feat(gsd): add research-phase for niche domain ecosystem discovery
- Add /gsd:research-phase command for comprehensive ecosystem research - Rename FINDINGS.md → DISCOVERY.md for clarity - Rename research-phase.md → discovery-phase.md (shallow "which library") - New research-phase.md for deep "how experts build this" research - Creates RESEARCH.md with stack, patterns, pitfalls, don't-hand-roll - plan-phase loads RESEARCH.md when present 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
293
get-shit-done/workflows/discovery-phase.md
Normal file
293
get-shit-done/workflows/discovery-phase.md
Normal file
@@ -0,0 +1,293 @@
|
||||
<purpose>
|
||||
Execute discovery at the appropriate depth level.
|
||||
Produces DISCOVERY.md (for Level 2-3) that informs PLAN.md creation.
|
||||
|
||||
Called from plan-phase.md's mandatory_discovery step with a depth parameter.
|
||||
|
||||
NOTE: For comprehensive ecosystem research ("how do experts build this"), use /gsd:research-phase 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 | DISCOVERY.md | Choosing between options, new integration |
|
||||
| 3 | Deep Dive | 1+ hour | Detailed DISCOVERY.md with validation gates | Architectural decisions, novel problems |
|
||||
|
||||
**Depth is determined by plan-phase.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/get-shit-done/templates/discovery.md `<discovery_protocol>` for full protocol.
|
||||
</source_hierarchy>
|
||||
|
||||
<process>
|
||||
|
||||
<step name="determine_depth">
|
||||
Check the depth parameter passed from plan-phase.md:
|
||||
- `depth=verify` → Level 1 (Quick Verification)
|
||||
- `depth=standard` → Level 2 (Standard Discovery)
|
||||
- `depth=deep` → Level 3 (Deep Dive)
|
||||
|
||||
Route to appropriate level workflow below.
|
||||
</step>
|
||||
|
||||
<step name="level_1_quick_verify">
|
||||
**Level 1: Quick Verification (2-5 minutes)**
|
||||
|
||||
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-phase.md with confirmation. No DISCOVERY.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 Discovery (15-30 minutes)**
|
||||
|
||||
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. **Quality check:** Before finalizing findings, consult ~/.claude/get-shit-done/references/research-pitfalls.md to avoid common research gaps.
|
||||
|
||||
7. **Create DISCOVERY.md** using ~/.claude/get-shit-done/templates/discovery.md structure:
|
||||
|
||||
- Summary with recommendation
|
||||
- Key findings per option
|
||||
- Code examples from Context7
|
||||
- Confidence level (should be MEDIUM-HIGH for Level 2)
|
||||
|
||||
8. Return to plan-phase.md.
|
||||
|
||||
**Output:** `.planning/phases/XX-name/DISCOVERY.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 discovery** using ~/.claude/get-shit-done/templates/discovery.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. **Quality check:** Before finalizing findings, consult ~/.claude/get-shit-done/references/research-pitfalls.md to ensure comprehensive coverage and avoid common research gaps.
|
||||
|
||||
7. **Create comprehensive DISCOVERY.md:**
|
||||
|
||||
- Full structure from ~/.claude/get-shit-done/templates/discovery.md
|
||||
- Quality report with source attribution
|
||||
- Confidence by finding
|
||||
- If LOW confidence on any critical finding → add validation checkpoints
|
||||
|
||||
8. **Confidence gate:** If overall confidence is LOW, present options before proceeding.
|
||||
|
||||
9. Return to plan-phase.md.
|
||||
|
||||
**Output:** `.planning/phases/XX-name/DISCOVERY.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 phase?
|
||||
|
||||
- Technology choices?
|
||||
- Best practices?
|
||||
- API patterns?
|
||||
- Architecture approach?
|
||||
</step>
|
||||
|
||||
<step name="create_discovery_scope">
|
||||
Use ~/.claude/get-shit-done/templates/discovery.md.
|
||||
|
||||
Include:
|
||||
|
||||
- Clear discovery objective
|
||||
- Scoped include/exclude lists
|
||||
- Source preferences (official docs, Context7, current year)
|
||||
- Output structure for DISCOVERY.md
|
||||
</step>
|
||||
|
||||
<step name="execute_discovery">
|
||||
Run the discovery:
|
||||
- Use web search for current info
|
||||
- Use Context7 MCP for library docs
|
||||
- Prefer current year sources
|
||||
- Structure findings per template
|
||||
</step>
|
||||
|
||||
<step name="create_discovery_output">
|
||||
Write `.planning/phases/XX-name/DISCOVERY.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 DISCOVERY.md, check confidence level.
|
||||
|
||||
If confidence is LOW:
|
||||
Use AskUserQuestion:
|
||||
|
||||
- header: "Low Confidence"
|
||||
- question: "Discovery 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: "Discovery complete (medium confidence). [brief reason]. Proceed to planning?"
|
||||
|
||||
If confidence is HIGH:
|
||||
Proceed directly, just note: "Discovery complete (high confidence)."
