research
Research domain knowledge using MCP servers (perplexity, context7, firecrawl). Gathers best practices, regulatory requirements, and competitive insights.
What this skill does
# Research Command
Research domain knowledge using MCP servers to enrich requirements elicitation.
## Usage
```bash
/requirements-elicitation:research "e-commerce checkout best practices"
/requirements-elicitation:research "GDPR compliance" --domain "user-data" --depth deep
/requirements-elicitation:research "authentication patterns" --focus regulatory
/requirements-elicitation:research "competitor features" --focus competitive
```
## Arguments
| Argument | Required | Description |
|----------|----------|-------------|
| topic | Yes | The topic to research |
| --domain | No | Domain name for organizing output |
| --depth | No | Research depth: `shallow`, `moderate`, `deep` (default: `moderate`) |
| --focus | No | Research focus: `best-practices`, `regulatory`, `competitive`, `technical`, `all` |
## Research Capabilities
### Best Practices Research
- Industry standards
- Common patterns
- Recommended approaches
- Lessons learned
### Regulatory Research
- Compliance requirements
- Legal obligations
- Industry regulations
- Audit requirements
### Competitive Research
- Competitor features
- Market standards
- Differentiation opportunities
- Feature gaps
### Technical Research
- Library capabilities
- Framework requirements
- Integration patterns
- Technology constraints
## Workflow
### Step 1: Parse Research Request
```yaml
research_request:
topic: "{from argument}"
domain: "{from --domain}"
depth: shallow|moderate|deep
focus: "{from --focus or all}"
```
### Step 2: Load Domain Research Skill
Invoke the `requirements-elicitation:domain-research` skill to load MCP patterns.
### Step 3: Execute MCP Queries
Based on focus area:
**Best Practices:**
```yaml
queries:
- server: perplexity
query: "{topic} best practices 2025"
- server: perplexity
query: "{topic} common patterns recommendations"
```
**Regulatory:**
```yaml
queries:
- server: perplexity
query: "{regulation} requirements {industry}"
- server: firecrawl
action: scrape regulatory documentation
```
**Competitive:**
```yaml
queries:
- server: firecrawl
action: search competitor features
- server: perplexity
query: "{industry} market leaders features"
```
**Technical:**
```yaml
queries:
- server: context7
action: resolve library, get docs
- server: perplexity
query: "{technology} integration requirements"
```
### Step 4: Synthesize Findings
Combine research results:
- Extract key findings
- Identify requirements implications
- Note confidence levels
- Flag items needing validation
### Step 5: Save and Report
Save to `.requirements/{domain}/research/`
Display summary of findings.
## Examples
### Best Practices Research
```bash
/requirements-elicitation:research "e-commerce checkout optimization"
```
Output:
```text
Researching: e-commerce checkout optimization
Depth: moderate
Focus: best-practices
Querying MCP servers...
[perplexity] e-commerce checkout best practices 2025
[perplexity] cart abandonment reduction techniques
Key Findings:
1. CHECKOUT FLOW
- Guest checkout reduces abandonment by 30%
- Progress indicators increase completion
- Mobile-first design essential
2. PAYMENT
- Multiple payment options required
- Saved payment methods increase conversion
- Clear security indicators build trust
3. PERFORMANCE
- Checkout should complete in < 3 steps
- Page load < 2 seconds critical
- Real-time validation reduces errors
Derived Requirements (8):
REQ-RES-001: System shall support guest checkout
REQ-RES-002: System shall display checkout progress
REQ-RES-003: System shall support multiple payment methods
REQ-RES-004: System shall complete checkout in 3 steps or fewer
... (4 more)
Confidence: MEDIUM (needs stakeholder validation)
Saved to: .requirements/checkout/research/RES-20251225-170000.yaml
```
### Regulatory Research
```bash
/requirements-elicitation:research "PCI-DSS" --focus regulatory --depth deep
```
Output:
```text
Researching: PCI-DSS compliance
Depth: deep
Focus: regulatory
Querying MCP servers...
