anchi-kit 1.2.3 → 1.2.6

package/.antigravity/skills/code-review/references/requesting-code-review.md

@@ -0,0 +1,105 @@
+---
+name: requesting-code-review
+description: Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches code-reviewer subagent to review implementation against plan or requirements before proceeding
+---
+
+# Requesting Code Review
+
+Dispatch code-reviewer subagent to catch issues before they cascade.
+
+**Core principle:** Review early, review often.
+
+## When to Request Review
+
+**Mandatory:**
+- After each task in subagent-driven development
+- After completing major feature
+- Before merge to main
+
+**Optional but valuable:**
+- When stuck (fresh perspective)
+- Before refactoring (baseline check)
+- After fixing complex bug
+
+## How to Request
+
+**1. Get git SHAs:**
+```bash
+BASE_SHA=$(git rev-parse HEAD~1)  # or origin/main
+HEAD_SHA=$(git rev-parse HEAD)
+```
+
+**2. Dispatch code-reviewer subagent:**
+
+Use Task tool with `code-reviewer` type, fill template at `code-reviewer.md`
+
+**Placeholders:**
+- `{WHAT_WAS_IMPLEMENTED}` - What you just built
+- `{PLAN_OR_REQUIREMENTS}` - What it should do
+- `{BASE_SHA}` - Starting commit
+- `{HEAD_SHA}` - Ending commit
+- `{DESCRIPTION}` - Brief summary
+
+**3. Act on feedback:**
+- Fix Critical issues immediately
+- Fix Important issues before proceeding
+- Note Minor issues for later
+- Push back if reviewer is wrong (with reasoning)
+
+## Example
+
+```
+[Just completed Task 2: Add verification function]
+
+You: Let me request code review before proceeding.
+
+BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
+HEAD_SHA=$(git rev-parse HEAD)
+
+[Dispatch code-reviewer subagent]
+  WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
+  PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
+  BASE_SHA: a7981ec
+  HEAD_SHA: 3df7661
+  DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
+
+[Subagent returns]:
+  Strengths: Clean architecture, real tests
+  Issues:
+    Important: Missing progress indicators
+    Minor: Magic number (100) for reporting interval
+  Assessment: Ready to proceed
+
+You: [Fix progress indicators]
+[Continue to Task 3]
+```
+
+## Integration with Workflows
+
+**Subagent-Driven Development:**
+- Review after EACH task
+- Catch issues before they compound
+- Fix before moving to next task
+
+**Executing Plans:**
+- Review after each batch (3 tasks)
+- Get feedback, apply, continue
+
+**Ad-Hoc Development:**
+- Review before merge
+- Review when stuck
+
+## Red Flags
+
+**Never:**
+- Skip review because "it's simple"
+- Ignore Critical issues
+- Proceed with unfixed Important issues
+- Argue with valid technical feedback
+
+**If reviewer wrong:**
+- Push back with technical reasoning
+- Show code/tests that prove it works
+- Request clarification
+
+See template at: requesting-code-review/code-reviewer.md

package/.antigravity/skills/code-review/references/verification-before-completion.md