|
||||
</step>
|
||||
|
||||
<step name="open_questions_gate">
|
||||
If DISCOVERY.md has open_questions:
|
||||
|
||||
Present them inline:
|
||||
"Open questions from discovery:
|
||||
|
||||
- [Question 1]
|
||||
- [Question 2]
|
||||
|
||||
These may affect implementation. Acknowledge and proceed? (yes / address first)"
|
||||
|
||||
If "address first": Gather user input on questions, update discovery.
|
||||
</step>
|
||||
|
||||
<step name="offer_next">
|
||||
```
|
||||
Discovery complete: .planning/phases/XX-name/DISCOVERY.md
|
||||
Recommendation: [one-liner]
|
||||
Confidence: [level]
|
||||
|
||||
What's next?
|
||||
|
||||
1. Discuss phase context (/gsd:discuss-phase [current-phase])
|
||||
2. Create phase plan (/gsd:plan-phase [current-phase])
|
||||
3. Refine discovery (dig deeper)
|
||||
4. Review discovery
|
||||
|
||||
```
|
||||
|
||||
NOTE: DISCOVERY.md is NOT committed separately. It will be committed with phase 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
|
||||
- DISCOVERY.md created with recommendation
|
||||
- Confidence level MEDIUM or higher
|
||||
- Ready to inform PLAN.md creation
|
||||
|
||||
**Level 3 (Deep Dive):**
|
||||
- Discovery scope defined
|
||||
- Context7 exhaustively consulted
|
||||
- All WebSearch findings verified against authoritative sources
|
||||
- DISCOVERY.md created with comprehensive analysis
|
||||
- Quality report with source attribution
|
||||
- If LOW confidence findings → validation checkpoints defined
|
||||
- Confidence gate passed
|
||||
- Ready to inform PLAN.md creation
|
||||
</success_criteria>
|
||||
@@ -142,7 +142,7 @@ fi
|
||||
|
||||
When creating decimal phases, mark them as "(INSERTED)" in roadmap entries.
|
||||
|
||||
Read any existing PLAN.md or FINDINGS.md in the phase directory.
|
||||
Read any existing PLAN.md or DISCOVERY.md in the phase directory.
|
||||
</step>
|
||||
|
||||
<step name="mandatory_discovery">
|
||||
@@ -184,11 +184,11 @@ cat package.json 2>/dev/null | grep -A5 '"dependencies"'
|
||||
→ If ALL work follows established codebase patterns: SKIP discovery, proceed to planning
|
||||
→ If ANY external dependency, new library, or API integration: Continue to Level 1+
|
||||
↓
|
||||
Does fresh FINDINGS.md exist?
|
||||
Does fresh DISCOVERY.md exist?
|
||||
─────────────────────────────────────
|
||||
|
||||
```bash
|
||||
ls .planning/phases/XX-name/FINDINGS.md 2>/dev/null
|
||||
ls .planning/phases/XX-name/DISCOVERY.md 2>/dev/null
|
||||
```
|
||||
|
||||
If exists, check freshness:
|
||||
@@ -197,7 +197,7 @@ If exists, check freshness:
|
||||
- Fast-moving APIs (Stripe, OpenAI, etc.): Valid for 7 days
|
||||
- Check file date vs today
|
||||
|
||||
→ If fresh FINDINGS.md exists covering this phase's topics: SKIP discovery, use existing
|
||||
→ If fresh DISCOVERY.md exists covering this phase's topics: SKIP discovery, use existing
|
||||
→ If missing or stale: Continue to determine depth
|
||||
↓
|
||||
Determine Discovery Depth
|
||||
@@ -215,7 +215,7 @@ Action:
|
||||
|
||||
1. Context7: mcp**context7**resolve-library-id → mcp**context7**get-library-docs
|
||||
2. Verify current version/API matches expectations
|
||||
3. No FINDINGS.md needed - proceed with confirmed knowledge
|
||||
3. No DISCOVERY.md needed - proceed with confirmed knowledge
|
||||
|
||||
**LEVEL 2 - Standard Research (15-30 min):**
|
||||
Use when:
|
||||
@@ -226,9 +226,9 @@ Use when:
|
||||
|
||||
Action:
|
||||
|
||||
1. Route to workflows/research-phase.md with depth=standard
|
||||
2. Produces FINDINGS.md with recommendation
|
||||
3. Return here after FINDINGS.md created
|
||||
1. Route to workflows/discovery-phase.md with depth=standard
|
||||
2. Produces DISCOVERY.md with recommendation
|
||||
3. Return here after DISCOVERY.md created
|
||||
|
||||
**LEVEL 3 - Deep Dive (1+ hour):**
|
||||
Use when:
|
||||
@@ -240,10 +240,12 @@ Use when:
|
||||
|
||||
Action:
|
||||
|
||||
1. Route to workflows/research-phase.md with depth=deep
|
||||
2. Full research with cross-verification
|
||||
3. FINDINGS.md with detailed rationale and validation checkpoints
|
||||
4. Return here after FINDINGS.md created
|
||||
1. Route to workflows/discovery-phase.md with depth=deep
|
||||
2. Full discovery with cross-verification
|
||||
3. DISCOVERY.md with detailed rationale and validation checkpoints
|
||||
4. Return here after DISCOVERY.md created
|
||||
|
||||
**NOTE:** For niche/complex domains (3D, games, audio, shaders, ML), consider using `/gsd:research-phase` BEFORE plan-phase. This produces comprehensive RESEARCH.md with ecosystem knowledge that goes beyond "which library" to "how do experts build this."
