renn-studio 0.6.0

package/renn/workflows/research-stage.md

@@ -0,0 +1,289 @@
+<purpose>
+Execute research at the appropriate depth level.
+Produces research.md (for Level 2-3) that informs run.md creation.
+
+Called from plan-stage.md's mandatory_research step with a depth parameter.
+
+NOTE: For comprehensive ecosystem research ("how do experts build this"), use /renn.research-stage instead, which produces RESEARCH.md.
+</purpose>
+
+<depth_levels>
+**This workflow supports three depth levels:**
+
+| Level | Name         | Time      | Output                                       | When                                      |
+| ----- | ------------ | --------- | -------------------------------------------- | ----------------------------------------- |
+| 1     | Quick Verify | 2-5 min   | No file, proceed with verified knowledge     | Single library, confirming current syntax |
+| 2     | Standard     | 15-30 min | research.md                                     | Choosing between options, new integration |
+| 3     | Deep Dive    | 1+ hour   | Detailed research.md with validation gates      | Architectural decisions, novel problems   |
+
+**Depth is determined by plan-stage.md before routing here.**
+</depth_levels>
+
+<source_hierarchy>
+**MANDATORY: Context7 BEFORE WebSearch**
+
+Claude's training data is 6-18 months stale. Always verify.
+
+1. **Context7 MCP FIRST** - Current docs, no hallucination
+2. **Official docs** - When Context7 lacks coverage
+3. **WebSearch LAST** - For comparisons and trends only
+
+See ~/.claude/renn/templates/research.md `<research_protocol>` for full protocol.
+</source_hierarchy>
+
+<process>
+
+<step name="determine_depth">
+Check the depth parameter passed from plan-stage.md:
+- `depth=verify` → Level 1 (Quick Verification)
+- `depth=standard` → Level 2 (Standard Research)
+- `depth=deep` → Level 3 (Deep Dive)
+
+Route to appropriate level workflow below.
+</step>
+
+<step name="level_1_quick_verify">
+**Level 1: Quick Verification**
+
+For: Single known library, confirming syntax/version still correct.
+
+**Process:**
+
+1. Resolve library in Context7:
+
+   ```
+   mcp__context7__resolve-library-id with libraryName: "[library]"
+   ```
+
+2. Fetch relevant docs:
+
+   ```
+   mcp__context7__get-library-docs with:
+   - context7CompatibleLibraryID: [from step 1]
+   - topic: [specific concern]
+   ```
+
+3. Verify:
+
+   - Current version matches expectations
+   - API syntax unchanged
+   - No breaking changes in recent versions
+
+4. **If verified:** Return to plan-stage.md with confirmation. No research.md needed.
+
+5. **If concerns found:** Escalate to Level 2.
+
+**Output:** Verbal confirmation to proceed, or escalation to Level 2.
+</step>
+
+<step name="level_2_standard">
+**Level 2: Standard Research**
+
+For: Choosing between options, new external integration.
+
+**Process:**
+
+1. **Identify what to discover:**
+
+   - What options exist?
+   - What are the key comparison criteria?
+   - What's our specific use case?
+
+2. **Context7 for each option:**
+
+   ```
+   For each library/framework:
+   - mcp__context7__resolve-library-id
+   - mcp__context7__get-library-docs (mode: "code" for API, "info" for concepts)
+   ```
+
+3. **Official docs** for anything Context7 lacks.
+
+4. **WebSearch** for comparisons:
+
+   - "[option A] vs [option B] {current_year}"
+   - "[option] known issues"
+   - "[option] with [our stack]"
+
+5. **Cross-verify:** Any WebSearch finding → confirm with Context7/official docs.
+
+6. **Create research.md** using ~/.claude/renn/templates/research.md structure:
+
+   - Summary with recommendation
+   - Key findings per option
+   - Code examples from Context7
+   - Confidence level (should be MEDIUM-HIGH for Level 2)
+
+7. Return to plan-stage.md.
+
+**Output:** `.renn/stages/XX-name/research.md`
+</step>
+
+<step name="level_3_deep_dive">
+**Level 3: Deep Dive (1+ hour)**
+
+For: Architectural decisions, novel problems, high-risk choices.
