sc-research
Skill19 starsChanged 8 months agoMITView on GitHub
Deep research on any topic combining real-time web search (Rube MCP) with multi-model consensus analysis (PAL MCP). Produces structured reports with sourced findings and confidence assessments.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- kreighmitchell/SuperClaudeword for word, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 1
- kreighmitchell/SuperClaude★ 4100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-data-engineerSkill
- agent-fullstack-developerSkill
- agent-kubernetes-specialistSkill
- agent-ml-engineerSkill
- agent-performance-engineerSkill
- agent-react-specialistSkill
- agent-security-engineerSkill
- agent-technical-writerSkill
- ask-multiSkill
- askSkill
- learned-skills-indexSkill
- sc-analyzeSkill
- sc-brainstormSkill
- sc-buildSkill
- sc-cicd-setupSkill
- sc-code-reviewSkill
- sc-designSkill
- sc-documentSkill
- sc-e2eSkill
- sc-estimateSkill
- sc-evaluateSkill
- sc-explainSkill
- sc-gitSkill
- sc-implementSkill
- sc-improveSkill
- sc-log-fixSkill
- sc-mcpSkill
- sc-pr-checkSkill
- sc-pr-fixSkill
- sc-principlesSkill
- sc-pushSkill
- sc-readmeSkill
- sc-tddSkill
- sc-testSkill
- sc-workflowSkill
- sc-worktreeSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 2 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 71
Use mcp__rube__RUBE_SEARCH_TOOLS to find web search and URL extraction tools:
- Very specific: line 84
If no active connection, call RUBE_MANAGE_CONNECTIONS and present auth link
- Very specific: line 86
If tools return schemaRef, call RUBE_GET_TOOL_SCHEMAS for full schemas
- Distinctive: line 94
Use specific, factual language
- Very specific: line 124
Use mcp__pal__thinkdeep for systematic analysis:
- Very specific: line 144
Call mcp__pal__listmodels.
- Very specific: line 148
Use mcp__pal__consensus with for/against/neutral stances:
- Very specific: line 243
If --output <filepath>: Write report to file, confirm path
- Distinctive: line 294
Search multiple perspectives for controversial topics
- Very specific: line 296
If Rube unavailable but PAL available, degrade to analysis-only via WebFetch
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Deep Research Skill
Conduct comprehensive research on any topic by combining real-time web search (via Rube MCP) with multi-model deep analysis and consensus synthesis (via PAL MCP). Produces structured research reports with sourced findings, cross-validated analysis, and confidence assessments.
Quick Start
# Quick overview
/sc:research "quantum computing developments" --depth shallow
# Balanced research (default)
/sc:research "Impact of AI regulation on open-source development"
# Exhaustive deep dive saved to file
/sc:research "carbon capture technologies" --depth deep --output reports/carbon.md
# More models for consensus
/sc:research "PostgreSQL vs CockroachDB for write-heavy workloads" --models 4Behavioral Flow
- Parse - Extract topic, depth, output path, model count
- Decompose - Break topic into 3-7 sub-questions for comprehensive coverage
- Discover - Find web search tools via Rube MCP
- Search - Execute web research in parallel batches
- Analyze - Deep analysis of findings via PAL ThinkDeep
- Validate - Multi-model consensus via PAL Consensus
- Report - Generate structured markdown report
- Output - Save to file or display in console
Flags
| Flag | Type | Default | Description |
--depth | string | medium | Research depth: shallow, medium, deep |
--output | string | - | Save report to file path |
--models | int | 3 | Number of models for consensus (2-5) |
Depth Levels
| Depth | Sub-questions | Searches/question | Follow-ups |
| shallow | 2-3 | 1 | 0 |
| medium | 3-5 | 1-2 | 1 per gap |
| deep | 5-7 | 2-3 | 2-3 per gap |
Phase 1: Parse and Plan
Extract topic from arguments. Decompose into sub-questions that provide comprehensive coverage when answered together.
Present research plan before proceeding:
Research Topic: <topic>
Depth: <level>
Sub-questions:
1. <sub-question>
2. <sub-question>
...
Estimated searches: ~NPhase 2: Discover Search Tools
Use mcp__rube__RUBE_SEARCH_TOOLS to find web search and URL extraction tools:
RUBE_SEARCH_TOOLS:
session: { generate_id: true }
queries:
- use_case: "search the web for information about a topic"
- use_case: "scrape and extract content from a web page URL"From the response:
- Record session_id — reuse for all subsequent Rube calls
- Check connection status for returned toolkits
- If no active connection, call
RUBE_MANAGE_CONNECTIONSand present auth link - Identify best tools for web search and URL content extraction
- If tools return
schemaRef, callRUBE_GET_TOOL_SCHEMASfor full schemas
Phase 3: Execute Web Research
Batch independent searches in parallel (up to 5 per call) via RUBE_MULTI_EXECUTE_TOOL:
Search query formulation:
- Rephrase sub-questions as effective search queries
- Use specific, factual language
- For controversial topics, search multiple perspectives explicitly
- Include date qualifiers if recency matters
After initial searches:
- Parse and collect all results
- Identify most relevant URLs
- For medium/deep: extract full content from top 3-5 URLs
- Identify information gaps
For medium/deep — follow-up searches:
- Generate refined queries targeting gaps
- Execute follow-up searches
- Extract additional URL content
Organize raw findings:
Sub-question 1: <question>
Sources:
- [Source Title](URL) - Key finding: <summary>
Gaps: <what's still unclear>
Sub-question 2: <question>
Sources:
- ...Phase 4: Deep Analysis (PAL ThinkDeep)
Use mcp__pal__thinkdeep for systematic analysis:
Step 1 — Analyze:
- Identify key themes and patterns across sources
- Flag contradictions between sources
- Assess source credibility and biases
- Identify well-supported vs. poorly-supported claims
- Note significant information gaps
- Synthesize preliminary narrative
Step 2 — Refine:
- Resolve contradictions with evidence-based reasoning
- Rank findings by confidence (high/medium/low)
- Produce structured outline for final report
- Identify 3-5 most important takeaways
Phase 5: Multi-Model Consensus (PAL Consensus)
5a. Discover Models
Call mcp__pal__listmodels. Select top N by score, preferring different providers for diversity.
