Display help and documentation for the Orion AI Research Automation System.
Displays comprehensive documentation for the Orion AI Research Automation System.
/plugin marketplace add hdubey-debug/orion/plugin install hdubey-debug-orion@hdubey-debug/orionDisplay help and documentation for the Orion AI Research Automation System.
/orion-help [topic]
overview - What is Orion?workflow - Complete research workflowcommands - Available commandsskills - Tree of Skills systemplan-mode - How Plan Mode workstroubleshooting - Common issuesWhen user invokes /orion-help, display the relevant documentation.
╔══════════════════════════════════════════════════════════════╗
║ ORION - AI Research Automation ║
╠══════════════════════════════════════════════════════════════╣
║ ║
║ Automate AI research: papers → knowledge → hypotheses → test ║
║ ║
╚══════════════════════════════════════════════════════════════╝
## Commands
| Command | Purpose |
|-------------------------|-----------------------------------|
| /orion-init | Initialize project structure |
| /knowledge | View accumulated knowledge |
| /literature-review | Read papers, extract skills |
| /benchmark-setup | Download/study benchmarks |
| /orion-setup | Clone and setup codebase |
| /hypothesis-generation | Generate hypotheses → PRD → JSON |
| /orion-help | This documentation |
## Quick Start
```bash
/orion-init "my-project"
# Place papers in research/papers/
/literature-review research/papers
/knowledge
/benchmark-setup
/hypothesis-generation --target 75.0
/ralph-loop "Test hypotheses..."
For details: /orion-help <topic>
### Topic: workflow
/orion-init "project-name"
Creates: research/ directory with skills structure
# Place PDFs in research/papers/
/literature-review research/papers
Extracts: methodology, experiments, metrics skills Uses: Plan Mode (creates plan, gets approval, executes)
/knowledge
/knowledge literature
/knowledge benchmarks
Shows: Accumulated knowledge summaries
/benchmark-setup
Downloads: Benchmark data (with permission) Creates: Benchmark skills and evaluation helpers
/orion-setup "https://github.com/author/paper-code"
Clones: Repository Verifies: Baseline reproduction
/hypothesis-generation --target 75.0 --benchmark VideoMME
Generates: Hypotheses from accumulated knowledge Creates: research-prd.md and research-prd.json
/ralph-loop "Test hypotheses in research/research-prd.json..."
Tests: Each hypothesis iteratively Documents: Learnings in skills/learned/
Papers → /literature-review → Skills
↓
/benchmark-setup → More Skills
↓
/hypothesis-generation → PRD + JSON
↓
/ralph-loop → Results + Learnings
### Topic: commands
Initialize a new Orion research project.
Creates:
Example:
/orion-init "video-understanding"
View accumulated knowledge.
Categories:
all (default) - Overview of all knowledgeliterature - Paper insightsdomain - User expertisebenchmarks - Benchmark infolearned - Experiment learningsstatus - Project progressExample:
/knowledge
/knowledge literature
Read papers and extract skills. Uses Plan Mode.
Extracts per paper:
Example:
/literature-review research/papers
Setup evaluation benchmarks. Uses Plan Mode.
Does:
Example:
/benchmark-setup
/benchmark-setup VideoMME
Clone and setup codebase. Uses Plan Mode.
Does:
Example:
/orion-setup "https://github.com/author/paper-code"
Generate hypotheses from knowledge. Uses Plan Mode.
Does:
Example:
/hypothesis-generation --target 75.0 --benchmark VideoMME
Display documentation (this command).
### Topic: skills
Orion organizes knowledge hierarchically to preserve context.
research/skills/
├── literature/ # From /literature-review
│ ├── _overview.md # Summary (always in context)
│ ├── paper_001/
│ │ ├── summary.md # Paper overview
│ │ ├── methodology.md # Core technique
│ │ ├── experiments.md # Benchmarks, setup
│ │ └── metrics.md # Evaluation methods
│ └── paper_002/
│
├── domain/ # User expertise
│ ├── _overview.md
│ └── [custom-skill].md
│
├── benchmarks/ # From /benchmark-setup
│ ├── _overview.md
│ └── [benchmark-name].md
│
└── learned/ # From experiments
├── _overview.md
└── h001_what_we_learned.md
_overview.md files are loadedExtracted from papers:
User-provided:
From setup:
From experiments:
### Topic: plan-mode
Most Orion commands use Plan Mode for user control.
Claude creates a plan
User reviews
Execution
| Command | What's Planned |
|---|---|
| /literature-review | Papers to read, skills to extract |
| /benchmark-setup | What to download, where to store |
| /orion-setup | Clone location, environment setup |
| /hypothesis-generation | Hypotheses, priority order |
| Command | Why |
|---|---|
| /orion-init | Simple directory creation |
| /knowledge | Read-only viewing |
| /orion-help | Documentation display |
### Topic: troubleshooting
Run /orion-init <project-name> first.
Claude Code can read PDFs directly. If issues:
/benchmark-setup --from-folderRun these first:
/literature-review - extract from papers/benchmark-setup - understand evaluation
Then retry /hypothesis-generationEnsure JSON format matches Ralph's expected structure:
userStories array with hypothesesid, title, acceptanceCriteriastatus field for trackingReset project:
rm -rf research/
/orion-init "project-name"
Check state:
cat research/orion.json
View all knowledge:
/knowledge status
/orion-help <topic> - specific documentation/knowledge - see what's accumulated
This is a read-only command that displays inline documentation.