/ Annuaire / Playground / openskills
● Communauté Geeksfino ⚡ Instantané

openskills

par 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.

Pourquoi l'utiliser

Fonctionnalités clés

Démo en direct

Aperçu en pratique

openskills-skill.replay ▶ prêt
0/0

Installer

Choisissez votre 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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : openskills

How to embed Agent Skills into your own agent runtime

👤 Engineers building custom LLM agents ⏱ ~120 min advanced

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

Prérequis
  • 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
Déroulement
  1. Install the binding
    Install the openskills Python or TS binding and point it at my skills directory.✓ Copié
    → Runtime loaded; skills enumerated
  2. Expose to your agent
    Wire the runtime into my agent's planner so it considers skills at each step.✓ Copié
    → Agent has a SkillRegistry abstraction
  3. Run sandboxed
    Enable Seatbelt sandboxing for skill scripts on macOS.✓ Copié
    → Skill scripts run under sandbox profile

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

Pièges
  • 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
Combiner avec : filesystem

Run a skill in isolation to test it outside Claude Code

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

Quand l'utiliser : You want to prove your skill works without the specific harness of Claude Code.

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

Résultat : Confidence your skill behaves portably.

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

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

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.✓ Copié
openskills-skill + filesystem

Operate on the skills directory directly

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

Outils

Ce que ce MCP expose

OutilEntréesQuand appelerCoût
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

Coût et limites

Coût d'exécution

Quota d'API
none
Tokens par appel
runtime is prompt-light; you control what's disclosed
Monétaire
free, open source
Astuce
Keep progressive disclosure on — loading every script upfront blows context

Sécurité

Permissions, secrets, portée

Stockage des identifiants : none at runtime level
Sortie de données : none beyond what scripts themselves do

Dépannage

Erreurs courantes et correctifs

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.

Alternatives

openskills vs autres

AlternativeQuand l'utiliserCompromis
Claude Code native skill loaderYou're only running inside Claude CodeNo cross-agent portability

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills