get-research-done 1.1.0

package/commands/grd/insights.md

@@ -0,0 +1,231 @@
+---
+name: grd:insights
+description: Generate plain English data insights for business analysts without code or jargon
+allowed-tools:
+  - Read
+  - Bash
+  - Write
+  - Task
+  - AskUserQuestion
+---
+
+<objective>
+
+Generate accessible, plain English data insights for business analysts and non-technical stakeholders.
+
+Unlike `/grd:explore` (technical) or `/grd:quick-explore` (fast), insights mode produces:
+- **Technical report** saved to file (same rigor as full explore)
+- **Plain English summary** displayed in console with "What This Means" explanations
+- **Actionable recommendations** based on data characteristics
+- **LLM prompts** for further exploration (copy-paste ready)
+
+**Creates:**
+- `.planning/DATA_REPORT.md` — full technical analysis (saved, not displayed)
+- `.planning/INSIGHTS_SUMMARY.md` — plain English summary with recommendations
+- Console output with business-friendly insights
+
+**Use cases:**
+- Explaining data to business stakeholders
+- Preparing for cross-functional meetings
+- Documenting data characteristics for non-technical team members
+- Getting LLM-powered exploration prompts for deeper analysis
+
+**After this command:**
+- Share INSIGHTS_SUMMARY.md with stakeholders
+- Use LLM prompts for further exploration
+- Proceed to `/grd:architect` for hypothesis formation
+
+</objective>
+
+<execution_context>
+
+@~/.claude/get-research-done/templates/data-report.md
+
+</execution_context>
+
+<process>
+
+## Phase 1: Setup and Data Path Resolution
+
+**Check if project initialized:**
+
+```bash
+[ ! -f .planning/PROJECT.md ] && echo "ERROR: Project not initialized. Run /grd:new-project first." && exit 1
+```
+
+**Determine data path:**
+
+If [path] argument provided:
+- Use it directly
+- Validate path exists
+
+If no argument:
+- Check for common data directories (./data/, ./datasets/, ./raw/)
+- If found, list contents and ask user to select
+- If not found, ask user to provide path interactively
+
+## Phase 2: Spawn Explorer Agent (Insights Mode)
+
+Display insights banner:
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GRD ► DATA INSIGHTS
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Analyzing: [data_path]
+Mode: Insights (business-friendly output)
+```
+
+Spawn grd-explorer agent with insights mode context:
+
+```
+Task(prompt="
+<data_source>
+Path: [data_path]
+Type: [file | directory]
+</data_source>
+
+<profiling_mode>insights</profiling_mode>
+
+<insights_mode_instructions>
+Insights mode generates TWO outputs:
+
+1. **Technical Report** (DATA_REPORT.md)
+   - Full statistical analysis (same as regular explore)
+   - Save to .planning/DATA_REPORT.md
+   - Do NOT display in console
+
+2. **Plain English Summary** (INSIGHTS_SUMMARY.md + Console)
+   - Business-friendly language
+   - Every statistic includes 'What This Means' explanation
+   - Actionable recommendations
+   - LLM prompts for further exploration
+
+Plain English writing rules:
+- No jargon: 'missing values' not 'null frequency'
+- Context for numbers: '15% missing' → '15% of rows have no value here, which could affect predictions'
+- Severity language: 'critical' / 'concerning' / 'minor' / 'looks good'
+- Action-oriented: 'Consider removing...' not 'High cardinality detected'
+</insights_mode_instructions>
+
+<summary_structure>
+# Data Insights Summary
+
+## TL;DR (5 bullet points max)
+The most important things a business person needs to know.
+
+## 5 Things to Know About This Data
+| Finding | What This Means |
+|---------|-----------------|
+| X rows of data | Enough/not enough for reliable analysis |
+| Y% missing in column Z | May need to collect more data or handle gaps |
+
+## Critical Issues (if any)
+Plain English explanation of blocking problems.
+
+## Recommendations
+Priority-sorted list with effort estimates:
+1. [High] Fix X before modeling — prevents Y problem
+2. [Medium] Consider Z — improves reliability
+
+## Dig Deeper (LLM Prompts)
+Copy-paste prompts for further exploration:
+
+```
+Analyze the relationship between [column A] and [column B] in this dataset.
+What patterns do you see?
+```
+
+```
+The [column] has [X]% missing values. What strategies would you recommend
+for handling this, given that [context from data]?
+```
+</summary_structure>
+
+<project_context>
+@.planning/PROJECT.md
+
+Extract:
+- What this project is about
+- Business context for recommendations
+</project_context>
+
+<output>
+1. Write .planning/DATA_REPORT.md (full technical analysis)
+2. Write .planning/INSIGHTS_SUMMARY.md (plain English summary)
+3. Print INSIGHTS_SUMMARY.md content to console
+4. Return paths to both files
+</output>
+", subagent_type="grd-explorer", model="sonnet", description="Generate data insights")
+```
+
+## Phase 3: Present Results
+
+After agent completes, display footer:
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GRD ► INSIGHTS COMPLETE ✓
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+**For stakeholders:** .planning/INSIGHTS_SUMMARY.md
+**Technical details:** .planning/DATA_REPORT.md
+
+───────────────────────────────────────────────────────────────
+
+**Share with team:** Copy INSIGHTS_SUMMARY.md content
+**Deep dive:** Use the LLM prompts in the summary
+**Next step:** /grd:architect — form a hypothesis
+
+───────────────────────────────────────────────────────────────
+```
+
+</process>
+
+<arguments>
+
+**[path]** (required)
+- Path to data file or directory
+- Examples: `./data/train.csv`, `./datasets/`
+
+</arguments>
+
+<examples>
+
+**Generate insights for CSV:**
+```
+/grd:insights ./data/train.csv
+```
+
+**Generate insights for directory:**
+```
+/grd:insights ./datasets/
+```
+
+</examples>
+
+<output>
+
+**Files created:**
+- `.planning/DATA_REPORT.md` — full technical analysis
+- `.planning/INSIGHTS_SUMMARY.md` — plain English summary
+
+**Console output:**
+- Complete INSIGHTS_SUMMARY.md content displayed
+- Business-friendly language throughout
+- LLM prompts for further exploration
+
+</output>
+
+<success_criteria>
+
+- [ ] Data path resolved
+- [ ] grd-explorer spawned with insights mode context
+- [ ] DATA_REPORT.md created with full technical analysis
+- [ ] INSIGHTS_SUMMARY.md created with plain English summary
+- [ ] Every statistic includes "What This Means" explanation
+- [ ] Actionable recommendations provided
+- [ ] LLM prompts generated for further exploration
+- [ ] Summary displayed in console
+
+</success_criteria>

