@cloudstreamsoftware/claude-tools 1.2.3 → 1.2.5

package/commands/instinct-export.md

@@ -0,0 +1,123 @@
+---
+description: Export instincts for sharing with teammates or other projects
+---
+
+# /instinct-export - Export Learned Instincts
+
+Exports instincts to a shareable format. Perfect for:
+- Sharing with teammates
+- Transferring to a new machine
+- Contributing to project conventions
+- Client knowledge handoff (sanitized)
+
+## When to Use
+
+- Before onboarding a new team member
+- When setting up a new development machine
+- To share learned patterns with the CloudStream team
+- During client handoff to capture project-specific conventions
+
+## Usage
+
+```bash
+/instinct-export                           # Export all personal instincts
+/instinct-export --domain testing          # Export only testing instincts
+/instinct-export --min-confidence 0.7      # Only export high-confidence instincts
+/instinct-export --output team-instincts.yaml
+/instinct-export --format json             # Export as JSON instead of YAML
+```
+
+## Process
+
+1. Read instincts from `~/.claude/homunculus/instincts/personal/`
+2. Filter based on flags
+3. Strip sensitive information:
+   - Remove session IDs
+   - Remove file paths (keep only patterns)
+   - Remove timestamps older than "last week"
+4. Generate export file
+
+## Output Format
+
+Creates a YAML file (default):
+
+```yaml
+# Instincts Export
+# Generated: 2026-01-27
+# Source: personal
+# Count: 12 instincts
+
+version: "2.0"
+exported_by: "continuous-learning-v2"
+export_date: "2026-01-27T10:30:00Z"
+
+instincts:
+  - id: prefer-functional-style
+    trigger: "when writing new functions"
+    action: "Use functional patterns over classes"
+    confidence: 0.8
+    domain: code-style
+    observations: 8
+
+  - id: test-first-workflow
+    trigger: "when adding new functionality"
+    action: "Write test first, then implementation"
+    confidence: 0.9
+    domain: testing
+    observations: 12
+
+  - id: grep-before-edit
+    trigger: "when modifying code"
+    action: "Search with Grep, confirm with Read, then Edit"
+    confidence: 0.7
+    domain: workflow
+    observations: 6
+```
+
+## Privacy Considerations
+
+### Exports include:
+- Trigger patterns
+- Actions
+- Confidence scores
+- Domains
+- Observation counts
+
+### Exports do NOT include:
+- Actual code snippets
+- File paths
+- Session transcripts
+- Personal identifiers
+- Client-specific data
+
+## Flags
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `--domain <name>` | Export only specified domain | all |
+| `--min-confidence <n>` | Minimum confidence threshold | 0.3 |
+| `--output <file>` | Output file path | instincts-export-YYYYMMDD.yaml |
+| `--format <yaml\|json\|md>` | Output format | yaml |
+| `--include-evidence` | Include evidence text | excluded |
+
+## CloudStream Integration
+
+For client knowledge capture during handoff:
+
+```bash
+# Export high-confidence client patterns
+/instinct-export --min-confidence 0.7 --output client-patterns.yaml
+
+# Review before sharing
+cat client-patterns.yaml
+
+# Import into new client project
+/instinct-import client-patterns.yaml
+```
+
+## Related Commands
+
+- `/instinct-status` - View current instincts
+- `/instinct-import` - Import instincts from teammates
+- `/handoff` - Generate client handoff documentation
+- `/learn` - Manually capture patterns

package/commands/instinct-import.md

@@ -0,0 +1,150 @@
+---
+description: Import instincts from teammates, Skill Creator, or other sources
+---
+
+# /instinct-import - Import Learned Instincts
+
+Import instincts from:
+- Teammates' exports
+- Skill Creator (repo analysis)
+- Community collections
+- Previous machine backups
+
+## When to Use
+
+- When onboarding to a new project
+- Setting up a new development machine
+- Receiving knowledge from teammates
+- Importing client-specific patterns
+
+## Usage
+
+```bash
+/instinct-import team-instincts.yaml
+/instinct-import https://github.com/org/repo/instincts.yaml
+/instinct-import --from-skill-creator acme/webapp
+/instinct-import --dry-run team-instincts.yaml    # Preview without importing
+```
+
+## Import Process
+
+```
+📥 Importing instincts from: team-instincts.yaml
+================================================
+
+Found 12 instincts to import.
+
+Analyzing conflicts...
+
+## New Instincts (8)
+These will be added:
+  ✓ use-zod-validation (confidence: 0.7)
+  ✓ prefer-named-exports (confidence: 0.65)
+  ✓ test-async-functions (confidence: 0.8)
+  ...
+
+## Duplicate Instincts (3)
+Already have similar instincts:
+  ⚠️ prefer-functional-style
+     Local: 0.8 confidence, 12 observations
+     Import: 0.7 confidence
+     → Keep local (higher confidence)
+
+  ⚠️ test-first-workflow
+     Local: 0.75 confidence
+     Import: 0.9 confidence
+     → Update to import (higher confidence)
+
+## Conflicting Instincts (1)
+These contradict local instincts:
+  ❌ use-classes-for-services
+     Conflicts with: avoid-classes
+     → Skip (requires manual resolution)
+
+---
+Import 8 new, update 1, skip 3?
+```
+
+## Merge Strategies
+
+### For Duplicates
+When importing an instinct that matches an existing one:
+- **Higher confidence wins**: Keep the one with higher confidence
+- **Merge evidence**: Combine observation counts
+- **Update timestamp**: Mark as recently validated
+
+### For Conflicts
+When importing an instinct that contradicts an existing one:
+- **Skip by default**: Don't import conflicting instincts
+- **Flag for review**: Mark both as needing attention
+- **Manual resolution**: User decides which to keep
+
+## Source Tracking
+
+Imported instincts are marked with:
+
+```yaml
+source: "inherited"
+imported_from: "team-instincts.yaml"
+imported_at: "2026-01-27T10:30:00Z"
+original_source: "session-observation"  # or "repo-analysis"
+```
+
+## Skill Creator Integration
+
+When importing from Skill Creator:
+
+```bash
+/instinct-import --from-skill-creator acme/webapp
+```
+
+This fetches instincts generated from repo analysis:
+- Source: `repo-analysis`
+- Higher initial confidence (0.7+)
+- Linked to source repository
+
+## Flags
+
+| Flag | Description |
+|------|-------------|
+| `--dry-run` | Preview without importing |
+| `--force` | Import even if conflicts exist |
+| `--merge-strategy <higher\|local\|import>` | How to handle duplicates |
+| `--from-skill-creator <owner/repo>` | Import from Skill Creator analysis |
+| `--min-confidence <n>` | Only import instincts above threshold |
+
+## Output
+
+After import:
+
+```
+✅ Import complete!
+
+Added: 8 instincts
+Updated: 1 instinct
+Skipped: 3 instincts (2 duplicates, 1 conflict)
+
+New instincts saved to: ~/.claude/homunculus/instincts/inherited/
+
+Run /instinct-status to see all instincts.
+```
+
+## CloudStream Integration
+
+For client project onboarding:
+
+```bash
+# Import team conventions
+/instinct-import cloudstream-conventions.yaml
+
+# Import client-specific patterns (if available)
+/instinct-import client-patterns.yaml --dry-run
+/instinct-import client-patterns.yaml
+```
+
+## Related Commands
+
+- `/instinct-status` - View current instincts
+- `/instinct-export` - Export instincts for sharing
+- `/client-switch` - Switch client context
+- `/onboard` - New project setup wizard

