openskills-skill -- git clone https://github.com/Geeksfino/openskills ~/.claude/skills/openskills

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: openskills

How to embed Agent Skills into your own agent runtime

👤 Engineers building custom LLM agents ⏱ ~120 min advanced

Wann einsetzen: You're writing an agent from scratch and want a skill system that already understands SKILL.md.

Voraussetzungen
  • Rust toolchain (for building) or prebuilt binding — rustup install stable; or use the TS/Python binding
  • Repo cloned — git clone https://github.com/Geeksfino/openskills ~/.claude/skills/openskills
Ablauf
  1. Install the binding
    Install the openskills Python or TS binding and point it at my skills directory.✓ Kopiert
    → Runtime loaded; skills enumerated
  2. Expose to your agent
    Wire the runtime into my agent's planner so it considers skills at each step.✓ Kopiert
    → Agent has a SkillRegistry abstraction
  3. Run sandboxed
    Enable Seatbelt sandboxing for skill scripts on macOS.✓ Kopiert
    → Skill scripts run under sandbox profile

Ergebnis: Your custom agent can load and run SKILL.md bundles like Claude Code does.

Fallstricke
  • Loading all scripts at startup kills memory — Rely on progressive disclosure — metadata first
  • Sandbox denies legitimate operations — Audit the sandbox profile; narrow-then-widen rather than default-deny everything
Kombinieren mit: filesystem

Run a skill in isolation to test it outside Claude Code

👤 Skill authors who want cross-agent validation ⏱ ~45 min intermediate

Wann einsetzen: You want to prove your skill works without the specific harness of Claude Code.

Ablauf
  1. Load the skill
    Load ~/.claude/skills/my-skill/ with openskills and print its metadata.✓ Kopiert
    → Parsed frontmatter + body
  2. Invoke with a prompt
    Feed it a sample task and observe what would get loaded.✓ Kopiert
    → Disclosure trace: what the agent would see

Ergebnis: Confidence your skill behaves portably.

Fallstricke
  • Skill depends on Claude Code internals — Refactor the skill to rely only on the public SKILL.md interface

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

openskills-skill + skill-optimizer-skill

Validate skills portably before optimizing them

Load the skill with openskills, then hand off to skill-optimizer for patch suggestions.✓ Kopiert
openskills-skill + filesystem

Operate on the skills directory directly

List all SKILL.md in ~/.claude/skills/, summarize each.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
skill-loader skills dir Agent startup minimal
progressive-disclosure skill id + stage During agent reasoning minimal
sandbox-runner script + policy Any time a skill spawns a subprocess script runtime

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
none
Tokens pro Aufruf
runtime is prompt-light; you control what's disclosed
Kosten in €
free, open source
Tipp
Keep progressive disclosure on — loading every script upfront blows context

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: none at runtime level
Datenabfluss: none beyond what scripts themselves do

Fehlerbehebung

Häufige Fehler und Lösungen

Binding import fails

Ensure the native binary matches your platform; rebuild from source if needed.

Sandbox blocks expected syscalls

Iterate on the Seatbelt profile; log denials to find the right allow list.

Alternativen

openskills vs. andere

AlternativeWann stattdessenKompromiss
Claude Code native skill loaderYou're only running inside Claude CodeNo cross-agent portability

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen