claude-code-pilot 3.0.0 → 3.1.0

package/src/pilot/workflows/help.md

@@ -120,7 +120,7 @@ These commands manage the full project lifecycle: initialization, planning, exec
 
 ---
 
-## Part 2: Development Workflow Commands (no prefix)
+## Part 2: Development Workflow Commands (`/ccp:` prefix)
 
 These are utility commands for day-to-day development: code quality, testing, builds, sessions, and language-specific workflows.
 
@@ -128,91 +128,83 @@ These are utility commands for day-to-day development: code quality, testing, bu
 
 | Command | Description |
 |---------|-------------|
-| `/code-review` | Comprehensive security and quality review of uncommitted changes |
-| `/tdd` | Enforce TDD workflow -- scaffold interfaces, generate tests first, then implement |
-| `/test-coverage` | Analyze test coverage, identify gaps, and generate missing tests for 80%+ |
-| `/refactor-clean` | Safely identify and remove dead code with test verification at every step |
-| `/prune` | Delete pending instincts older than 30 days that were never promoted |
-| `/rules-distill` | Scan skills to extract cross-cutting principles and distill them into rules |
+| `/ccp:code-review` | Comprehensive security and quality review of uncommitted changes |
+| `/ccp:tdd` | Enforce TDD workflow -- scaffold interfaces, generate tests first, then implement |
+| `/ccp:test-coverage` | Analyze test coverage, identify gaps, and generate missing tests for 80%+ |
+| `/ccp:refactor-clean` | Safely identify and remove dead code with test verification at every step |
+| `/ccp:prune` | Delete pending instincts older than 30 days that were never promoted |
+| `/ccp:rules-distill` | Scan skills to extract cross-cutting principles and distill them into rules |
 
 ### Build & Fix
 
 | Command | Description |
 |---------|-------------|
-| `/build-fix` | Incrementally fix build and type errors with minimal, safe changes |
-| `/e2e` | Generate and run end-to-end tests with Playwright |
-| `/docs` | Look up current documentation for a library or topic via Context7 |
-| `/update-docs` | Sync documentation with the codebase, generating from source-of-truth files |
-| `/update-codemaps` | Analyze codebase structure and generate token-lean architecture docs |
+| `/ccp:build-fix` | Incrementally fix build and type errors with minimal, safe changes |
+| `/ccp:e2e` | Generate and run end-to-end tests with Playwright |
+| `/ccp:docs` | Look up current documentation for a library or topic via Context7 |
+| `/ccp:update-docs` | Sync documentation with the codebase, generating from source-of-truth files |
+| `/ccp:update-codemaps` | Analyze codebase structure and generate token-lean architecture docs |
 
 ### Planning & Orchestration
 
 | Command | Description |
 |---------|-------------|
-| `/plan` | Restate requirements, assess risks, and create step-by-step implementation plan |
-| `/orchestrate` | Sequential and tmux/worktree guidance for multi-agent workflows |
-| `/aside` | Answer a quick side question without losing context from the current task |
-| `/context-budget` | Analyze context window usage and find optimization opportunities |
-| `/prompt-optimize` | Analyze a draft prompt and output an optimized version |
-
-### Multi-Agent Collaboration
-
-| Command | Description |
-|---------|-------------|
-| `/multi-plan` | Multi-model collaborative planning with dual-model analysis |
-| `/multi-execute` | Multi-model collaborative execution with prototype and refactor flow |
-| `/multi-workflow` | Multi-model collaborative development workflow with quality gates |
+| `/ccp:plan` | Restate requirements, assess risks, and create step-by-step implementation plan |
+| `/ccp:orchestrate` | Sequential and tmux/worktree guidance for multi-agent workflows |
+| `/ccp:aside` | Answer a quick side question without losing context from the current task |
+| `/ccp:context-budget` | Analyze context window usage and find optimization opportunities |
+| `/ccp:prompt-optimize` | Analyze a draft prompt and output an optimized version |
 
 ### Sessions
 
 | Command | Description |
 |---------|-------------|
-| `/save-session` | Save current session state to a dated file for future resumption |
-| `/resume-session` | Load the most recent session file and resume work with full context |
-| `/sessions` | Manage session history -- list, load, alias, and edit sessions |
-| `/checkpoint` | Create or verify a checkpoint in your workflow |
+| `/ccp:save-session` | Save current session state to a dated file for future resumption |
+| `/ccp:resume-session` | Load the most recent session file and resume work with full context |
+| `/ccp:sessions` | Manage session history -- list, load, alias, and edit sessions |
+| `/ccp:checkpoint` | Create or verify a checkpoint in your workflow |
 
 ### Evaluation & Skills
 
 | Command | Description |
 |---------|-------------|
-| `/eval` | Manage eval-driven development workflow |
-| `/harness-audit` | Run a deterministic repository harness audit and return a scorecard |
-| `/skill-create` | Analyze git history to extract coding patterns and generate SKILL.md files |
-| `/skill-health` | Show skill portfolio health dashboard with charts and analytics |
+| `/ccp:eval` | Manage eval-driven development workflow |
+| `/ccp:harness-audit` | Run a deterministic repository harness audit and return a scorecard |
+| `/ccp:skill-create` | Analyze git history to extract coding patterns and generate SKILL.md files |
+| `/ccp:skill-health` | Show skill portfolio health dashboard with charts and analytics |
 
 ### Configuration & Setup
 
 | Command | Description |
 |---------|-------------|
-| `/setup` | First-time project setup -- scan codebase, generate CLAUDE.md, install rules |
-| `/setup-refresh` | Re-scan codebase and update CLAUDE.md, rules, and architecture docs |
-| `/setup-pm` | Configure your preferred package manager (npm/pnpm/yarn/bun) |
-| `/tool-guide` | MCP tool recommendations per task type -- which tools to use when |
-| `/model-route` | Recommend the best model tier for the current task by complexity |
-| `/quality-gate` | Run the quality pipeline on demand for a file or project scope |
-| `/verify` | Run comprehensive verification on current codebase state |
-| `/learn` | Analyze current session and extract patterns worth saving as skills |
-| `/evolve` | Analyze instincts and suggest or generate evolved structures |
+| `/ccp:setup` | First-time project setup -- scan codebase, generate CLAUDE.md, install rules |
+| `/ccp:setup-refresh` | Re-scan codebase and update CLAUDE.md, rules, and architecture docs |
+| `/ccp:setup-pm` | Configure your preferred package manager (npm/pnpm/yarn/bun) |
+| `/ccp:tool-guide` | MCP tool recommendations per task type -- which tools to use when |
+| `/ccp:model-route` | Recommend the best model tier for the current task by complexity |
+| `/ccp:quality-gate` | Run the quality pipeline on demand for a file or project scope |
+| `/ccp:verify` | Run comprehensive verification on current codebase state |
+| `/ccp:learn` | Analyze current session and extract patterns worth saving as skills |
+| `/ccp:evolve` | Analyze instincts and suggest or generate evolved structures |
 
 ### Language-Specific Workflows
 
 | Command | Description |
 |---------|-------------|
-| `/go-build` | Fix Go build errors, go vet warnings, and linter issues |
-| `/go-review` | Go code review for idiomatic patterns, concurrency, and security |
-| `/go-test` | TDD workflow for Go -- table-driven tests, 80%+ coverage |
-| `/rust-build` | Fix Rust build errors, borrow checker issues, and dependencies |
-| `/rust-review` | Rust code review for ownership, lifetimes, and idiomatic patterns |
-| `/rust-test` | TDD workflow for Rust -- tests first, 80%+ coverage with cargo-llvm-cov |
-| `/kotlin-build` | Fix Kotlin/Gradle build errors and dependency issues |
-| `/kotlin-review` | Kotlin code review for null safety, coroutines, and security |
-| `/kotlin-test` | TDD workflow for Kotlin -- Kotest tests, 80%+ coverage with Kover |
-| `/cpp-build` | Fix C++ build errors, CMake issues, and linker problems |
-| `/cpp-review` | C++ code review for memory safety, modern idioms, and concurrency |
-| `/cpp-test` | TDD workflow for C++ -- GoogleTest, coverage with gcov/lcov |
-| `/python-review` | Python code review for PEP 8, type hints, security, and idioms |
-| `/gradle-build` | Fix Gradle build errors for Android and KMP projects |
+| `/ccp:go-build` | Fix Go build errors, go vet warnings, and linter issues |
+| `/ccp:go-review` | Go code review for idiomatic patterns, concurrency, and security |
+| `/ccp:go-test` | TDD workflow for Go -- table-driven tests, 80%+ coverage |
+| `/ccp:rust-build` | Fix Rust build errors, borrow checker issues, and dependencies |
+| `/ccp:rust-review` | Rust code review for ownership, lifetimes, and idiomatic patterns |
+| `/ccp:rust-test` | TDD workflow for Rust -- tests first, 80%+ coverage with cargo-llvm-cov |
+| `/ccp:kotlin-build` | Fix Kotlin/Gradle build errors and dependency issues |
+| `/ccp:kotlin-review` | Kotlin code review for null safety, coroutines, and security |
+| `/ccp:kotlin-test` | TDD workflow for Kotlin -- Kotest tests, 80%+ coverage with Kover |
+| `/ccp:cpp-build` | Fix C++ build errors, CMake issues, and linker problems |
+| `/ccp:cpp-review` | C++ code review for memory safety, modern idioms, and concurrency |
+| `/ccp:cpp-test` | TDD workflow for C++ -- GoogleTest, coverage with gcov/lcov |
+| `/ccp:python-review` | Python code review for PEP 8, type hints, security, and idioms |
+| `/ccp:gradle-build` | Fix Gradle build errors for Android and KMP projects |
 