+
+**Process:**
+
+1. **Scope the research** using ~/.claude/renn/templates/research.md:
+
+   - Define clear scope
+   - Define include/exclude boundaries
+   - List specific questions to answer
+
+2. **Exhaustive Context7 research:**
+
+   - All relevant libraries
+   - Related patterns and concepts
+   - Multiple topics per library if needed
+
+3. **Official documentation deep read:**
+
+   - Architecture guides
+   - Best practices sections
+   - Migration/upgrade guides
+   - Known limitations
+
+4. **WebSearch for ecosystem context:**
+
+   - How others solved similar problems
+   - Production experiences
+   - Gotchas and anti-patterns
+   - Recent changes/announcements
+
+5. **Cross-verify ALL findings:**
+
+   - Every WebSearch claim → verify with authoritative source
+   - Mark what's verified vs assumed
+   - Flag contradictions
+
+6. **Create comprehensive research.md:**
+
+   - Full structure from ~/.claude/renn/templates/research.md
+   - Quality report with source attribution
+   - Confidence by finding
+   - If LOW confidence on any critical finding → add validation checkpoints
+
+7. **Confidence gate:** If overall confidence is LOW, present options before proceeding.
+
+8. Return to plan-stage.md.
+
+**Output:** `.renn/stages/XX-name/research.md` (comprehensive)
+</step>
+
+<step name="identify_unknowns">
+**For Level 2-3:** Define what we need to learn.
+
+Ask: What do we need to learn before we can plan this stage?
+
+- Technology choices?
+- Best practices?
+- API patterns?
+- Architecture approach?
+  </step>
+
+<step name="create_research_scope">
+Use ~/.claude/renn/templates/research.md.
+
+Include:
+
+- Clear research objective
+- Scoped include/exclude lists
+- Source preferences (official docs, Context7, current year)
+- Output structure for research.md
+  </step>
+
+<step name="execute_research">
+Run the research:
+- Use web search for current info
+- Use Context7 MCP for library docs
+- Prefer current year sources
+- Structure findings per template
+</step>
+
+<step name="create_research_output">
+Write `.renn/stages/XX-name/research.md`:
+- Summary with recommendation
+- Key findings with sources
+- Code examples if applicable
+- Metadata (confidence, dependencies, open questions, assumptions)
+</step>
+
+<step name="confidence_gate">
+After creating research.md, check confidence level.
+
+If confidence is LOW:
+Use AskUserQuestion:
+
+- header: "Low Confidence"
+- question: "Research confidence is LOW: [reason]. How would you like to proceed?"
+- options:
+  - "Dig deeper" - Do more research before planning
+  - "Proceed anyway" - Accept uncertainty, plan with caveats
+  - "Pause" - I need to think about this
+
+If confidence is MEDIUM:
+Inline: "Research complete (medium confidence). [brief reason]. Proceed to planning?"
+
+If confidence is HIGH:
+Proceed directly, just note: "Research complete (high confidence)."
+</step>
+
+<step name="open_questions_gate">
+If research.md has open_questions:
+
+Present them inline:
+"Open questions from research:
+
+- [Question 1]
+- [Question 2]
+
+These may affect implementation. Acknowledge and proceed? (yes / address first)"
+
+If "address first": Gather user input on questions, update research.
+</step>
+
+<step name="offer_next">
+```
+Research complete: .renn/stages/XX-name/research.md
+Recommendation: [one-liner]
+Confidence: [level]
+
+What's next?
+
+1. Discuss stage context (/renn.discuss-stage [current-stage])
+2. Create stage plan (/renn.plan-stage [current-stage])
+3. Refine research (dig deeper)
+4. Review research
+
+```
+
+NOTE: research.md is NOT committed separately. It will be committed with stage completion.
+</step>
+
+</process>
+
+<success_criteria>
+**Level 1 (Quick Verify):**
+- Context7 consulted for library/topic
+- Current state verified or concerns escalated
+- Verbal confirmation to proceed (no files)
+
+**Level 2 (Standard):**
+- Context7 consulted for all options
+- WebSearch findings cross-verified
+- research.md created with recommendation
+- Confidence level MEDIUM or higher
+- Ready to inform run.md creation
+
+**Level 3 (Deep Dive):**
+- Research scope defined
+- Context7 exhaustively consulted
+- All WebSearch findings verified against authoritative sources
+- research.md created with comprehensive analysis
+- Quality report with source attribution
+- If LOW confidence findings → validation checkpoints defined
+- Confidence gate passed
+- Ready to inform run.md creation
+</success_criteria>