|
||||
|
||||
```
|
||||
</discovery_decision_tree>
|
||||
@@ -268,7 +270,7 @@ Action:
|
||||
**Discovery can be skipped (Level 0) ONLY when ALL true:**
|
||||
□ Pattern already exists in codebase (grep confirms)
|
||||
□ No new external dependencies
|
||||
□ Fresh FINDINGS.md exists (if external deps involved)
|
||||
□ Fresh DISCOVERY.md exists (if external deps involved)
|
||||
□ Pure internal refactoring or feature extension
|
||||
□ Using established project conventions only
|
||||
|
||||
@@ -294,7 +296,7 @@ Discovery assessment:
|
||||
- Roadmap flag: [Likely / Unlikely] ([reason from roadmap])
|
||||
- Roadmap topics: [topics if flagged, or N/A]
|
||||
- New external dependencies: [yes/no - list them]
|
||||
- Existing FINDINGS.md: [yes (date) / no]
|
||||
- Existing DISCOVERY.md: [yes (date) / no]
|
||||
- Codebase patterns exist: [yes/no]
|
||||
|
||||
Discovery depth: [Level 0 (skip) / Level 1 (verify) / Level 2 (standard) / Level 3 (deep)]
|
||||
@@ -380,18 +382,38 @@ For this specific phase, understand:
|
||||
- What's the phase goal? (from roadmap)
|
||||
- What exists already? (scan codebase if mid-project)
|
||||
- What dependencies are met? (previous phases complete?)
|
||||
- Any research findings? (FINDINGS.md)
|
||||
- Any phase context? ({phase}-CONTEXT.md)
|
||||
- Any ecosystem research? (RESEARCH.md from /gsd:research-phase)
|
||||
- Any discovery findings? (DISCOVERY.md from mandatory discovery)
|
||||
- Any phase context? ({phase}-CONTEXT.md from /gsd:discuss-phase)
|
||||
|
||||
```bash
|
||||
# If mid-project, understand current state
|
||||
ls -la src/ 2>/dev/null
|
||||
cat package.json 2>/dev/null | head -20
|
||||
|
||||
# Check for comprehensive ecosystem research (created by /gsd:research-phase)
|
||||
cat .planning/phases/XX-name/${PHASE}-RESEARCH.md 2>/dev/null
|
||||
|
||||
# Check for phase-specific context (created by /gsd:discuss-phase)
|
||||
cat .planning/phases/XX-name/${PHASE}-CONTEXT.md 2>/dev/null
|
||||
```
|
||||
|
||||
**If {phase}-RESEARCH.md exists:**
|
||||
This file contains comprehensive ecosystem research for niche/complex domains. It captures:
|
||||
- Standard stack (libraries, versions, why they're standard)
|
||||
- Architecture patterns (how experts structure this type of project)
|
||||
- Don't hand-roll list (problems with existing solutions - use libraries instead)
|
||||
- Common pitfalls (mistakes to avoid)
|
||||
- Code examples (verified patterns from authoritative sources)
|
||||
|
||||
**You MUST use this research to inform your planning:**
|
||||
|
||||
- `<standard_stack>` → use these libraries, don't pick alternatives without reason
|
||||
- `<architecture_patterns>` → follow these patterns in task structure
|
||||
- `<dont_hand_roll>` → NEVER create custom solutions for listed problems
|
||||
- `<common_pitfalls>` → inform verification criteria, add warnings to task actions
|
||||
- `<code_examples>` → reference in task actions when applicable
|
||||
|
||||
**If {phase}-CONTEXT.md exists:**
|
||||
This file contains the user's input gathered through pre-planning questions. It captures their intent, preferences, constraints, and decisions BEFORE you plan.
|
||||
|
||||
@@ -405,8 +427,9 @@ This file contains the user's input gathered through pre-planning questions. It
|
||||
- `<decisions_needed>` → resolve during task breakdown or flag as checkpoints
|
||||
- `<notes>` → user clarifications that override assumptions
|
||||
|
||||
**If {phase}-CONTEXT.md does NOT exist:**
|
||||
Suggest running `/gsd:discuss-phase {phase}` first to gather context, OR proceed with roadmap description only (less informed planning).
|
||||
**If neither RESEARCH.md nor CONTEXT.md exist:**
|
||||
For niche domains (3D, games, audio, shaders, etc.), suggest `/gsd:research-phase {phase}` first.
|
||||
For simpler domains, suggest `/gsd:discuss-phase {phase}` or proceed with roadmap description only.