 ---
 

package/src/pilot/workflows/profile-user.md

@@ -0,0 +1,452 @@
+<purpose>
+Orchestrate the full developer profiling flow: consent, session analysis (or questionnaire fallback), profile generation, result display, and artifact creation.
+
+This workflow wires Phase 1 (session pipeline) and Phase 2 (profiling engine) into a cohesive user-facing experience. All heavy lifting is done by the LLM using its standard tools (Read, Write, Bash, Glob, Grep) and the ccp-user-profiler agent -- this workflow orchestrates the sequence, handles branching, and provides the UX.
+</purpose>
+
+<required_reading>
+Read all files referenced by the invoking prompt's execution_context before starting.
+
+Key references:
+- @~/.claude/pilot/references/ui-brand.md (display patterns)
+<!-- ccp-user-profiler agent and user-profiling reference are planned for a future release -->
+</required_reading>
+
+<process>
+
+## 1. Initialize
+
+Parse flags from $ARGUMENTS:
+- Detect `--questionnaire` flag (skip session analysis, questionnaire-only)
+- Detect `--refresh` flag (rebuild profile even when one exists)
+
+Check for existing profile:
+
+```bash
+PROFILE_PATH="./.claude/pilot/USER-PROFILE.md"
+[ -f "$PROFILE_PATH" ] && echo "EXISTS" || echo "NOT_FOUND"
+```
+
+**If profile exists AND --refresh NOT set AND --questionnaire NOT set:**
+
+Use AskUserQuestion:
+- header: "Existing Profile"
+- question: "You already have a profile. What would you like to do?"
+- options:
+  - "View it" -- Display summary card from existing profile data, then exit
+  - "Refresh it" -- Continue with --refresh behavior
+  - "Cancel" -- Exit workflow
+
+If "View it": Read USER-PROFILE.md, display its content formatted as a summary card, then exit.
+If "Refresh it": Set --refresh behavior and continue.
+If "Cancel": Display "No changes made." and exit.
+
+**If profile exists AND --refresh IS set:**
+
+Backup existing profile:
+```bash
+cp "./.claude/pilot/USER-PROFILE.md" "./.claude/pilot/USER-PROFILE.backup.md"
+```
+
+Display: "Re-analyzing your sessions to update your profile."
+Continue to step 2.
+
+**If no profile exists:** Continue to step 2.
+
+---
+
+## 2. Consent Gate (ACTV-06)
+
+**Skip if** `--questionnaire` flag is set (no JSONL reading occurs -- jump directly to step 4b).
+
+Display consent screen:
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ CCP > PROFILE YOUR CODING STYLE
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Claude starts every conversation generic. A profile teaches Claude
+how YOU actually work -- not how you think you work.
+
+## What We'll Analyze
+
+Your recent Claude Code sessions, looking for patterns in these
+8 behavioral dimensions:
+
+| Dimension            | What It Measures                            |
+|----------------------|---------------------------------------------|
+| Communication Style  | How you phrase requests (terse vs. detailed) |
+| Decision Speed       | How you choose between options               |
+| Explanation Depth    | How much explanation you want with code      |
+| Debugging Approach   | How you tackle errors and bugs               |
+| UX Philosophy        | How much you care about design vs. function  |
+| Vendor Philosophy    | How you evaluate libraries and tools         |
+| Frustration Triggers | What makes you correct Claude                |
+| Learning Style       | How you prefer to learn new things           |
+
+## Data Handling
+
+✓ Reads session files locally (read-only, nothing modified)
+✓ Analyzes message patterns (not content meaning)
+✓ Stores profile at ./.claude/pilot/USER-PROFILE.md
+✗ Nothing is sent to external services
+✗ Sensitive content (API keys, passwords) is automatically excluded
+```
+
+**If --refresh path:**
+Show abbreviated consent instead:
+
+```
+Re-analyzing your sessions to update your profile.
+Your existing profile has been backed up to USER-PROFILE.backup.md.
+```
+
+Use AskUserQuestion:
+- header: "Refresh"
+- question: "Continue with profile refresh?"
+- options:
+  - "Continue" -- Proceed to step 3
+  - "Cancel" -- Exit workflow
+
+**If default (no --refresh) path:**
+
+Use AskUserQuestion:
+- header: "Ready?"
+- question: "Ready to analyze your sessions?"
+- options:
+  - "Let's go" -- Proceed to step 3 (session analysis)
+  - "Use questionnaire instead" -- Jump to step 4b (questionnaire path)
+  - "Not now" -- Display "No worries. Run /ccp:profile-user when ready." and exit
+
+---
+
+## 3. Session Scan
+
+Display: "◆ Scanning sessions..."
+
+Scan for Claude Code session files:
+- Check `$HOME/.claude/` and `.claude/` for session JSONL files (projects/*/sessions/*.jsonl or similar)
+- Use Glob to find all *.jsonl session files
+- Count sessions and group by project directory
+- Report: "Found N sessions across M projects"
+- If 0 sessions found: display "No sessions found. Switching to questionnaire." and jump to step 4b
+
+Display: "✓ Found N sessions across M projects"
+
+**Determine data sufficiency:**
+- Count total messages available from the scan result (sum sessions across projects)
+- If 0 sessions found: Display "No sessions found. Switching to questionnaire." and jump to step 4b
+- If sessions found: Continue to step 4a
+
+---
+
+## 4a. Session Analysis Path
+
+Display: "◆ Sampling messages..."
+
+Sample messages from discovered session files:
+- Read a representative sample of messages from the discovered JSONL files (aim for ~200 messages spread across projects)
+- For each JSONL file, read lines, parse JSON, extract human/assistant message pairs
+- Skip messages containing sensitive patterns (API keys, passwords, tokens)
+- Write sampled messages to a temp file for analysis
+- Report: "Sampled N messages from M projects"
+
+Display: "✓ Sampled N messages from M projects"
+
+Display: "◆ Analyzing patterns..."
+
+<!-- TODO: ccp-user-profiler agent not yet available. The profile-user workflow currently operates without a dedicated profiler agent. -->
+
+**Analyze patterns using Task tool:**
+
+Use the Task tool to analyze the sampled session messages. Provide it with:
+- The sampled JSONL file path from profile-sample output
+
+The agent prompt should follow this structure:
+```
+Read the sampled session messages, then analyze the developer's behavioral patterns across all 8 dimensions.
+
+Session data: {temp_dir}/profile-sample.jsonl
+
+Analyze these messages and return your analysis in the <analysis> JSON format.
+```
+
+**Parse the agent's output:**
+- Extract the `<analysis>` JSON block from the agent's response
+- Save analysis JSON to a temp file (in the same temp directory created by profile-sample)
+
+```bash
+ANALYSIS_PATH="{temp_dir}/analysis.json"
+```
+
+Write the analysis JSON to `$ANALYSIS_PATH`.
+
+Display: "✓ Analysis complete (N dimensions scored)"
+
+**Check for thin data:**
+- Read the analysis JSON and check the total message count
+- If < 50 messages were analyzed: Note that a questionnaire supplement could improve accuracy. Display: "Note: Limited session data (N messages). Results may have lower confidence."
+
+Continue to step 5.
+
+---
+
+## 4b. Questionnaire Path
+
+Display: "Using questionnaire to build your profile."
+
+**Get questions:**
+
+Generate 8 behavioral dimension questions directly. For each of the 8 dimensions (Communication Style, Decision Speed, Explanation Depth, Debugging Approach, UX Philosophy, Vendor Philosophy, Frustration Triggers, Learning Style), create a question with 3-4 answer options that map to behavioral ratings.
+
+**Present each question to the user via AskUserQuestion:**
+
+For each question in the questions array:
+- header: The dimension name (e.g., "Communication Style")
+- question: The question text
+- options: The answer options from the question definition
+
+Collect all answers into an answers JSON object mapping dimension keys to selected answer values.
+
+**Save answers to temp file:**
+```bash
+ANSWERS_PATH=$(mktemp /tmp/ccp-profile-answers-XXXXXX.json)
+```
+
+Write the answers JSON to `$ANSWERS_PATH`.
+
+**Convert answers to analysis:**
+
+Convert the collected answers into an analysis JSON object. Map each answer to a behavioral rating and confidence level for its dimension. Build the same analysis JSON structure as the session analysis path produces.
+
+Save analysis JSON to a temp file:
+```bash
+ANALYSIS_PATH=$(mktemp /tmp/ccp-profile-analysis-XXXXXX.json)
+```
+
+Write the analysis JSON to `$ANALYSIS_PATH`.
+
+Continue to step 5 (skip split resolution since questionnaire handles ambiguity internally).
