multiAI Summary Pending
project-research
Research workflow patterns specific to {project}. Covers research agent coordination, source management, and synthesis strategies.
231 stars
Installation
Claude Code / Cursor / Codex
$curl -o ~/.claude/skills/project-research/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/consiliency/project-research/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/project-research/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How project-research Compares
| Feature / Agent | project-research | Standard Approach |
|---|---|---|
| Platform Support | multi | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Research workflow patterns specific to {project}. Covers research agent coordination, source management, and synthesis strategies.
Which AI agents support this skill?
This skill is compatible with multi.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
<!-- Generated by ai-dev-kit:recommend-skills on {date} -->
<!-- This skill can be safely deleted if no longer needed -->
# {project} Research Patterns
Research workflow patterns tailored to this project's domain and research requirements.
## Variables
| Variable | Default | Description |
|----------|---------|-------------|
| MAX_SOURCES | 10 | Maximum sources to consult per research task |
| SYNTHESIS_STYLE | comprehensive | Output style: concise, comprehensive, or academic |
| REQUIRE_CITATIONS | true | Always include source citations |
## Instructions
1. Identify the research question and scope
2. Select appropriate sources based on domain
3. Coordinate research subagents if available
4. Synthesize findings with proper attribution
5. Format output according to project conventions
## Red Flags - STOP and Reconsider
If you're about to:
- Make claims without source verification
- Skip the synthesis step
- Use sources outside the approved list
**STOP** -> Verify sources -> Synthesize properly -> Then report
## Workflow
### 1. Scope Definition
Define the research scope:
- Primary question
- Related sub-questions
- Domain boundaries
- Required source types
### 2. Source Selection
Approved source types for this project:
- [TODO: Add project-specific sources]
- Web search for recent information
- Documentation for technical details
- Academic sources for foundational concepts
### 3. Research Execution
For each source type:
1. Query appropriate source
2. Extract relevant information
3. Note confidence level
4. Record citation
### 4. Synthesis
Combine findings into coherent output:
- Summarize key findings
- Highlight consensus/disagreements
- Provide confidence assessment
- List all citations
## Project-Specific Patterns
### [TODO: Add patterns discovered in this project]
Example pattern:
```markdown
### Pattern: [Name]
- **When**: [Trigger condition]
- **Do**: [Actions]
- **Output**: [Expected format]
```
## Integration
This skill integrates with:
- Research subagents in `.claude/agents/`
- BAML types for structured outputs (if applicable)
- Documentation in `ai-docs/`
## Customization
Edit this file to add project-specific:
- Approved sources
- Domain vocabulary
- Output templates
- Quality criteria