|
||||
|
||||
</step>
|
||||
|
||||
@@ -646,8 +669,11 @@ Output: [What artifacts will be created by this plan]
|
||||
@.planning/ROADMAP.md
|
||||
@.planning/STATE.md
|
||||
|
||||
[If research done:]
|
||||
@.planning/phases/XX-name/FINDINGS.md
|
||||
[If comprehensive ecosystem research exists (from /gsd:research-phase):]
|
||||
@.planning/phases/XX-name/{phase}-RESEARCH.md
|
||||
|
||||
[If discovery done (from mandatory discovery):]
|
||||
@.planning/phases/XX-name/DISCOVERY.md
|
||||
|
||||
[If phase context exists (from /gsd:discuss-phase):]
|
||||
@.planning/phases/XX-name/{phase}-CONTEXT.md
|
||||
@@ -777,18 +803,20 @@ Tasks are instructions for Claude, not Jira tickets.
|
||||
Phase planning is complete when:
|
||||
- [ ] STATE.md read and project history absorbed
|
||||
- [ ] **Mandatory discovery completed** (Level 0-3 as appropriate)
|
||||
- [ ] If Level 2-3: FINDINGS.md exists with current context
|
||||
- [ ] If Level 2-3: DISCOVERY.md exists with current context
|
||||
- [ ] If Level 1: Quick verification performed via Context7
|
||||
- [ ] If RESEARCH.md exists: ecosystem knowledge incorporated into plan
|
||||
- [ ] Prior decisions, issues, and concerns synthesized
|
||||
- [ ] One or more PLAN files exist with XML structure ({phase}-{plan}-PLAN.md)
|
||||
- [ ] Each plan has: Objective, context, tasks, verification, success criteria, output
|
||||
- [ ] @context references included (including STATE.md, FINDINGS.md if exists, relevant prior summaries)
|
||||
- [ ] @context references included (including STATE.md, RESEARCH.md if exists, DISCOVERY.md if exists, relevant prior summaries)
|
||||
- [ ] Prior decisions documented in context section
|
||||
- [ ] Deferred issues being addressed are noted
|
||||
- [ ] Each plan has 2-3 tasks (scoped to ~50% context)
|
||||
- [ ] Each task has: Type, Files (if auto), Action, Verify, Done
|
||||
- [ ] Checkpoints identified and properly structured
|
||||
- [ ] Tasks are specific enough for Claude to execute
|
||||
- [ ] If RESEARCH.md exists: "don't hand-roll" items are NOT being custom-built
|
||||
- [ ] If multiple plans: logical split by subsystem/dependency/complexity
|
||||
- [ ] User knows next steps
|
||||
</success_criteria>
|
||||
|
||||
@@ -1,293 +1,416 @@
|
||||
<purpose>
|
||||
Execute discovery/research at the appropriate depth level.
|
||||
Produces FINDINGS.md (for Level 2-3) that informs PLAN.md creation.
|
||||
Comprehensive research on HOW to implement a phase before planning.
|
||||
|
||||
Called from plan-phase.md's mandatory_discovery step with a depth parameter.
|
||||
Triggered by /gsd:research-phase command when the domain is niche, complex, or Claude's training is likely stale.
|
||||
|
||||
Produces RESEARCH.md with ecosystem knowledge that informs quality planning - not just "which library" but "how do experts build this."
|
||||
</purpose>
|
||||
|
||||
<depth_levels>
|
||||
**This workflow supports three depth levels:**
|
||||
<when_to_use>
|
||||
**This workflow is for domains where Claude fails without research:**
|
||||
- 3D graphics (Three.js, Babylon.js, procedural generation, level design)
|
||||
- Game development (physics engines, collision, AI, ECS patterns)
|
||||
- Audio/music (Web Audio, DSP, synthesis, MIDI)
|
||||
- Shaders (GLSL, Metal, ISF, compute shaders)
|
||||
- ML/AI integration (model serving, inference, vector DBs)
|
||||
- Real-time systems (WebSockets, WebRTC, CRDT sync)
|
||||
- Specialized frameworks with active ecosystems Claude may not know
|
||||
|
||||
| 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 | FINDINGS.md | Choosing between options, new integration |
|
||||
| 3 | Deep Dive | 1+ hour | Detailed FINDINGS.md with validation gates | Architectural decisions, novel problems |
|
||||
**Skip this for commodity domains:**
|
||||
- Standard auth (JWT, OAuth)
|
||||
- CRUD APIs
|
||||
- Forms and validation
|
||||
- Well-documented integrations (Stripe, SendGrid)
|
||||
</when_to_use>
|
||||
|
||||
**Depth is determined by plan-phase.md before routing here.**
|
||||
</depth_levels>
|
||||
<key_insight>
|
||||
The current "mandatory discovery" in plan-phase asks: "Which library should I use?"
|
||||
|
||||
<source_hierarchy>
|
||||
**MANDATORY: Context7 BEFORE WebSearch**
|
||||
This workflow asks: "What do I not know that I don't know?"
|
||||
|
||||
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/get-shit-done/templates/research-prompt.md `<source_hierarchy>` for full protocol.
|
||||
</source_hierarchy>
|
||||
For niche domains, the question isn't library selection - it's:
|
||||
- What's the established architecture pattern?
|
||||
- What libraries form the standard stack?
|
||||
- What problems do people commonly hit?
|
||||
- What's SOTA vs what Claude thinks is SOTA?
