Agent skill
parallel-research
Research scope too big? This skill decomposes large questions into independent parts, spawns parallel researchers, and synthesizes findings. Essential when comprehensive research would overflow a single context window.
Install this agent skill to your Project
npx add-skill https://github.com/malhashemi/dotfiles/tree/main/dot_config/opencode/skill/parallel-research
SKILL.md
Parallel Research
Overview
When research scope is large, decompose into independent questions and spawn parallel researchers. This skill turns a single researcher into a research coordinator.
When to Use
- When research question spans multiple distinct domains
- When research would exceed context window if done sequentially
- When independent aspects can be researched concurrently
- When RPIV or Planner requests broad research coverage
Decomposition Criteria
A research question should be decomposed when:
| Criterion | Threshold | Example |
|---|---|---|
| Topic breadth | 3+ distinct areas | "Research auth, caching, AND API patterns" |
| Estimated context | >50% for single researcher | Large codebase analysis |
| Independence | Aspects don't depend on each other | Security review vs performance review |
A research question should NOT be decomposed when:
- Topics are deeply interrelated
- Sequential discovery is required (A informs B)
- Total scope fits in single context window
Decomposition Process
Step 1: Analyze Research Scope
Parse the research request to identify:
- Core questions that must be answered
- Independent aspects that can be parallelized
- Dependencies between aspects (if any)
Step 2: Design Research Questions
For each independent aspect, create a focused research question:
## Research Question: [Aspect Name]
**Focus**: [Specific scope - what to research]
**Boundaries**: [What NOT to research - stay focused]
**Output**: [Expected deliverable format]
**Context needed**: [What context to provide]
Step 3: Spawn Parallel Researchers
Use the Task tool to spawn researchers:
task({
subagent_type: "researcher",
description: "Research [aspect name]",
prompt: "Research Question: [question]
Focus: [scope]
Boundaries: [limits]
Output format: [expected format]
Return findings as structured Markdown with file:line references."
})
Spawn all independent researchers simultaneously by issuing multiple Task calls in parallel.
Step 4: Collect Results
As each researcher returns:
- Validate the response addresses the question
- Extract key findings
- Note any cross-references or dependencies discovered
Step 5: Synthesize Findings
Combine all research into a unified output:
# Research Synthesis: [Original Topic]
## Executive Summary
[High-level findings across all research tracks]
## Detailed Findings
### [Aspect 1 Name]
[Synthesized findings from Researcher 1]
- Key discovery 1 (file:line)
- Key discovery 2 (file:line)
### [Aspect 2 Name]
[Synthesized findings from Researcher 2]
- Key discovery 1 (file:line)
- Key discovery 2 (file:line)
## Cross-Cutting Themes
[Patterns or connections discovered across research tracks]
## Recommendations
[Actionable next steps based on findings]
## References
[All file:line references from all researchers]
Output to Parent
When research is complete, return to orchestrator (RPIV or Planner):
RESEARCH_COMPLETE
Topics researched: N
Key findings:
- [Finding 1]
- [Finding 2]
Full synthesis: [path to research doc]
Error Handling
- Researcher fails: Continue with other researchers, note gap in synthesis
- Context overflow in child: Accept partial findings, note limitation
- Conflicting findings: Document both perspectives, flag for human review
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
phase-execution
Your bulletproof guide to executing implementation phases! Handles commits, detects when phases are too big, and knows when to bail cleanly. Load this whenever you're implementing a phase - it provides clean commit protocol and signals the orchestrator when things go sideways.
plan-review
Catch oversized phases BEFORE implementation begins! This skill reviews plans for sizing, dependencies, and completeness - flagging phases that need decomposition before a single line of code is written. Load this when validating plans pre-implementation.
brand-palette
Brand color discovery and palette generation skill. This skill should be used when helping users create brand color palettes, design systems, or Tailwind color configs. It guides through hue selection (RYB color wheel), chroma/tone decisions, and generates Obsidian-compatible palette reports with APCA accessibility validation. Supports starting from hex color or OKLCH values for refinement workflows. Triggers: "brand colors", "palette", "color scheme", "design system colors", "Tailwind colors", "generate palette from hex", "generate palette from OKLCH", or when users describe brand values that imply color decisions.
pr-review-orchestration
Automated PR review cycle for RPIV orchestration. Waits for Gemini reviews, assesses feedback, implements fixes, and manages the review loop. Used by Planner agent after RPIV opens PRs. This skill is triggered automatically by RPIV when entering the PR Review phase.
pr-review
This skill provides a complete workflow for handling GitHub Pull Request reviews, specifically optimized for @gemini-code-assist automated reviews. This skill should be used when addressing PR review comments, responding to reviewers, resolving threads, requesting re-reviews, or merging PRs after feedback is addressed. Triggers include: /pr-review command, "address PR feedback", "handle review comments", "respond to gemini", or any PR review lifecycle management request.
plan-validation
Validates implementation plan execution by verifying success criteria and identifying deviations. This skill should be used after a phase or plan has been implemented and committed. It runs automated checks (tests, types, lint), compares actual changes against the plan's specifications, and generates a validation report documenting what was completed, what deviated, and what needs manual testing.
Didn't find tool you were looking for?