+
+---
+
+## 5. Split Resolution
+
+**Skip if** questionnaire-only path (splits already handled internally).
+
+Read the analysis JSON from `$ANALYSIS_PATH`.
+
+Check each dimension for `cross_project_consistent: false`.
+
+**For each split detected:**
+
+Use AskUserQuestion:
+- header: The dimension name (e.g., "Communication Style")
+- question: "Your sessions show different patterns:" followed by the split context (e.g., "CLI/backend projects -> terse-direct, Frontend/UI projects -> detailed-structured")
+- options:
+  - Rating option A (e.g., "terse-direct")
+  - Rating option B (e.g., "detailed-structured")
+  - "Context-dependent (keep both)"
+
+**If user picks a specific rating:** Update the dimension's `rating` field in the analysis JSON to the selected value.
+
+**If user picks "Context-dependent":** Keep the dominant rating in the `rating` field. Add a `context_note` to the dimension's summary describing the split (e.g., "Context-dependent: terse in CLI projects, detailed in frontend projects").
+
+Write updated analysis JSON back to `$ANALYSIS_PATH`.
+
+---
+
+## 6. Profile Write
+
+Display: "◆ Writing profile..."
+
+Generate USER-PROFILE.md from the analysis JSON:
+- Read the analysis JSON from $ANALYSIS_PATH
+- Write a structured markdown profile to ./.claude/pilot/USER-PROFILE.md containing:
+  - Header with generation timestamp and method (session-analysis or questionnaire)
+  - Table of all 8 dimensions with rating, confidence, and summary
+  - Evidence section for each dimension (from analysis data)
+  - Overall profile summary paragraph
+
+Display: "✓ Profile written to ./.claude/pilot/USER-PROFILE.md"
+
+---
+
+## 7. Result Display
+
+Read the analysis JSON from `$ANALYSIS_PATH` to build the display.
+
+**Show report card table:**
+
+```
+## Your Profile
+
+| Dimension            | Rating               | Confidence |
+|----------------------|----------------------|------------|
+| Communication Style  | detailed-structured  | HIGH       |
+| Decision Speed       | deliberate-informed  | MEDIUM     |
+| Explanation Depth    | concise              | HIGH       |
+| Debugging Approach   | hypothesis-driven    | MEDIUM     |
+| UX Philosophy        | pragmatic            | LOW        |
+| Vendor Philosophy    | thorough-evaluator   | HIGH       |
+| Frustration Triggers | scope-creep          | MEDIUM     |
+| Learning Style       | self-directed        | HIGH       |
+```
+
+(Populate with actual values from the analysis JSON.)
+
+**Show highlight reel:**
+
+Pick 3-4 dimensions with the highest confidence and most evidence signals. Format as:
+
+```
+## Highlights
+
+- **Communication (HIGH):** You consistently provide structured context with
+  headers and problem statements before making requests
+- **Vendor Choices (HIGH):** You research alternatives thoroughly -- comparing
+  docs, GitHub activity, and bundle sizes before committing
+- **Frustrations (MEDIUM):** You correct Claude most often for doing things
+  you didn't ask for -- scope creep is your primary trigger
+```
+
+Build highlights from the `evidence` array and `summary` fields in the analysis JSON. Use the most compelling evidence quotes. Format each as "You tend to..." or "You consistently..." with evidence attribution.
+
+**Offer full profile view:**
+
+Use AskUserQuestion:
+- header: "Profile"
+- question: "Want to see the full profile?"
+- options:
+  - "Yes" -- Read and display the full USER-PROFILE.md content, then continue to step 8
+  - "Continue to artifacts" -- Proceed directly to step 8
+
+---
+
+## 8. Artifact Selection (ACTV-05)
+
+Use AskUserQuestion with multiSelect:
+- header: "Artifacts"
+- question: "Which artifacts should I generate?"
+- options (ALL pre-selected by default):
+  - "/ccp:dev-preferences command file" -- "Load your preferences in any session"
+  - "CLAUDE.md profile section" -- "Add profile to this project's CLAUDE.md"
+  - "Global CLAUDE.md" -- "Add profile to $HOME/.claude/CLAUDE.md for all projects"
+
+**If no artifacts selected:** Display "No artifacts generated. Your profile is saved at ./.claude/pilot/USER-PROFILE.md" and jump to step 10.
+
+---
+
+## 9. Artifact Generation
+
+Generate selected artifacts sequentially (file I/O is fast, no benefit from parallel agents):