package/commands/grd/join-discord.md

@@ -0,0 +1,18 @@
+---
+name: grd:join-discord
+description: Join the GSD Discord community
+---
+
+<objective>
+Display the Discord invite link for the GSD community server.
+</objective>
+
+<output>
+# Join the GSD Discord
+
+Connect with other GSD users, get help, share what you're building, and stay updated.
+
+**Invite link:** https://discord.gg/5JJgD5svVS
+
+Click the link or paste it into your browser to join.
+</output>

package/commands/grd/list-phase-assumptions.md

@@ -0,0 +1,50 @@
+---
+name: grd:list-phase-assumptions
+description: Surface Claude's assumptions about a phase approach before planning
+argument-hint: "[phase]"
+allowed-tools:
+  - Read
+  - Bash
+  - Grep
+  - Glob
+---
+
+<objective>
+Analyze a phase and present Claude's assumptions about technical approach, implementation order, scope boundaries, risk areas, and dependencies.
+
+Purpose: Help users see what Claude thinks BEFORE planning begins - enabling course correction early when assumptions are wrong.
+Output: Conversational output only (no file creation) - ends with "What do you think?" prompt
+</objective>
+
+<execution_context>
+@~/.claude/get-research-done/workflows/list-phase-assumptions.md
+</execution_context>
+
+<context>
+Phase number: $ARGUMENTS (required)
+
+**Load project state first:**
+@.planning/STATE.md
+
+**Load roadmap:**
+@.planning/ROADMAP.md
+</context>
+
+<process>
+1. Validate phase number argument (error if missing or invalid)
+2. Check if phase exists in roadmap
+3. Follow list-phase-assumptions.md workflow:
+   - Analyze roadmap description
+   - Surface assumptions about: technical approach, implementation order, scope, risks, dependencies
+   - Present assumptions clearly
+   - Prompt "What do you think?"
+4. Gather feedback and offer next steps
+</process>
+
+<success_criteria>
+
+- Phase validated against roadmap
+- Assumptions surfaced across five areas
+- User prompted for feedback
+- User knows next steps (discuss context, plan phase, or correct assumptions)
+  </success_criteria>

package/commands/grd/map-codebase.md

@@ -0,0 +1,71 @@
+---
+name: grd:map-codebase
+description: Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents
+argument-hint: "[optional: specific area to map, e.g., 'api' or 'auth']"
+allowed-tools:
+  - Read
+  - Bash
+  - Glob
+  - Grep
+  - Write
+  - Task
+---
+
+<objective>
+Analyze existing codebase using parallel grd-codebase-mapper agents to produce structured codebase documents.
+
+Each mapper agent explores a focus area and **writes documents directly** to `.planning/codebase/`. The orchestrator only receives confirmations, keeping context usage minimal.
+
+Output: .planning/codebase/ folder with 7 structured documents about the codebase state.
+</objective>
+
+<execution_context>
+@~/.claude/get-research-done/workflows/map-codebase.md
+</execution_context>
+
+<context>
+Focus area: $ARGUMENTS (optional - if provided, tells agents to focus on specific subsystem)
+
+**Load project state if exists:**
+Check for .planning/STATE.md - loads context if project already initialized
+
+**This command can run:**
+- Before /grd:new-project (brownfield codebases) - creates codebase map first
+- After /grd:new-project (greenfield codebases) - updates codebase map as code evolves
+- Anytime to refresh codebase understanding
+</context>
+
+<when_to_use>
+**Use map-codebase for:**
+- Brownfield projects before initialization (understand existing code first)
+- Refreshing codebase map after significant changes
+- Onboarding to an unfamiliar codebase
+- Before major refactoring (understand current state)
+- When STATE.md references outdated codebase info
+
+**Skip map-codebase for:**
+- Greenfield projects with no code yet (nothing to map)
+- Trivial codebases (<5 files)
+</when_to_use>
+
+<process>
+1. Check if .planning/codebase/ already exists (offer to refresh or skip)
+2. Create .planning/codebase/ directory structure
+3. Spawn 4 parallel grd-codebase-mapper agents:
+   - Agent 1: tech focus → writes STACK.md, INTEGRATIONS.md
+   - Agent 2: arch focus → writes ARCHITECTURE.md, STRUCTURE.md
+   - Agent 3: quality focus → writes CONVENTIONS.md, TESTING.md
+   - Agent 4: concerns focus → writes CONCERNS.md
+4. Wait for agents to complete, collect confirmations (NOT document contents)
+5. Verify all 7 documents exist with line counts
+6. Commit codebase map
+7. Offer next steps (typically: /grd:new-project or /grd:plan-phase)
+</process>
+
+<success_criteria>
+- [ ] .planning/codebase/ directory created
+- [ ] All 7 codebase documents written by mapper agents
+- [ ] Documents follow template structure
+- [ ] Parallel agents completed without errors
+- [ ] User knows next steps
+</success_criteria>