|
||||
- What should NOT be hand-rolled?
|
||||
</key_insight>
|
||||
|
||||
<process>
|
||||
|
||||
<step name="determine_depth">
|
||||
Check the depth parameter passed from plan-phase.md:
|
||||
- `depth=verify` → Level 1 (Quick Verification)
|
||||
- `depth=standard` → Level 2 (Standard Research)
|
||||
- `depth=deep` → Level 3 (Deep Dive)
|
||||
<step name="validate_phase" priority="first">
|
||||
Phase number: $ARGUMENTS (required)
|
||||
|
||||
Route to appropriate level workflow below.
|
||||
</step>
|
||||
Validate phase exists in roadmap:
|
||||
|
||||
<step name="level_1_quick_verify">
|
||||
**Level 1: Quick Verification (2-5 minutes)**
|
||||
|
||||
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-phase.md with confirmation. No FINDINGS.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 (15-30 minutes)**
|
||||
|
||||
For: Choosing between options, new external integration.
|
||||
|
||||
**Process:**
|
||||
|
||||
1. **Identify what to research:**
|
||||
|
||||
- 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. **Quality check:** Before finalizing findings, consult ~/.claude/get-shit-done/references/research-pitfalls.md to avoid common research gaps.
|
||||
|
||||
7. **Create FINDINGS.md** using ~/.claude/get-shit-done/templates/research-prompt.md structure:
|
||||
|
||||
- Summary with recommendation
|
||||
- Key findings per option
|
||||
- Code examples from Context7
|
||||
- Confidence level (should be MEDIUM-HIGH for Level 2)
|
||||
|
||||
8. Return to plan-phase.md.
|
||||
|
||||
**Output:** `.planning/phases/XX-name/FINDINGS.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/get-shit-done/templates/research-prompt.md:
|
||||
|
||||
- Create RESEARCH.md with 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. **Quality check:** Before finalizing findings, consult ~/.claude/get-shit-done/references/research-pitfalls.md to ensure comprehensive coverage and avoid common research gaps.
|
||||
|
||||
7. **Create comprehensive FINDINGS.md:**
|
||||
|
||||
- Full structure from ~/.claude/get-shit-done/templates/research-prompt.md
|
||||
- Quality report with source attribution
|
||||
- Confidence by finding
|
||||
- If LOW confidence on any critical finding → add validation checkpoints
|
||||
|
||||
8. **Confidence gate:** If overall confidence is LOW, present options before proceeding.
|
||||
|
||||
9. Return to plan-phase.md.
|
||||
|
||||
**Output:** `.planning/phases/XX-name/FINDINGS.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 phase?
|
||||
|
||||
- Technology choices?
|
||||
- Best practices?
|
||||
- API patterns?
|
||||
- Architecture approach?
|
||||
</step>
|
||||
|
||||
<step name="create_research_prompt">
|
||||
Use ~/.claude/get-shit-done/templates/research-prompt.md.
|
||||
Write to `.planning/phases/XX-name/RESEARCH.md`
|
||||
|
||||
Include:
|
||||
|
||||
- Clear research objective
|
||||
- Scoped include/exclude lists
|
||||
- Source preferences (official docs, Context7, current year)
|
||||
- Output structure for FINDINGS.md
|
||||
</step>
|
||||
|
||||
<step name="execute_research">
|
||||
Run the research prompt:
|
||||
- Use web search for current info
|
||||
- Use Context7 MCP for library docs
|
||||
- Prefer current year sources
|
||||
- Structure findings per template
|
||||
</step>
|
||||
|
||||
<step name="create_findings">
|
||||
Write `.planning/phases/XX-name/FINDINGS.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 FINDINGS.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 FINDINGS.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 findings.
|
||||
</step>
|
||||
|
||||
<step name="offer_next">
|
||||
```bash
|
||||
if [ -f .planning/ROADMAP.md ]; then
|
||||
grep -A5 "Phase ${PHASE}:" .planning/ROADMAP.md
|
||||
fi
|
||||
```
|
||||
Research complete: .planning/phases/XX-name/FINDINGS.md
|
||||
Recommendation: [one-liner]
|
||||
Confidence: [level]
|
||||
|
||||
**If phase not found:**
|
||||
```
|
||||
Error: Phase ${PHASE} not found in roadmap.
|
||||
|
||||
Use /gsd:progress to see available phases.
|
||||
```
|
||||
Exit workflow.
|
||||
|
||||
**If phase found:**
|
||||
Extract:
|
||||
- Phase number
|
||||
- Phase name
|
||||
- Phase description
|
||||
- Any "Research: Likely" flags
|
||||
|
||||
Continue to check_existing.
|
||||
</step>
|
||||
|
||||
<step name="check_existing">
|
||||
Check if RESEARCH.md already exists for this phase:
|
||||
|
||||
```bash
|
||||
ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null
|
||||
ls .planning/phases/${PHASE}-*/${PHASE}-RESEARCH.md 2>/dev/null
|
||||
```
|
||||
|
||||
**If exists:**
|
||||
```
|
||||
Phase ${PHASE} already has research: [path to RESEARCH.md]
|
||||
|
||||
What's next?
