intersystems-ready-hackathon/ready-2026-team-09/ai-hub-subagents-and-skills
Claude Code and agent skill by intersystems-ready-hackathon/ready-2026-team-09
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Use when decomposing work with nested agents, %AI.SubAgent, DelegateTask-style delegation, or reusable %AI.Skill definitions that can be exported, loaded, and registered as discoverable tools.
Install
npx vskill@latest install intersystems-ready-hackathon/ready-2026-team-09/ai-hub-subagents-and-skillsSKILL.md
AI Hub SubAgents and Skills
Use this skill when the problem is decomposition: programmatic sub-agents, nested-agent workflows, or reusable %AI.Skill definitions.
When to Use
- Deciding between
%AI.SubAgentand%AI.Skill - Implementing delegate-task or recursive-agent patterns
- Exporting or loading skills from external
SKILL.mdsources - Building a parent agent that hands specialized work to child agents
Core Workflow
- Decide whether the child capability should be programmatic, reusable, or externally shareable.
- Use
%AI.SubAgentwhen the parent controls creation directly in code. - Use
%AI.Skillwhen the capability should be a discoverable tool with metadata and optional tool dependencies. - Register the child capability with the parent agent.
- Keep cost and latency in mind when nesting calls.
Critical Rules
%AI.SubAgentis the simple programmatic path.%AI.Skillis the structured, reusable, shareable path.- Delegate-task tools are an implementation pattern, not the only way to do nested agents.
- Pair this skill with
ai-hub-toolsetswhen the child agent needs its own tool surface.
Common Mistakes
- Treating
%AI.Skillas just a prompt snippet instead of a tool-registerable sub-agent - Using nested delegation without a clear reason to split the work
- Ignoring the extra model calls and latency that come with each delegated step
- Assuming external
SKILL.mdloading behaves like a plain local class without validation
References
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/ai-hub-subagents-and-skills/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/intersystems-ready-hackathon/ready-2026-team-09/ai-hub-subagents-and-skills)