devflow-kit 0.6.1 → 0.7.0

package/src/claude/skills/devflow/research/SKILL.md

@@ -6,7 +6,7 @@ allowed-tools: Task
 
 # Research Skill - Auto-Dispatcher
 
-**Purpose**: Detect when pre-implementation research is needed and auto-launch the research agent.
+**Purpose**: Detect when pre-implementation research is needed and auto-launch the brainstorm agent for exploration.
 
 ## When to Activate
 
@@ -23,8 +23,8 @@ Auto-activates when:
 ```markdown
 Quick check (don't do heavy research):
 1. Is this pattern already in codebase? → Show example
-2. Is this unfamiliar/complex? → Launch research agent
-3. Are there multiple approaches? → Launch research agent
+2. Is this unfamiliar/complex? → Launch brainstorm agent
+3. Are there multiple approaches? → Launch brainstorm agent
 ```
 
 ## Decision Logic
@@ -34,14 +34,14 @@ Quick check (don't do heavy research):
 - Similar feature already implemented
 - Just need to reference existing code
 
-**Launch research agent** (unknown):
+**Launch brainstorm agent** (unknown):
 - Unfamiliar feature or technology
 - New library integration
 - Multiple possible approaches
 - Need to study docs/examples
 - Integration strategy unclear
 
-## Auto-Launch Research Agent
+## Auto-Launch Brainstorm Agent
 
 When research is needed:
 
@@ -49,25 +49,25 @@ When research is needed:
 I've detected this requires pre-implementation research.
 
 **Feature**: [what's being implemented]
-**Unknowns**: [what we need to research]
+**Unknowns**: [what we need to explore]
 
-Launching research agent to analyze approaches and create implementation plan...
+Launching brainstorm agent to explore approaches and patterns...
 ```
 
-Then launch the research agent using Task tool:
+Then launch the brainstorm agent using Task tool:
 
 ```
 Task(
-  subagent_type="research",
-  description="Pre-implementation research",
-  prompt="Conduct comprehensive research for implementing: [feature description].
+  subagent_type="brainstorm",
+  description="Explore implementation approaches",
+  prompt="Explore implementation approaches for: [feature description].
 
-  Research focus:
-  - Evaluate implementation approaches
-  - Study official documentation and examples
-  - Analyze existing codebase patterns
-  - Design integration strategy
-  - Create actionable implementation plan
+  Focus on:
+  - What approaches exist for this problem?
+  - What are the trade-offs of each approach?
+  - What patterns are already in the codebase?
+  - What libraries/frameworks could help?
+  - What are the risks and edge cases?
 
   Context: [relevant project context]"
 )
@@ -78,13 +78,15 @@ Task(
 After agent completes, summarize key findings:
 
 ```markdown
-🔬 **Research Complete**
+**Exploration Complete**
 
-**Recommended Approach**: [chosen solution]
-**Integration Points**: [where it fits]
-**Implementation Plan**: [step-by-step]
-**Key Considerations**: [risks/trade-offs]
-**Documentation**: `.docs/research/[session-id].md`
+**Approaches Found**: [list of options]
+**Codebase Patterns**: [relevant existing patterns]
+**Recommended Direction**: [suggested approach]
+**Trade-offs**: [key considerations]
+**Documentation**: `.docs/brainstorm/[topic-slug]-[timestamp].md`
+
+**Next Step**: Run `/design` to create detailed implementation plan for chosen approach.
 ```
 
 ## Examples
@@ -99,17 +101,17 @@ Skill: "We already use this pattern. See src/api/users.ts:45
 **Example 2: Unfamiliar - Launch Agent**
 ```
 User: "Add OAuth authentication"
-Skill: "OAuth integration requires research of approaches and patterns.
-Launching research agent..."
-[Launches research agent for comprehensive analysis]
+Skill: "OAuth integration requires exploration of approaches.
+Launching brainstorm agent..."
+[Launches brainstorm agent for approach exploration]
 ```
 
 **Example 3: Multiple Approaches - Launch Agent**
 ```
 User: "Add real-time updates to dashboard"
 Skill: "Multiple approaches possible (WebSockets, SSE, polling).
-Launching research agent to evaluate options..."
-[Launches research agent]
+Launching brainstorm agent to explore options..."
+[Launches brainstorm agent]
 ```
 
 ## Quick Pattern Recognition
@@ -122,14 +124,15 @@ grep -r "similar_pattern" --include="*.ts" src/ | head -3
 ```
 
 If pattern found → Show it
-If not found → Launch agent
+If not found → Launch brainstorm agent
 
 ## Key Points
 
-- **Lightweight**: Skill does minimal checking (~20 lines)
-- **Smart dispatch**: Shows existing patterns vs researches new
-- **No heavy analysis**: Delegates comprehensive research to agent
+- **Lightweight**: Skill does minimal checking
+- **Smart dispatch**: Shows existing patterns vs explores new options
+- **Exploration focus**: Brainstorm agent explores approaches, not detailed planning
 - **Autonomous**: Auto-launches when research needed
 - **Clean context**: Main session stays focused on implementation
+- **Next step guidance**: Suggests `/design` after exploration completes
 
-This ensures thorough research happens in separate context while main session remains clean.
+This ensures thorough exploration happens in separate context while main session remains clean. For detailed implementation planning, use `/design` after exploration.