research
Orchestrate parallel scientist droids for comprehensive research with AUTO mode
>_
Quick Installnpxskills add merozemory/oh-my-droid--skill researchInstructions
Loading…
Orchestrate parallel scientist droids for comprehensive research with AUTO mode
npxskills add merozemory/oh-my-droid--skill researchLoading…
Orchestrate parallel scientist agents for comprehensive research workflows with optional AUTO mode for fully autonomous execution.
Research is a multi-stage workflow that decomposes complex research goals into parallel investigations:
/research <goal> # Standard research with user checkpoints
/research AUTO: <goal> # Fully autonomous until complete
/research status # Check current research session status
/research resume # Resume interrupted research session
/research list # List all research sessions
/research report <session-id> # Generate report for session
/research What are the performance characteristics of different sorting algorithms?
/research AUTO: Analyze authentication patterns in this codebase
/research How does the error handling work across the API layer?
When given a research goal, decompose into 3-7 independent stages:
## Research Decomposition
**Goal:** <original research goal>
### Stage 1: <stage-name>
- **Focus:** What this stage investigates
- **Hypothesis:** Expected finding (if applicable)
- **Scope:** Files/areas to examine
- **Tier:** LOW | MEDIUM | HIGH
### Stage 2: <stage-name>
...
Fire independent stages in parallel via Task tool:
// Stage 1 - Simple data gathering
Task(subagent_type="oh-my-droid:scientist-low", model="claude-haiku-4-5-20251001", prompt="[RESEARCH_STAGE:1] Investigate...")
// Stage 2 - Standard analysis
Task(subagent_type="oh-my-droid:scientist", model="claude-sonnet-4-5-20250929", prompt="[RESEARCH_STAGE:2] Analyze...")
// Stage 3 - Complex reasoning
Task(subagent_type="oh-my-droid:scientist-high", model="claude-opus-4-5-20251101", prompt="[RESEARCH_STAGE:3] Deep analysis of...")
CRITICAL: Always pass model parameter explicitly!
| Task Complexity | Agent | Model | Use For |
|---|---|---|---|
| Data gathering | scientist-low | haiku | File enumeration, pattern counting, simple lookups |
| Standard analysis | scientist | sonnet | Code analysis, pattern detection, documentation review |
| Complex reasoning | scientist-high | opus | Architecture analysis, cross-cutting concerns, hypothesis validation |
| Research Task | Tier | Example Prompt |
|---|---|---|
| "Count occurrences of X" | LOW | "Count all usages of useState hook" |
| "Find all files matching Y" | LOW | "List all test files in the project" |
| "Analyze pattern Z" | MEDIUM | "Analyze error handling patterns in API routes" |
| "Document how W works" | MEDIUM | "Document the authentication flow" |
| "Explain why X happens" | HIGH | "Explain why race conditions occur in the cache layer" |
| "Compare approaches A vs B" | HIGH | "Compare Redux vs Context for state management here" |
After parallel execution completes, verify findings:
// Cross-validation stage
Task(subagent_type="oh-my-droid:scientist", model="claude-sonnet-4-5-20250929", prompt="
[RESEARCH_VERIFICATION]
Cross-validate these findings for consistency:
Stage 1 findings: <summary>
Stage 2 findings: <summary>
Stage 3 findings: <summary>
Check for:
1. Contradictions between stages
2. Missing connections
3. Gaps in coverage
4. Evidence quality
Output: [VERIFIED] or [CONFLICTS:<list>]
")
AUTO mode runs the complete research workflow autonomously with loop control.
[RESEARCH + AUTO - ITERATION {{ITERATION}}/{{MAX}}]
Your previous attempt did not output the completion promise. Continue working.
