KS
Killer-Skills

openskills-skill-authoring — Categories.community

v1.0.0
GitHub

About this Skill

Ideal for AI Agents like Claude, AutoGPT, and LangChain requiring advanced skill authoring capabilities with Rust runtime and TS/Python bindings. Rust runtime with TS/Python bindings for Claude Skills with progressive disclosure of skill metadata, full content and scripts/resources. Any agent can now own skills. Currently support Seatbelt and experimentally, WASM, sandboxing

Geeksfino Geeksfino
[0]
[0]
Updated: 3/4/2026

Quality Score

Top 5%
47
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add Geeksfino/openskills

Agent Capability Analysis

The openskills-skill-authoring MCP Server by Geeksfino is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Ideal for AI Agents like Claude, AutoGPT, and LangChain requiring advanced skill authoring capabilities with Rust runtime and TS/Python bindings.

Core Value

Empowers agents to create and manage skills with progressive disclosure of skill metadata, utilizing YAML frontmatter, and supporting scripts, references, and assets, all while leveraging sandboxing and optionally, WASM for secure execution.

Capabilities Granted for openskills-skill-authoring MCP Server

Authoring skills with detailed metadata and execution flows
Creating and managing skill directories with standardized structures
Experimenting with sandboxed skill execution using Seatbelt and WASM

! Prerequisites & Limits

  • Requires Rust runtime environment
  • Currently experimental support for WASM
  • Specific directory structure and file format requirements (e.g., SKILL.md, YAML frontmatter)
Project
SKILL.md
1.1 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

OpenSkills Skill Authoring

Use this skill when creating or updating skills under examples/skills or any OpenSkills-compatible skill directory.

Authoring Standard

Each skill directory should include:

  • SKILL.md (required)
  • optional scripts/, references/, assets/

SKILL.md Requirements

  • YAML frontmatter with:
    • name
    • description
  • Body with concise instructions and practical execution flow.
  • Description must include both:
    • what the skill does
    • when to activate it

Writing Guidance

  1. Keep core instructions short; move details to references/.
  2. Prefer deterministic scripts for fragile or repetitive steps.
  3. Include explicit input/output expectations.
  4. Avoid vague names and ambiguous activation phrases.

Validation Flow

  1. Ensure directory name matches skill name semantics.
  2. Verify skill discovery and activation behavior in runtime or example agent.
  3. If scripts are present, verify paths and execution assumptions.

Output Format

  • Skill metadata quality review
  • Instruction clarity review
  • Activation trigger quality review
  • Suggested revisions

Related Skills

Looking for an alternative to openskills-skill-authoring or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication