subagents AI Agent Skills

subagent-testing

196

athola

TDD-style testing methodology for skills using fresh subagent instances to prevent priming bias and validate skill effectiveness. Use when validating skill improvements, testing skill effectiveness, preventing priming bias, measuring skill impact on behavior. Do not use when implementing skills (use skill-authoring instead), creating hooks (use hook-authoring instead).

rlm-orchestrator

42

belumume

Implement RLM-style (Recursive Language Model) orchestration for complex tasks. This skill should be used when facing large context requirements, multi-part tasks that would benefit from parallel execution, or when context rot is a concern. Automatically decomposes tasks, spawns parallel subagents, aggregates results, and iterates until completion. Inspired by the RLM research paper (arXiv:2512.24601).

subagent-driven-development

15

Oimiragieo Agent Studio Subagent Driven Development

Execute plans via autonomous agents with two-stage review per task. Use for complex implementations requiring quality gates.

agent-ops

14

0xAxiom

Workflow orchestration, sub-agent architecture, and task management patterns

context-window-stewardship

1

fratilanico

Use when context window is filling up, when agent responses degrade in quality over a long session, when deciding what to load into an agent's context vs keep in files, or when designing multi-agent systems where subagents need isolated contexts. Triggers on: context full, context rot, compaction, session degradation, token limit.