@codihaus/claude-skills 1.6.8 → 1.6.10

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@codihaus/claude-skills",
-  "version": "1.6.8",
+  "version": "1.6.10",
   "description": "Claude Code skills for software development workflow",
   "main": "src/index.js",
   "bin": {

package/skills/debrief/SKILL.md

@@ -68,6 +68,7 @@ Depending on mode:
 **New Project:**
 - BRD with use cases grouped by feature
 - Context document (stakeholders, constraints, users)
+- Market research (MVP/Standard/Advanced feature tiers)
 - Feature folders created
 - Architecture feasibility validated
 - Questionnaire for customer gaps
@@ -110,22 +111,72 @@ Detect automatically on start:
 
 ## Context Gathering
 
-Use `AskUserQuestion` to understand project context.
+Use `AskUserQuestion` to understand project context and scope preferences.
+
+### For New Project
+
+Ask 5 key questions using `AskUserQuestion`:
+
+**Q1: Project Type & Source Code**
+Options:
+- New project (no existing code)
+- Existing codebase (current folder)
+- Existing codebase (different folder)
+
+**Q2: Industry/Niche**
+Options:
+- SaaS B2B
+- SaaS B2C
+- E-commerce
+- Marketplace
+- Enterprise
+- Other
+
+**Q3: Target Users**
+Options:
+- Business users (B2B)
+- Consumers (B2C)
+- Internal users
+- Mixed
+
+**Q4: Known Constraints** (multi-select)
+Options:
+- Timeline constraint
+- Budget constraint
+- Compliance requirements
+- Integration requirements
+- None
+
+**Q5: Scope Tier Preference**
+Options:
+- **Core (3-5 use cases)** - MVP, essential features only
+- **Standard (8-12 use cases)** - Competitive parity, market standard
+- **Full (15+ use cases)** - Advanced features, differentiation
+
+This helps align on MVP vs market standard vs advanced features upfront.
+
+### For Add Feature
+
+Ask 2 questions:
+
+**Q1: Feature Name**
+What to call this feature (e.g., "billing", "notifications", "analytics")
 
-**For New Project, ask about:**
-- Project type (new vs existing codebase)
-- Industry/niche
-- Target users
-- Known constraints
-- Scope tier (Core/Standard/Full)
+**Q2: Scope for This Feature**
+Options:
+- **Core** - MVP/essential only
+- **Standard** - Competitive parity
+- **Full** - Advanced/differentiation features
 
-**For Add Feature, ask about:**
-- Feature name
-- Scope for this feature
+### For Existing Codebase
 
-**For Existing Codebase:**
-- Scan for docs, existing features, patterns
-- Reference `references/file-patterns.md` for scan patterns
+**If user indicates existing codebase:**
+- Scan for docs (CLAUDE.md, README, CONTRIBUTING)
+- Scan frontend files (.vue, .tsx, .jsx) to infer existing features
+- Use `references/file-patterns.md` for scan patterns
+- Summarize findings in `context.md`
+
+This codebase discovery informs which features already exist and what gaps remain.
 
 ## Duplicate Prevention
 
@@ -150,12 +201,62 @@ Use `AskUserQuestion` to understand project context.
 - Open questions
 - References from market research
 
-**Market research:**
-- Industry patterns
-- User flows
-- Compliance requirements
-- Documentation links
-- Output to `references.md`
+## Market Research
+
+**Why research:** Understand feature tiers and competitive landscape to inform scope decisions.
+
+**Combines with user's scope preference:**
+- User chose "Core" → Focus research on MVP features
+- User chose "Standard" → Research MVP + market standard features
+- User chose "Full" → Research all tiers including advanced/differentiation
+
+**What to research:**
+- Industry patterns (what similar products do)
+- User flows (standard UX patterns in this domain)
+- Compliance requirements (regulations, standards, must-haves)
+- Documentation links (references for engineers)
+
+**Expected insights organized by tier:**
+- **MVP Features (Must-Have):** Minimum to be viable product
+  - Example: Login, basic CRUD, core workflows
+- **Market Standard (Competitive Parity):** What competitors offer
+  - Example: SSO, notifications, exports
+- **Advanced Features (Differentiation):** What sets apart top products
+  - Example: AI suggestions, real-time collaboration, advanced analytics
+
+**Output:**
+- `references.md` - Organized by feature tier with links and notes
+- Use insights to:
+  - Validate user's scope choice (Core/Standard/Full)
+  - Prioritize use cases (Must/Should/Could)
+  - Guide customer conversations ("This is standard" vs "This is premium")
+
+**Format for references.md:**
+```markdown
+## {Feature} - Market Research
+
+### MVP (Must-Have)
+- Login/Signup - Industry standard: email + password + OAuth
+  - Reference: [Auth0 best practices](link)
+- Profile management - Every product has this
+
+### Market Standard (Competitive Parity)
+- SSO integration - 80% of competitors offer this
+  - Reference: [SAML guide](link)
+- Email notifications - User expectation
+
+### Advanced (Differentiation)
+- AI-powered recommendations - Only Competitor X has this
+  - Reference: [ML recommendation patterns](link)
+- Real-time collaboration - Top-tier feature
+```
+
+**How it guides use case creation:**
+- User chose "Core" → Create use cases for MVP tier only
+- User chose "Standard" → Create use cases for MVP + Market Standard tiers
+- User chose "Full" → Create use cases for all tiers
+
+This alignment ensures use cases match the agreed scope.
 