|
||||
|
||||
1. Discuss phase context (/gsd:discuss-phase [current-phase])
|
||||
2. Create phase plan (/gsd:plan-phase [current-phase])
|
||||
3. Refine research (dig deeper)
|
||||
4. Review findings
|
||||
|
||||
1. Update research - Refresh with new findings
|
||||
2. View existing - Show me the current research
|
||||
3. Skip - Use existing research as-is
|
||||
```
|
||||
|
||||
NOTE: FINDINGS.md is NOT committed separately. It will be committed with phase completion.
|
||||
Wait for user response.
|
||||
|
||||
If "Update research": Load existing RESEARCH.md, proceed to research with update mindset
|
||||
If "View existing": Read and display RESEARCH.md, then offer update/skip
|
||||
If "Skip": Exit workflow
|
||||
|
||||
**If doesn't exist:**
|
||||
Continue to load_context.
|
||||
</step>
|
||||
|
||||
<step name="load_context">
|
||||
Load available context to inform research direction:
|
||||
|
||||
**1. Project context:**
|
||||
```bash
|
||||
cat .planning/PROJECT.md 2>/dev/null | head -50
|
||||
```
|
||||
|
||||
**2. Phase context (if exists from /gsd:discuss-phase):**
|
||||
```bash
|
||||
cat .planning/phases/${PHASE}-*/${PHASE}-CONTEXT.md 2>/dev/null
|
||||
```
|
||||
|
||||
If CONTEXT.md exists, use it to understand:
|
||||
- User's specific goals for this phase
|
||||
- Constraints mentioned
|
||||
- Any preferences stated
|
||||
|
||||
**3. Prior phase decisions:**
|
||||
```bash
|
||||
cat .planning/STATE.md 2>/dev/null | grep -A20 "## Accumulated Decisions"
|
||||
```
|
||||
|
||||
These may constrain technology choices.
|
||||
|
||||
Present what was found:
|
||||
```
|
||||
Research context for Phase ${PHASE}: ${PHASE_NAME}
|
||||
|
||||
Roadmap description: ${PHASE_DESCRIPTION}
|
||||
|
||||
[If CONTEXT.md exists:]
|
||||
Phase context available - will incorporate user preferences.
|
||||
|
||||
[If prior decisions exist:]
|
||||
Prior decisions to respect: [list relevant ones]
|
||||
|
||||
Proceeding with ecosystem research...
|
||||
```
|
||||
</step>
|
||||
|
||||
<step name="identify_domains">
|
||||
Analyze the phase description to identify what needs researching.
|
||||
|
||||
**Ask: "What knowledge do I need to actually implement this well?"**
|
||||
|
||||
Categories to consider:
|
||||
|
||||
**1. Core Technology:**
|
||||
- What's the primary technology/framework?
|
||||
- What version is current? (Claude's training may be stale)
|
||||
- What's the standard setup/toolchain?
|
||||
|
||||
**2. Ecosystem/Stack:**
|
||||
- What libraries do experts pair with this?
|
||||
- What's the "blessed" stack for this problem domain?
|
||||
- What helper libraries exist that I might not know about?
|
||||
|
||||
**3. Architecture Patterns:**
|
||||
- How do experts structure this type of project?
|
||||
- What design patterns apply?
|
||||
- What's the recommended project organization?
|
||||
|
||||
**4. Common Pitfalls:**
|
||||
- What do beginners get wrong?
|
||||
- What are the "gotchas" in this domain?
|
||||
- What mistakes lead to rewrites?
|
||||
|
||||
**5. What NOT to Hand-Roll:**
|
||||
- What existing solutions should be used instead of custom code?
|
||||
- What problems look simple but have nasty edge cases?
|
||||
- What libraries solve problems I don't know I have?
|
||||
|
||||
**6. Current State of the Art:**
|
||||
- What's changed recently in this ecosystem?
|
||||
- What approaches are now considered outdated?
|
||||
- What new tools/patterns have emerged?
|
||||
|
||||
Present research scope:
|
||||
```
|
||||
Research domains identified:
|
||||
|
||||
1. Core: [e.g., "Three.js for 3D web graphics"]
|
||||
2. Ecosystem: [e.g., "Physics engine, asset loading, controls"]
|
||||
3. Patterns: [e.g., "Scene graph architecture, game loop patterns"]
|
||||
4. Pitfalls: [e.g., "Performance, memory, mobile compatibility"]
|
||||
5. Don't hand-roll: [e.g., "Physics, collision detection, procedural generation"]
|
||||
6. SOTA check: [e.g., "WebGPU vs WebGL, drei ecosystem"]
|
||||
|
||||
Proceeding with comprehensive research...
|
||||
```
|
||||
</step>
|
||||
|
||||
<step name="execute_research">
|
||||
Execute research systematically for each domain identified.
|
||||
|
||||
**CRITICAL: Source hierarchy - Context7 BEFORE WebSearch**
|
||||
|
||||
Claude's training data is 6-18 months stale. Treat pre-existing knowledge as hypothesis, not fact.