5b. Run Consensus
Use mcp__pal__consensus with for/against/neutral stances:
| Stance | Purpose |
| for | Evaluate findings charitably, look for strengths |
| against | Critically evaluate, look for weaknesses and gaps |
| neutral | Balanced evaluation, weigh strengths and weaknesses |
5c. Incorporate Consensus
Synthesize:
- Areas of agreement — high confidence findings
- Areas of disagreement — flag for nuance
- Missing perspectives — gaps identified by any model
- Confidence adjustments — raise/lower based on feedback
Phase 6: Generate Report
# Deep Research Report: <Topic>
**Generated**: <date>
**Depth**: <shallow|medium|deep>
**Sources consulted**: <N>
**Models consulted**: <list>
---
## Executive Summary
<3-5 paragraph synthesis for general audience>
---
## Research Question
<Original topic and how it was decomposed>
---
## Key Findings
### Finding 1: <Title>
**Confidence**: High | Medium | Low
**Consensus**: Agreed | Mixed | Disputed
<Detailed finding with inline source citations>
**Sources**: [Source 1](url), [Source 2](url)
---
## Analysis
### Themes and Patterns
<Cross-cutting themes across sources>
### Contradictions and Debates
<Where sources/models disagreed>
### Information Gaps
<What remains unclear>
---
## Model Consensus
| Model | Stance | Confidence | Key Feedback |
|-------|--------|------------|--------------|
| <model_1> | For | X/10 | <summary> |
| <model_2> | Against | X/10 | <summary> |
| <model_3> | Neutral | X/10 | <summary> |
**Agreement Areas**: <where all models agreed>
**Divergent Views**: <where models differed>
---
## Sources
| # | Title | URL | Relevance |
|---|-------|-----|-----------|
| 1 | <title> | <url> | <contribution> |
---
## Methodology
1. **Web search** via Rube MCP (<N> searches)
2. **Deep analysis** via PAL ThinkDeep
3. **Multi-model consensus** via PAL Consensus (<N> models)Phase 7: Output
- If
--output <filepath>: Write report to file, confirm path - Otherwise: Display full report in console
End with summary:
Research complete:
- Topic: <topic>
- Sources: <N> web sources
- Models: <N> reached consensus
- Confidence: <overall assessment>
- Key takeaway: <1-sentence summary>MCP Integration
PAL MCP
| Tool | Phase | Purpose |
mcp__pal__thinkdeep | Analysis | Multi-stage hypothesis testing |
mcp__pal__consensus | Validation | Multi-model cross-validation |
mcp__pal__listmodels | Discovery | Available models for consensus |
mcp__pal__challenge | Validation | Critical thinking on controversial claims |
Rube MCP
| Tool | Phase | Purpose |
mcp__rube__RUBE_SEARCH_TOOLS | Discovery | Find search/scraping tools |
mcp__rube__RUBE_GET_TOOL_SCHEMAS | Discovery | Load full schemas if needed |
mcp__rube__RUBE_MULTI_EXECUTE_TOOL | Search | Parallel web searches |
mcp__rube__RUBE_MANAGE_CONNECTIONS | Auth | Connect search integrations |
mcp__rube__RUBE_REMOTE_BASH_TOOL | Processing | Handle large response data |
Error Handling
| Scenario | Action |
| No search tools found | Fall back to WebFetch for direct URLs |
| Connection not active | Call RUBE_MANAGE_CONNECTIONS, present auth link |
| Search returns no results | Reformulate with broader terms |
| Tool schema missing | Call RUBE_GET_TOOL_SCHEMAS first |
| PAL MCP unavailable | Skip consensus, report from web research only |
| ThinkDeep fails | Continue with raw findings |
| Rate limiting | Reduce parallel batch size to 2-3 |
Guardrails
- Present research plan before executing searches
- Preserve all source URLs for verifiability
- Search multiple perspectives for controversial topics
--depth deepcan make 15-25+ API calls — use judiciously- If Rube unavailable but PAL available, degrade to analysis-only via
WebFetch
Tool Coordination
- WebFetch - Fallback URL fetching when Rube unavailable
- Write - Save report to file
- Bash - File operations
- PAL MCP - Analysis, consensus, challenge
- Rube MCP - Web search, URL extraction
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