+
+**For /ccp:dev-preferences (if selected):**
+
+Generate a /ccp:dev-preferences command file:
+- Read the analysis JSON from $ANALYSIS_PATH
+- Create ./.claude/commands/ccp/dev-preferences.md with frontmatter (name, description) and a structured prompt that loads the user's behavioral preferences into Claude's context
+- The command content should describe the user's communication preferences, explanation depth preference, debugging style, etc. derived from the profile dimensions
+
+Display: "✓ Generated /ccp:dev-preferences at ./.claude/commands/ccp/dev-preferences.md"
+
+**For CLAUDE.md profile section (if selected):**
+
+Generate a CLAUDE.md profile section:
+- Read the analysis JSON from $ANALYSIS_PATH
+- Read the existing ./CLAUDE.md file
+- Append (or update) a "## Developer Profile" section with a concise summary of the user's behavioral dimensions
+- Write the updated CLAUDE.md back
+
+Display: "✓ Added profile section to CLAUDE.md"
+
+**For Global CLAUDE.md (if selected):**
+
+Generate a global CLAUDE.md profile section:
+- Read the analysis JSON from $ANALYSIS_PATH
+- Read $HOME/.claude/CLAUDE.md (create if it does not exist)
+- Append (or update) a "## Developer Profile" section
+- Write the updated file back
+
+Display: "✓ Added profile section to $HOME/.claude/CLAUDE.md"
+
+**Error handling:** If any step fails, display the error message and use AskUserQuestion to offer "Retry" or "Skip this artifact". On retry, re-run the step. On skip, continue to next artifact.
+
+---
+
+## 10. Summary & Refresh Diff
+
+**If --refresh path:**
+
+Read both old backup and new analysis to compare dimension ratings/confidence.
+
+Read the backed-up profile:
+```bash
+BACKUP_PATH="./.claude/pilot/USER-PROFILE.backup.md"
+```
+
+Compare each dimension's rating and confidence between old and new. Display diff table showing only changed dimensions:
+
+```
+## Changes
+
+| Dimension       | Before                      | After                        |
+|-----------------|-----------------------------|-----------------------------|
+| Communication   | terse-direct (LOW)          | detailed-structured (HIGH)  |
+| Debugging       | fix-first (MEDIUM)          | hypothesis-driven (MEDIUM)  |
+```
+
+If nothing changed: Display "No changes detected -- your profile is already up to date."
+
+**Display final summary:**
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ CCP > PROFILE COMPLETE ✓
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Your profile:    ./.claude/pilot/USER-PROFILE.md
+```
+
+Then list paths for each generated artifact:
+```
+Artifacts:
+  ✓ /ccp:dev-preferences   ./.claude/commands/ccp/dev-preferences.md
+  ✓ CLAUDE.md section       ./CLAUDE.md
+  ✓ Global CLAUDE.md        $HOME/.claude/CLAUDE.md
+```
+
+(Only show artifacts that were actually generated.)
+
+**Clean up temp files:**
+
+Remove the temp directory created by profile-sample (contains sample JSONL and analysis JSON):
+```bash
+rm -rf "$TEMP_DIR"
+```
+
+Also remove any standalone temp files created for questionnaire answers:
+```bash
+rm -f "$ANSWERS_PATH" 2>/dev/null
+rm -f "$ANALYSIS_PATH" 2>/dev/null
+```
+
+(Only clean up temp paths that were actually created during this workflow run.)
+
+</process>
+
+<success_criteria>
+- [ ] Initialization detects existing profile and handles all three responses (view/refresh/cancel)
+- [ ] Consent gate shown for session analysis path, skipped for questionnaire path
+- [ ] Session scan discovers sessions and reports statistics
+- [ ] Session analysis path: samples messages, spawns profiler agent, extracts analysis JSON
+- [ ] Questionnaire path: presents 8 questions, collects answers, converts to analysis JSON
+- [ ] Split resolution presents context-dependent splits with user resolution options
+- [ ] Profile written to USER-PROFILE.md via write-profile subcommand
+- [ ] Result display shows report card table and highlight reel with evidence
+- [ ] Artifact selection uses multiSelect with all options pre-selected
+- [ ] Artifacts generated sequentially via LLM-driven file operations
+- [ ] Refresh diff shows changed dimensions when --refresh was used
+- [ ] Temp files cleaned up on completion
+</success_criteria>