|
||||
|
||||
<research_protocol>
|
||||
|
||||
**For each domain, in order:**
|
||||
|
||||
**1. Context7 First (authoritative, current):**
|
||||
```
|
||||
For core technology:
|
||||
- mcp__context7__resolve-library-id with libraryName: "[main technology]"
|
||||
- mcp__context7__get-library-docs with topic: "getting started"
|
||||
- mcp__context7__get-library-docs with topic: "[specific concern]"
|
||||
|
||||
For ecosystem libraries:
|
||||
- Resolve and fetch docs for each major library
|
||||
- Focus on integration patterns, not just API reference
|
||||
```
|
||||
|
||||
**2. Official Documentation:**
|
||||
- Use WebFetch for official docs not in Context7
|
||||
- Check for "ecosystem" or "community" pages
|
||||
- Look for "awesome-{technology}" lists
|
||||
- Check GitHub trending/stars for the domain
|
||||
|
||||
**3. WebSearch for Ecosystem Discovery:**
|
||||
```
|
||||
Ecosystem discovery queries (use {current_year}):
|
||||
- "[technology] best practices {current_year}"
|
||||
- "[technology] recommended libraries {current_year}"
|
||||
- "[technology] common mistakes"
|
||||
- "[technology] vs [alternative] {current_year}"
|
||||
- "how to build [type of thing] with [technology]"
|
||||
- "[technology] performance optimization"
|
||||
- "[technology] project structure"
|
||||
|
||||
For niche domains:
|
||||
- "[technology] tutorials {current_year}"
|
||||
- "[technology] examples github"
|
||||
- "[technology] showcase"
|
||||
```
|
||||
|
||||
**4. Cross-Verification (MANDATORY):**
|
||||
Every WebSearch finding MUST be verified:
|
||||
- Check Context7 or official docs to confirm
|
||||
- Mark confidence level (HIGH if verified, MEDIUM if partially verified, LOW if WebSearch only)
|
||||
- Flag contradictions between sources
|
||||
|
||||
</research_protocol>
|
||||
|
||||
<research_execution>
|
||||
Execute research queries and document findings as you go:
|
||||
|
||||
**Core Technology Findings:**
|
||||
- Current version: [from Context7]
|
||||
- Key changes since [Claude's training]: [from docs/WebSearch]
|
||||
- Setup approach: [verified pattern]
|
||||
|
||||
**Ecosystem Stack:**
|
||||
- [Library 1]: [what it does, why it's standard, version]
|
||||
- [Library 2]: [what it does, why it's standard, version]
|
||||
- [Library 3]: [what it does, why it's standard, version]
|
||||
|
||||
**Architecture Patterns:**
|
||||
- [Pattern 1]: [what it is, when to use]
|
||||
- [Pattern 2]: [what it is, when to use]
|
||||
- Project structure: [recommended organization]
|
||||
|
||||
**Common Pitfalls:**
|
||||
- [Pitfall 1]: [what goes wrong, how to avoid]
|
||||
- [Pitfall 2]: [what goes wrong, how to avoid]
|
||||
- [Pitfall 3]: [what goes wrong, how to avoid]
|
||||
|
||||
**Don't Hand-Roll:**
|
||||
- [Problem]: Use [library] instead because [reason]
|
||||
- [Problem]: Use [library] instead because [reason]
|
||||
|
||||
**SOTA Updates:**
|
||||
- [Old approach]: Now superseded by [new approach]
|
||||
- [New tool]: [what it enables]
|
||||
</research_execution>
|
||||
|
||||
</step>
|
||||
|
||||
<step name="quality_check">
|
||||
Before creating RESEARCH.md, run through research-pitfalls.md checklist:
|
||||
|
||||
**From ~/.claude/get-shit-done/references/research-pitfalls.md:**
|
||||
|
||||
- [ ] All enumerated items investigated (not just some)
|
||||
- [ ] Negative claims verified with official docs
|
||||
- [ ] Multiple sources cross-referenced for critical claims
|
||||
- [ ] URLs provided for authoritative sources
|
||||
- [ ] Publication dates checked (prefer recent/current)
|
||||
- [ ] Tool/environment-specific variations documented
|
||||
- [ ] Confidence levels assigned honestly
|
||||
- [ ] Assumptions distinguished from verified facts
|
||||
- [ ] "What might I have missed?" review completed
|
||||
|
||||
**Additional checks for ecosystem research:**
|
||||
- [ ] Checked for libraries Claude might not know about
|
||||
- [ ] Verified version numbers are current
|
||||
- [ ] Confirmed patterns still recommended (not deprecated)
|
||||
- [ ] Looked for "don't do this" warnings in docs
|
||||
- [ ] Checked for breaking changes in recent versions
|
||||
</step>
|
||||
|
||||
<step name="write_research">
|
||||
Create RESEARCH.md using accumulated findings.
|
||||
|
||||
**File location:** `.planning/phases/${PHASE}-${SLUG}/${PHASE}-RESEARCH.md`
|
||||
|
||||
**If phase directory doesn't exist:**
|
||||
Create it: `.planning/phases/${PHASE}-${SLUG}/`
|
||||
|
||||
Use template from ~/.claude/get-shit-done/templates/research.md
|
||||
|
||||
Populate sections with verified findings from research execution.