Current state: {{STATE}}
Completed stages: {{COMPLETED_STAGES}}
Pending stages: {{PENDING_STAGES}}
| Tag | Meaning | When to Use |
|---|---|---|
[PROMISE:RESEARCH_COMPLETE] | Research finished successfully | All stages done, verified, report generated |
[PROMISE:RESEARCH_BLOCKED] | Cannot proceed | Missing data, access issues, circular dependency |
/cancel or "stop", "cancel"/research AUTO: Comprehensive security analysis of the authentication system
[Decomposition]
- Stage 1 (LOW): Enumerate auth-related files
- Stage 2 (MEDIUM): Analyze token handling
- Stage 3 (MEDIUM): Review session management
- Stage 4 (HIGH): Identify vulnerability patterns
- Stage 5 (MEDIUM): Document security controls
[Execution - Parallel]
Firing stages 1-3 in parallel...
Firing stages 4-5 after dependencies complete...
[Verification]
Cross-validating findings...
[Synthesis]
Generating report...
[PROMISE:RESEARCH_COMPLETE]
When stages analyze different data sources:
// All fire simultaneously
Task(subagent_type="oh-my-droid:scientist-low", model="claude-haiku-4-5-20251001", prompt="[STAGE:1] Analyze src/api/...")
Task(subagent_type="oh-my-droid:scientist-low", model="claude-haiku-4-5-20251001", prompt="[STAGE:2] Analyze src/utils/...")
Task(subagent_type="oh-my-droid:scientist-low", model="claude-haiku-4-5-20251001", prompt="[STAGE:3] Analyze src/components/...")
When testing multiple hypotheses:
// Test hypotheses simultaneously
Task(subagent_type="oh-my-droid:scientist", model="claude-sonnet-4-5-20250929", prompt="[HYPOTHESIS:A] Test if caching improves...")
Task(subagent_type="oh-my-droid:scientist", model="claude-sonnet-4-5-20250929", prompt="[HYPOTHESIS:B] Test if batching reduces...")
Task(subagent_type="oh-my-droid:scientist", model="claude-sonnet-4-5-20250929", prompt="[HYPOTHESIS:C] Test if lazy loading helps...")
When verification depends on all findings:
// Wait for all parallel stages
[stages complete]
// Then sequential verification
Task(subagent_type="oh-my-droid:scientist-high", model="claude-opus-4-5-20251101", prompt="
[CROSS_VALIDATION]
Validate consistency across all findings:
- Finding 1: ...
- Finding 2: ...
- Finding 3: ...
")
Maximum 5 concurrent scientist agents to prevent resource exhaustion.
If more than 5 stages, batch them:
Batch 1: Stages 1-5 (parallel)
[wait for completion]
Batch 2: Stages 6-7 (parallel)
.omd/research/{session-id}/
state.json # Session state and progress
stages/
stage-1.md # Stage 1 findings
stage-2.md # Stage 2 findings
...
findings/
raw/ # Raw findings from scientists
verified/ # Post-verification findings
figures/
figure-1.png # Generated visualizations
...
