KS
Killer-Skills

onboard — Categories.community

v1.0.0
GitHub

About this Skill

Ideal for Knowledge Retrieval Agents requiring comprehensive onboarding processes through markdown files like agents.md, onboarding.md, and README.md. Repo for Q/A MAS tool in VSC Codex

MykolaPinchuk MykolaPinchuk
[0]
[0]
Updated: 3/1/2026

Quality Score

Top 5%
18
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add MykolaPinchuk/QAMAS/onboard

Agent Capability Analysis

The onboard MCP Server by MykolaPinchuk 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 Knowledge Retrieval Agents requiring comprehensive onboarding processes through markdown files like agents.md, onboarding.md, and README.md.

Core Value

Enables agents to perform bounded discovery of up to 10 additional files, such as repo_workflow.md and QAMAS_PRD.md, facilitating efficient knowledge acquisition through markdown file analysis and VSC Codex integration.

Capabilities Granted for onboard MCP Server

Onboarding new agents through automated markdown file reading
Identifying essential files for knowledge acquisition using bounded discovery
Streamlining agent workflow by focusing on critical files like HANDOFF.md and REPO_MAP.md

! Prerequisites & Limits

  • Requires access to specific markdown files
  • Limited to reading up to 10 additional files during bounded discovery
  • Dependent on VSC Codex for repository workflow
Project
SKILL.md
803 B
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

When invoked (or when the user says Onboard), do this exactly:

  1. Read (in order, if present):
  • agents.md (if not already in context)
  • repo_workflow.md
  • onboarding.md
  • HANDOFF.md
  • REPO_MAP.md
  • a2a_notes.md
  • README.md (focus on "For agents")
  • QAMAS_PRD.md
  • QAMAS_IMPLEMENTATION.md
  1. Bounded discovery:
  • Identify up to 10 additional files needed for the current slice.
  • Print the list (file path + 1-line reason each).
  • Open only those files after listing them.
  • Do not perform broad repo scans.
  1. Output contract:
  • 5 bullets: current state summary
  • 3 options: next slice choices (each 1-2 bullets)
  • files read (including the bounded discovery list)
  • unknowns/risks (<= 5 bullets)
  1. Log:
  • Append an entry to agent_logs/current.md with intent and next steps.

Related Skills

Looking for an alternative to onboard 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