|
||||
|
||||
**Critical content requirements:**
|
||||
|
||||
**1. Standard Stack section:**
|
||||
- List specific libraries with versions
|
||||
- Explain what each does and why it's standard
|
||||
- Note any alternatives and when to use them
|
||||
|
||||
**2. Architecture Patterns section:**
|
||||
- Document recommended patterns with code examples if available
|
||||
- Include project structure recommendations
|
||||
- Note what patterns to avoid
|
||||
|
||||
**3. Don't Hand-Roll section:**
|
||||
- Be explicit about what problems have existing solutions
|
||||
- Explain why custom solutions are worse
|
||||
- List the libraries to use instead
|
||||
|
||||
**4. Common Pitfalls section:**
|
||||
- Specific mistakes with explanations
|
||||
- How to avoid each
|
||||
- Warning signs to watch for
|
||||
|
||||
**5. Code Examples section:**
|
||||
- Include verified code patterns from Context7/official docs
|
||||
- Show the "right way" to do common operations
|
||||
- Note any gotchas in the examples
|
||||
|
||||
Write file.
|
||||
</step>
|
||||
|
||||
<step name="confirm_creation">
|
||||
Present RESEARCH.md summary to user:
|
||||
|
||||
```
|
||||
Created: .planning/phases/${PHASE}-${SLUG}/${PHASE}-RESEARCH.md
|
||||
|
||||
## Research Summary
|
||||
|
||||
**Domain:** [what was researched]
|
||||
|
||||
**Standard Stack:**
|
||||
- [Library 1] - [brief what/why]
|
||||
- [Library 2] - [brief what/why]
|
||||
- [Library 3] - [brief what/why]
|
||||
|
||||
**Key Patterns:**
|
||||
- [Pattern 1]
|
||||
- [Pattern 2]
|
||||
|
||||
**Don't Hand-Roll:**
|
||||
- [Thing 1] - use [library] instead
|
||||
- [Thing 2] - use [library] instead
|
||||
|
||||
**Top Pitfalls:**
|
||||
- [Pitfall 1]
|
||||
- [Pitfall 2]
|
||||
|
||||
**Confidence:** [HIGH/MEDIUM/LOW] - [brief reason]
|
||||
|
||||
What's next?
|
||||
1. Plan this phase (/gsd:plan-phase ${PHASE}) - RESEARCH.md will be loaded automatically
|
||||
2. Dig deeper - Research specific areas more thoroughly
|
||||
3. Review full RESEARCH.md
|
||||
4. Done for now
|
||||
```
|
||||
</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
|
||||
- FINDINGS.md created with recommendation
|
||||
- Confidence level MEDIUM or higher
|
||||
- Ready to inform PLAN.md creation
|
||||
|
||||
**Level 3 (Deep Dive):**
|
||||
- RESEARCH.md exists with clear scope
|
||||
- Context7 exhaustively consulted
|
||||
- All WebSearch findings verified against authoritative sources
|
||||
- FINDINGS.md created with comprehensive analysis
|
||||
- Quality report with source attribution
|
||||
- If LOW confidence findings → validation checkpoints defined
|
||||
- Confidence gate passed
|
||||
- Ready to inform PLAN.md creation
|
||||
- [ ] Phase validated against roadmap
|
||||
- [ ] Research domains identified from phase description
|
||||
- [ ] Context7 consulted for all relevant libraries
|
||||
- [ ] Official docs consulted where Context7 lacks coverage
|
||||
- [ ] WebSearch used for ecosystem discovery
|
||||
- [ ] All WebSearch findings cross-verified
|
||||
- [ ] Quality checklist completed
|
||||
- [ ] RESEARCH.md created with comprehensive ecosystem knowledge
|
||||
- [ ] Standard stack documented with versions
|
||||
- [ ] Architecture patterns documented
|
||||
- [ ] "Don't hand-roll" list is clear and actionable
|
||||
- [ ] Common pitfalls catalogued
|
||||
- [ ] Confidence levels assigned honestly
|
||||
- [ ] User knows next steps (plan phase)
|
||||
</success_criteria>
|
||||
```
|
||||
|
||||
<integration_with_planning>
|
||||
When /gsd:plan-phase runs after research:
|
||||
|
||||
1. plan-phase detects RESEARCH.md exists in phase directory
|
||||
2. RESEARCH.md loaded as @context reference
|
||||
3. "Standard stack" informs library choices in tasks
|
||||
4. "Don't hand-roll" prevents custom solutions where libraries exist
|
||||
5. "Common pitfalls" inform verification criteria
|
||||
6. "Architecture patterns" inform task structure
|
||||
7. "Code examples" can be referenced in task actions
|
||||
|
||||
This produces higher quality plans because Claude knows:
|
||||
- What tools experts use
|
||||
- What patterns to follow
|
||||
- What mistakes to avoid
|
||||
- What NOT to build from scratch
|
||||
</integration_with_planning>
|
||||
|
||||
Reference in New Issue
Block a user