report.md # Final synthesized report
{
"id": "research-20240115-abc123",
"goal": "Original research goal",
"status": "in_progress | complete | blocked | cancelled",
"mode": "standard | auto",
"iteration": 3,
"maxIterations": 10,
"stages": [
{
"id": 1,
"name": "Stage name",
"tier": "LOW | MEDIUM | HIGH",
"status": "pending | running | complete | failed",
"startedAt": "ISO timestamp",
"completedAt": "ISO timestamp",
"findingsFile": "stages/stage-1.md"
}
],
"verification": {
"status": "pending | passed | failed",
"conflicts": [],
"completedAt": "ISO timestamp"
},
"createdAt": "ISO timestamp",
"updatedAt": "ISO timestamp"
}
| Command | Action |
|---|---|
/research status | Show current session progress |
/research resume | Resume most recent interrupted session |
/research resume <session-id> | Resume specific session |
/research list | List all sessions with status |
/research report <session-id> | Generate/regenerate report |
/research cancel | Cancel current session (preserves state) |
Scientists use structured tags for findings. Extract them with these patterns:
[FINDING:<id>] <title>
<evidence and analysis>
[/FINDING]
[EVIDENCE:<finding-id>]
- File: <path>
- Lines: <range>
- Content: <relevant code/text>
[/EVIDENCE]
[CONFIDENCE:<level>] # HIGH | MEDIUM | LOW
<reasoning for confidence level>
// Finding extraction
const findingPattern = /\[FINDING:(\w+)\]\s*(.*?)\n([\s\S]*?)\[\/FINDING\]/g;
// Evidence extraction
const evidencePattern = /\[EVIDENCE:(\w+)\]([\s\S]*?)\[\/EVIDENCE\]/g;
// Confidence extraction
const confidencePattern = /\[CONFIDENCE:(HIGH|MEDIUM|LOW)\]\s*(.*)/g;
// Stage completion
const stageCompletePattern = /\[STAGE_COMPLETE:(\d+)\]/;
// Verification result
const verificationPattern = /\[(VERIFIED|CONFLICTS):?(.*?)\]/;
When extracting evidence, include context window:
[EVIDENCE:F1]
- File: /src/auth/login.ts
- Lines: 45-52 (context: 40-57)
- Content:
```typescript
// Lines 45-52 with 5 lines context above/below
[/EVIDENCE]
### Quality Validation
Findings must meet quality threshold:
| Quality Check | Requirement |
|---------------|-------------|
| Evidence present | At least 1 [EVIDENCE] per [FINDING] |
| Confidence stated | Each finding has [CONFIDENCE] |
| Source cited | File paths are absolute and valid |
| Reproducible | Another agent could verify |
## Report Generation
### Report Template
```markdown
# Research Report: {{GOAL}}
**Session ID:** {{SESSION_ID}}
**Date:** {{DATE}}
**Status:** {{STATUS}}
## Executive Summary
{{2-3 paragraph summary of key findings}}
## Methodology
### Research Stages
| Stage | Focus | Tier | Status |
|-------|-------|------|--------|
{{STAGES_TABLE}}
### Approach
{{Description of decomposition rationale and execution strategy}}
## Key Findings
### Finding 1: {{TITLE}}
**Confidence:** {{HIGH|MEDIUM|LOW}}
{{Detailed finding with evidence}}
#### Evidence
{{Embedded evidence blocks}}
### Finding 2: {{TITLE}}
...
## Visualizations
{{FIGURES}}
## Cross-Validation Results
{{Verification summary, any conflicts resolved}}
## Limitations
- {{Limitation 1}}
- {{Limitation 2}}
- {{Areas not covered and why}}
## Recommendations
1. {{Actionable recommendation}}
2. {{Actionable recommendation}}
## Appendix
### Raw Data
{{Links to raw findings files}}
### Session State
{{Link to state.json}}
Scientists generate visualizations using this marker:
[FIGURE:path/to/figure.png]
Caption: Description of what the figure shows
Alt: Accessibility description
[/FIGURE]
Report generator embeds figures:
## Visualizations
*Caption: Description of what the figure shows*
*Caption: Description of what the figure shows*
| Type | Use For | Generated By |
|---|---|---|
| Architecture diagram | System structure | scientist-high |
| Flow chart | Process flows | scientist |
| Dependency graph | Module relationships | scientist |
| Timeline | Sequence of events | scientist |
| Comparison table | A vs B analysis | scientist |
Optional settings in .factory/settings.json:
{
"omd": {
"research": {
"maxIterations": 10,
"maxConcurrentScientists": 5,
"defaultTier": "MEDIUM",
"autoVerify": true,
"generateFigures": true,
"evidenceContextLines": 5
}
}
}
/cancel
Or say: "stop research", "cancel research", "abort"
Progress is preserved in .omd/research/{session-id}/ for resume.
Stuck in verification loop?
Scientists returning low-quality findings?
AUTO mode exhausted iterations?
Missing figures in report?
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).