[perplexity] PCI-DSS requirements payment processing
[perplexity] PCI-DSS 4.0 changes requirements
[firecrawl] scraping PCI Security Standards Council
Key Findings:
1. DATA PROTECTION (Requirement 3)
- Never store CVV after authorization
- Encrypt stored card data (AES-256)
- Mask PAN when displayed
2. ACCESS CONTROL (Requirement 7-8)
- Restrict access to need-to-know
- Unique IDs for each user
- MFA for administrative access
3. MONITORING (Requirement 10)
- Log all access to cardholder data
- Retain logs for 1 year minimum
- Daily log review required
4. TESTING (Requirement 11)
- Quarterly vulnerability scans
- Annual penetration testing
- Change detection mechanisms
Derived Requirements (15):
REQ-RES-001: System shall not store CVV/CVC after authorization [MUST]
REQ-RES-002: System shall encrypt stored card data using AES-256 [MUST]
REQ-RES-003: System shall mask PAN displaying only last 4 digits [MUST]
... (12 more)
Confidence: HIGH (from official documentation)
Saved to: .requirements/payment/research/RES-20251225-171500.yaml
```
### Competitive Research
```bash
/requirements-elicitation:research "inventory management software" --focus competitive
```
Output:
```text
Researching: inventory management software competitors
Depth: moderate
Focus: competitive
Querying MCP servers...
[firecrawl] searching inventory management software features
[perplexity] inventory management market leaders 2025
Competitors Analyzed:
1. CompetitorA
- Real-time inventory tracking
- Multi-warehouse support
- Barcode scanning
- Automated reorder points
2. CompetitorB
- AI demand forecasting
- Supplier management
- Integration marketplace
- Mobile app
3. CompetitorC
- Simple interface
- Low-cost option
- Basic reporting
- Limited integrations
Feature Matrix:
Feature | A | B | C | Our Need?
Real-time tracking | ✓ | ✓ | ✓ | Table stakes
Multi-warehouse | ✓ | ✓ | - | Should have
AI forecasting | - | ✓ | - | Differentiator?
Supplier management | ✓ | ✓ | - | Should have
Mobile app | ✓ | ✓ | - | Should have
Derived Requirements (10):
REQ-RES-001: System shall provide real-time inventory visibility [MUST]
REQ-RES-002: System shall support multiple warehouse locations [SHOULD]
REQ-RES-003: System shall integrate with barcode scanners [SHOULD]
... (7 more)
Confidence: LOW (based on public information)
Saved to: .requirements/inventory/research/RES-20251225-173000.yaml
```
### Technical Research
```bash
/requirements-elicitation:research "React state management" --focus technical
```
Output:
```text
Researching: React state management
Depth: moderate
Focus: technical
Querying MCP servers...
[context7] resolving react library
[context7] getting docs: state management
[perplexity] React state management patterns 2025
Key Findings:
1. BUILT-IN OPTIONS
- useState for local state
- useReducer for complex state
- Context API for global state (with caveats)
2. EXTERNAL LIBRARIES
- Redux Toolkit (complex apps)
- Zustand (simple, performant)
- Jotai (atomic state)
- React Query (server state)
3. RECOMMENDATIONS
- Start simple (useState, Context)
- Add complexity only when needed
- Separate server state from client state
Technical Constraints:
- React 18+ required for new patterns
- SSR considerations for Next.js
- Bundle size implications
Derived Requirements (5):
REQ-RES-001: System shall use React 18 or later [CONSTRAINT]
REQ-RES-002: System shall separate server state from client state [SHOULD]
REQ-RES-003: System shall minimize bundle size impact of state library [SHOULD]
... (2 more)
Confidence: MEDIUM (verify with team)
Saved to: .requirements/frontend/research/RES-20251225-174500.yaml
```
## Output Format
### Saved YAML Structure
```yaml
research_Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.