Configure project-level settings (in `.autoresearch/config/`) and user-level preferences (in `~/.autoresearch/`). Supports interactive wizard and command-line modes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/airesearchorchestrator:configureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Configure project-level settings (in `.autoresearch/config/`) and user-level preferences (in `~/.autoresearch/`). Supports interactive wizard and command-line modes.
Configure project-level settings (in .autoresearch/config/) and user-level preferences (in ~/.autoresearch/). Supports interactive wizard and command-line modes.
/configure
│
├─→ Interactive mode (default)
│ ├─→ Show current settings
│ ├─→ Present configurable options
│ └─→ Guide through changes
│
└─→ Non-interactive mode
├─→ --action set: Set a specific key
├─→ --action get: Get a specific key
└─→ --action list: List all settings
# Interactive configuration
python3 scripts/configure_project.py --project-root /abs/path/to/project
# Set specific configuration
python3 scripts/configure_project.py --project-root /abs/path/to/project --action set --key max-loops --value 5
# Get specific configuration
python3 scripts/configure_project.py --project-root /abs/path/to/project --action get --key max-loops
# List all configurations
python3 scripts/configure_project.py --project-root /abs/path/to/project --action list
.autoresearch/config/orchestrator-config.yaml)| Setting | Type | Default | Description |
|---|---|---|---|
language.process_docs | string | zh-CN | Language for process documentation |
language.paper | string | en-US | Language for paper writing |
max_loops_per_phase | int | 3 | Maximum loops before escalation |
auto_proceed | bool | false | Auto-advance without human gates |
reviewer.enabled | bool | true | Enable external reviewer |
reviewer.model | string | gpt-5.4 | Reviewer model |
~/.autoresearch/user-config.yaml)| Setting | Type | Description |
|---|---|---|
author.name | string | Author name for papers |
author.email | string | Author email |
author.affiliation | string | Author affiliation |
defaults.research_type | string | Default research type |
defaults.venue | string | Default target venue |
Configure available GPU resources in ~/.autoresearch/gpu-registry.yaml:
gpus:
- id: gpu-001
name: RTX 4090
memory: 24GB
location: local
- id: gpu-002
name: A100
memory: 80GB
location: remote
host: gpu-server.example.com
┌─────────────────────────────────┐
│ Configuration Wizard │
├─────────────────────────────────┤
│ 1. Language Settings │
│ 2. Loop Limits │
│ 3. Reviewer Settings │
│ 4. GPU Configuration │
│ 5. User Preferences │
│ │
│ [q] Quit without saving │
│ [s] Save and exit │
└─────────────────────────────────┘
npx claudepluginhub jacazjx/ai-research-orchestrator --plugin airesearchorchestrator7-step setup wizard that produces a complete, ready-to-run research.md without executing the research loop. Walks the user through goal, metric, search space, constraints, evaluator design, and baseline measurement, then writes the file. TRIGGER when: user wants to set up a research project; user wants to plan before running the loop; user says "plan my research"; user has a goal but no research.md; user invokes /autoresearch:plan. DO NOT TRIGGER when: research.md already exists and the user wants to run the loop; user wants a one-shot answer; user wants to debug, not optimize.
Configures Plan-Build-Run settings: workflow depth, model profiles, features, git branching/mode, and gates. Interactive or direct args like 'depth standard' or 'feature auto_continue on'.
Queries or modifies Gran Maestro workflow settings (config.json) including feedback rounds, discussion limits, concurrency, and server options.