package/commands/instinct-status.md

@@ -0,0 +1,111 @@
+---
+description: View all learned instincts with confidence scores grouped by domain
+---
+
+# /instinct-status - View Learned Instincts
+
+The `/instinct-status` command displays all learned instincts with their confidence scores, grouped by domain.
+
+## When to Use
+
+- Review what patterns Claude has learned from your sessions
+- Identify low-confidence instincts that need reinforcement
+- Before exporting instincts to share with teammates
+- To understand which domains have the most learned behaviors
+
+## Usage
+
+```bash
+/instinct-status                           # Show all instincts
+/instinct-status --domain testing          # Filter by domain
+/instinct-status --low-confidence          # Show instincts below 50%
+/instinct-status --high-confidence         # Show instincts 70%+
+/instinct-status --source repo-analysis    # Filter by source
+/instinct-status --json                    # Output as JSON
+```
+
+## Output Format
+
+```
+INSTINCT STATUS
+===============
+
+## Code Style (4 instincts)
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+prefer-functional-style
+  Trigger: when writing new functions
+  Action: Use functional patterns over classes
+  Confidence: ████████░░ 80%
+  Source: session-observation
+  Observations: 12
+
+use-early-returns
+  Trigger: when handling edge cases
+  Action: Return early instead of nested conditionals
+  Confidence: ███████░░░ 70%
+  Source: session-observation
+  Observations: 8
+
+## Testing (3 instincts)
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+test-first-workflow
+  Trigger: when adding new functionality
+  Action: Write test first, then implementation
+  Confidence: █████████░ 90%
+  Source: inherited
+  Observations: 15
+
+## Workflow (2 instincts)
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+grep-before-edit
+  Trigger: when modifying code
+  Action: Search with Grep, confirm with Read, then Edit
+  Confidence: ███████░░░ 70%
+  Source: session-observation
+  Observations: 6
+
+---
+SUMMARY
+Total Instincts: 9
+  Personal: 6
+  Inherited: 3
+Observer: Running (last analysis: 5 min ago)
+```
+
+## Available Filters
+
+| Flag | Description |
+|------|-------------|
+| `--domain <name>` | Filter by domain (code-style, testing, git, workflow) |
+| `--low-confidence` | Show instincts below 50% confidence |
+| `--high-confidence` | Show instincts 70% or higher |
+| `--source <type>` | Filter by source (session-observation, repo-analysis, inherited) |
+| `--json` | Export results as JSON for programmatic integration |
+
+## Domain Categories
+
+- **code-style** - Formatting, naming, patterns
+- **testing** - Test patterns, coverage practices
+- **workflow** - File operations, command sequences
+- **git** - Commit practices, branching
+- **architecture** - Structure, organization
+- **security** - Security practices, input validation
+
+## Confidence Levels
+
+| Range | Meaning |
+|-------|---------|
+| 0.3 - 0.5 | Observed but not yet validated |
+| 0.5 - 0.7 | Growing confidence through repetition |
+| 0.7 - 0.9 | Well-established pattern |
+| 0.9+ | Core workflow, highly reliable |
+
+## Related Commands
+
+- `/instinct-export` - Export instincts for sharing
+- `/instinct-import` - Import instincts from teammates
+- `/evolve` - Cluster instincts into higher-level structures
+- `/learn` - Manually capture patterns

package/commands/learn.md

@@ -0,0 +1,75 @@
+---
+name: learn
+description: Analyze current session and extract reusable patterns worth saving as skills. Critical for consultancy knowledge capture.
+---
+
+# /learn - Extract Reusable Patterns
+
+Analyze the current session and extract any patterns worth saving as skills.
+
+## Trigger
+
+Run `/learn` at any point during a session when you've solved a non-trivial problem.
+
+## What to Extract
+
+Look for:
+
+1. **Error Resolution Patterns**
+   - What error occurred?
+   - What was the root cause?
+   - What fixed it?
+   - Is this reusable for similar errors?
+
+2. **Debugging Techniques**
+   - Non-obvious debugging steps
+   - Tool combinations that worked
+   - Diagnostic patterns
+
+3. **Workarounds**
+   - Library quirks
+   - API limitations
+   - Version-specific fixes
+
+4. **Project-Specific Patterns**
+   - Codebase conventions discovered
+   - Architecture decisions made
+   - Integration patterns
+
+## Output Format
+
+Create a skill file at `~/.claude/skills/learned/[pattern-name].md`:
+
+```markdown
+# [Descriptive Pattern Name]
+
+**Extracted:** [Date]
+**Context:** [Brief description of when this applies]
+
+## Problem
+[What problem this solves - be specific]
+
+## Solution
+[The pattern/technique/workaround]
+
+## Example
+[Code example if applicable]
+
+## When to Use
+[Trigger conditions - what should activate this skill]
+```
+
+## Process
+
+1. Review the session for extractable patterns
+2. Identify the most valuable/reusable insight
+3. Draft the skill file
+4. Ask user to confirm before saving
+5. Save to `~/.claude/skills/learned/`
+
+## Notes
+
+- Don't extract trivial fixes (typos, simple syntax errors)
+- Don't extract one-time issues (specific API outages, etc.)
+- Focus on patterns that will save time in future sessions
+- Keep skills focused - one pattern per skill

