Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/moai-alfred-agent-factory
Agent Factory master skill for intelligent Claude Code agent generation. Includes requirement analysis, domain detection, model selection, template system, validation framework, and advanced features. Contains algorithms, workflows, and patterns.
Passed 18 of 21 test cases with the skill, and 8 of 21 without it.
and 14 more in the full report
12 fixed7 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
Specify the standard template tier assigned for mid-level tasks with complexity score 5.
| Checked | Without skill | With skill |
|---|---|---|
| The generation logic selects Tier 2 standard template. | Passed | Passed |
| The expected output line count is designated within the 200 to 500 line range. | Missed | Passed |
The instructions your model reads when the skill loads.
Master Skill for Intelligent Agent Generation
Complete reference for agent-factory agent to automatically generate production-ready Claude Code sub-agents through requirement analysis, research, template generation, and validation.
Version: 1.0.0 Status: Production Ready Components: 6 core systems + advanced features
| Component | Location | Purpose |
|---|---|---|
| Intelligence Engine | reference/intelligence-engine.md | Analyze requirements → domain/capabilities/complexity |
| Research Engine | reference/research-engine.md | Context7 MCP workflow → fetch docs → extract practices |
| Template System | reference/template-system.md | 3-tier templates (Simple/Standard/Complex) + variables |
| Validation Framework | reference/validation-framework.md | 4 quality gates + test cases |
| Advanced Features | reference/advanced-features.md | Versioning, multi-domain, optimization |
| Practical Examples | examples.md | 3 main test cases + edge cases |
User Requirement
↓
[Stage 1-2] Intelligence Engine
├─ Parse requirement
├─ Detect domain (primary + secondary)
├─ Score complexity (1-10)
├─ Select model (Sonnet/Haiku/Inherit)
└─ Calculate tools & skills
↓
[Stage 3] Research Engine (Context7 MCP)
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.