 ## BRD Structure
 

package/skills/utils/docs-graph/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: utils/docs-graph
 description: View and query the documentation knowledge graph
-version: 1.2.0
+version: 1.3.0
 ---
 
 # /utils/docs-graph - Documentation Graph Viewer
@@ -18,74 +18,47 @@ View and query relationships between planning documents.
 - See overview of all plans and their relationships
 - Find related documents before making changes
 - Check impact of changes (what links to this?)
-- Verify graph is up-to-date
+- Verify links are valid
 
 ## Usage
 
 ```
 /utils/docs-graph                    # Show graph summary
 /utils/docs-graph auth               # Show nodes related to "auth"
-/utils/docs-graph --regenerate       # Force regenerate graph
 /utils/docs-graph --check            # Verify all links resolve
 ```
 
 ## How It Works
 
-The graph is automatically updated via Claude Code hooks whenever files in `plans/` are created or modified. This skill provides on-demand viewing and querying.
-
-### Automatic Updates
-
-PostToolUse hook triggers on Write/Edit to plans/:
-1. Hook detects file path contains `plans/`
-2. Runs `python3 scripts/graph.py --check-path <path>`
-3. Graph files updated before next Claude action
-
-### Graph Files
+**Automatic Updates:**
+- PostToolUse hook triggers on Write/Edit to `plans/`
+- Regenerates entire graph from all files in `plans/`
+- Updates `plans/docs-graph.json` and `plans/docs-graph.md`
+- Timeout: 3 minutes
 
+**Graph Files:**
 ```
 plans/
 ├── docs-graph.json    # Machine-readable graph data
 └── docs-graph.md      # Mermaid visualization
 ```
 
-## Workflow
-
-### Phase 1: Load Graph
-
-1. Check if `plans/docs-graph.json` exists
-2. If not, run `python3 scripts/graph.py` to generate
-3. Read graph data
-
-### Phase 2: Display or Query
+## Expected Outcome
 
 **Summary mode (default):**
-- Show node count by type
-- Show edge count
-- Display mermaid diagram from docs-graph.md
-- List any errors
-
-**Query mode (with argument):**
-- Filter nodes matching query
-- Show incoming links (what references this)
-- Show outgoing links (what this references)
+- Node count by type
+- Edge count
+- Mermaid diagram from docs-graph.md
 
-**Regenerate mode (--regenerate):**
-- Force full rescan of plans/
-- Update docs-graph.json and docs-graph.md
-- Show diff if changes detected
+**Query mode (with argument like "auth"):**
+- Matching nodes
+- Incoming links (what references this)
+- Outgoing links (what this references)
 
 **Check mode (--check):**
-- Verify all wikilinks resolve to existing nodes
 - Report broken links
 - Suggest fixes
 
-### Phase 3: Output
-
-Display results with:
-- Mermaid diagram (if summary)
-- Table of matching nodes (if query)
-- Broken link report (if check)
-
 ## Wikilink Convention
 
 Documents use `[[wikilinks]]` to reference each other:

package/templates/hooks-guide.md

@@ -158,13 +158,15 @@ if [ ! -f ".claude/scripts/graph.py" ]; then
   exit 0
 fi
 
-timeout 10s python3 .claude/scripts/graph.py --check-path "$1" || true
+# Full regeneration (scans all files in plans/)
+timeout 180s python3 .claude/scripts/graph.py || true
 ```
 
 Then in settings.json:
 ```json
 {
-  "command": "bash .claude/scripts/safe-graph-update.sh $PATH"
+  "command": "bash .claude/scripts/safe-graph-update.sh $PATH",
+  "timeout": 180000
 }
 ```
 
@@ -182,7 +184,8 @@ Choose the right `failureAction` based on hook criticality:
 **Example - Non-critical hook:**
 ```json
 {
-  "command": "python3 .claude/scripts/graph.py --check-path $PATH || true",
+  "command": "timeout 180 python3 .claude/scripts/graph.py || true",
+  "timeout": 180000,
   "retries": {
     "maxAttempts": 3,
     "failureAction": "warn"

package/templates/scripts/safe-graph-update.sh

@@ -5,18 +5,17 @@
 # This script provides resilient execution of graph.py with:
 # - Dependency checking
 # - Graceful failure handling
-# - Timeout protection
-# - Clear error messages
+# - Timeout protection (3 minutes)
+# - Full regeneration of graph from all files in plans/
 #
 
 set -e
 
 # Configuration
-TIMEOUT_SECONDS=10
+TIMEOUT_SECONDS=180  # 3 minutes
 # Get the directory where this script is located
 SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 GRAPH_SCRIPT="$SCRIPT_DIR/graph.py"
-MAX_RETRIES=0  # Let Claude Code handle retries
 
 # Colors for output (optional)
 RED='\033[0;31m'
@@ -49,8 +48,8 @@ if [[ ! "$FILE_PATH" =~ ^plans/.*\.md$ ]]; then
     exit 0
 fi
 
-# Run graph.py with timeout
-if timeout "$TIMEOUT_SECONDS" python3 "$GRAPH_SCRIPT" --check-path "$FILE_PATH" 2>/dev/null; then
+# Run full graph regeneration (no --check-path, scans all files)
+if timeout "$TIMEOUT_SECONDS" python3 "$GRAPH_SCRIPT" 2>/dev/null; then
     # Success - silent
     exit 0
 else