package/commands/onboard.md

@@ -0,0 +1,133 @@
+---
+name: onboard
+description: Interactive setup wizard for new users. Guides through prerequisites, installation verification, and first steps with CloudStream Claude Tools.
+---
+
+# Onboard Command
+
+Interactive wizard to help new users get set up with CloudStream Claude Tools.
+
+## Instructions
+
+When user runs `/onboard`, guide them through an interactive setup process.
+
+### Wizard Flow
+
+**Step 1: Welcome & Prerequisites**
+```
+Welcome to CloudStream Claude Code!
+
+Let's get you set up. This takes about 15 minutes.
+
+[1/6] Checking prerequisites...
+```
+
+Check and report:
+- Node.js version (18+ required)
+- Git configured
+- npm/yarn/pnpm available
+
+If any fail, provide specific instructions to fix.
+
+**Step 2: Repository Check**
+```
+[2/6] Checking repository setup...
+```
+
+Verify:
+- In a git repository
+- Has upstream remote configured
+- Is a fork of the central repo
+
+If not configured, guide through:
+```
+To set up upstream, run:
+  git remote add upstream https://github.com/CloudStreamSoftware/css_claude_code.git
+```
+
+**Step 3: Dependency Check**
+```
+[3/6] Checking dependencies...
+```
+
+Verify:
+- node_modules exists
+- All dependencies installed
+
+If missing:
+```
+Dependencies not installed. Run:
+  npm install
+```
+
+**Step 4: Credential Setup**
+```
+[4/6] Checking credentials...
+```
+
+Check for `~/.claude/.env`:
+- If exists, verify it has content
+- If missing, guide through creation
+
+Provide template:
+```
+Create ~/.claude/.env with:
+  GITHUB_TOKEN=your_github_token
+
+Ask your team lead for additional credentials needed for your client projects.
+```
+
+**Step 5: Health Check**
+```
+[5/6] Running health check...
+```
+
+Run `/health-check` internally and report results.
+
+**Step 6: Next Steps**
+```
+[6/6] Setup complete!
+
+Your system is ready. Here's what to do next:
+
+1. Start the tutorial:
+   /tutorial
+
+2. Review documentation:
+   - README.md (overview)
+   - GETTING-STARTED.md (detailed setup)
+   - docs/DAY-ONE-CHECKLIST.md (first day guide)
+
+3. When ready for client work:
+   /client-switch [client-name]
+
+Questions? Ask your team buddy or post in #claude-code channel.
+```
+
+## Arguments
+
+$ARGUMENTS can be:
+- (none) - Run full wizard
+- `--skip-checks` - Skip prerequisite checks (for re-running)
+- `--status` - Show current setup status without wizard
+
+## Examples
+
+```
+/onboard              # Full interactive wizard
+/onboard --status     # Just show current status
+```
+
+## When to Use
+
+- First time setting up CloudStream Claude Tools
+- After cloning to a new machine
+- When helping a teammate get set up
+- To verify setup is complete
+
+## Related Commands
+
+- `/health-check` - Quick health verification
+- `/diagnose` - Deep troubleshooting
+- `/tutorial` - Start learning the system
+- `/verify` - Verify tutorial setup