@@ -0,0 +1,139 @@
+---
+name: verification-before-completion
+description: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
+---
+
+# Verification Before Completion
+
+## Overview
+
+Claiming work is complete without verification is dishonesty, not efficiency.
+
+**Core principle:** Evidence before claims, always.
+
+**Violating the letter of this rule is violating the spirit of this rule.**
+
+## The Iron Law
+
+```
+NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
+```
+
+If you haven't run the verification command in this message, you cannot claim it passes.
+
+## The Gate Function
+
+```
+BEFORE claiming any status or expressing satisfaction:
+
+1. IDENTIFY: What command proves this claim?
+2. RUN: Execute the FULL command (fresh, complete)
+3. READ: Full output, check exit code, count failures
+4. VERIFY: Does output confirm the claim?
+   - If NO: State actual status with evidence
+   - If YES: State claim WITH evidence
+5. ONLY THEN: Make the claim
+
+Skip any step = lying, not verifying
+```
+
+## Common Failures
+
+| Claim | Requires | Not Sufficient |
+|-------|----------|----------------|
+| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
+| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
+| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
+| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
+| Regression test works | Red-green cycle verified | Test passes once |
+| Agent completed | VCS diff shows changes | Agent reports "success" |
+| Requirements met | Line-by-line checklist | Tests passing |
+
+## Red Flags - STOP
+
+- Using "should", "probably", "seems to"
+- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
+- About to commit/push/PR without verification
+- Trusting agent success reports
+- Relying on partial verification
+- Thinking "just this once"
+- Tired and wanting work over
+- **ANY wording implying success without having run verification**
+
+## Rationalization Prevention
+
+| Excuse | Reality |
+|--------|---------|
+| "Should work now" | RUN the verification |
+| "I'm confident" | Confidence ≠ evidence |
+| "Just this once" | No exceptions |
+| "Linter passed" | Linter ≠ compiler |
+| "Agent said success" | Verify independently |
+| "I'm tired" | Exhaustion ≠ excuse |
+| "Partial check is enough" | Partial proves nothing |
+| "Different words so rule doesn't apply" | Spirit over letter |
+
+## Key Patterns
+
+**Tests:**
+```
+✅ [Run test command] [See: 34/34 pass] "All tests pass"
+❌ "Should pass now" / "Looks correct"
+```
+
+**Regression tests (TDD Red-Green):**
+```
+✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
+❌ "I've written a regression test" (without red-green verification)
+```
+
+**Build:**
+```
+✅ [Run build] [See: exit 0] "Build passes"
+❌ "Linter passed" (linter doesn't check compilation)
+```
+
+**Requirements:**
+```
+✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
+❌ "Tests pass, phase complete"
+```
+
+**Agent delegation:**
+```
+✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
+❌ Trust agent report
+```
+
+## Why This Matters
+
+From 24 failure memories:
+- your human partner said "I don't believe you" - trust broken
+- Undefined functions shipped - would crash
+- Missing requirements shipped - incomplete features
+- Time wasted on false completion → redirect → rework
+- Violates: "Honesty is a core value. If you lie, you'll be replaced."
+
+## When To Apply
+
+**ALWAYS before:**
+- ANY variation of success/completion claims
+- ANY expression of satisfaction
+- ANY positive statement about work state
+- Committing, PR creation, task completion
+- Moving to next task
+- Delegating to agents
+
+**Rule applies to:**
+- Exact phrases
+- Paraphrases and synonyms
+- Implications of success
+- ANY communication suggesting completion/correctness
+
+## The Bottom Line
+
+**No shortcuts for verification.**
+
+Run the command. Read the output. THEN claim the result.
+
+This is non-negotiable.

package/.antigravity/skills/common/api_key_helper.py

@@ -0,0 +1,300 @@
+#!/usr/bin/env python3
+"""
+Common API Key Detection Helper for Gemini Skills
+
+Supports both Google AI Studio and Vertex AI endpoints.
+
+API Key Detection Order:
+1. Process environment variable
+2. Project root .env file
+3. ./.cursor/.env
+4. ./.cursor/skills/.env
+5. Skill directory .env file
+
+Vertex AI Configuration:
+- GEMINI_USE_VERTEX: Set to "true" to use Vertex AI endpoint
+- VERTEX_PROJECT_ID: GCP project ID (required for Vertex AI)
+- VERTEX_LOCATION: GCP region (default: us-central1)
+"""
+
+import os
+import sys
+from pathlib import Path
+from typing import Optional, Dict, Any
+
+
+def find_api_key(skill_dir: Optional[Path] = None) -> Optional[str]:
+    """
+    Find GEMINI_API_KEY using 5-step lookup:
+    1. Process environment
+    2. Project root .env
+    3. ./.cursor/.env
+    4. ./.cursor/skills/.env
+    5. Skill directory .env
+
+    Args:
+        skill_dir: Path to skill directory (optional, auto-detected if None)
+
+    Returns:
+        API key string or None if not found
+    """
+    # Step 1: Check process environment
+    api_key = os.getenv('GEMINI_API_KEY')
+    if api_key:
+        print("✓ Using API key from environment variable", file=sys.stderr)
+        return api_key
+
+    # Determine paths
+    if skill_dir is None:
+        skill_dir = Path(__file__).parent.parent
+    project_dir = skill_dir.parent.parent.parent  # 3 levels up from skill dir
+
+    # Step 2: Check project root .env
+    project_env = project_dir / '.env'
+    if project_env.exists():
+        api_key = load_env_file(project_env)
+        if api_key:
+            print(f"✓ Using API key from {project_env}", file=sys.stderr)
+            return api_key
+
+    # Step 3: Check ./.cursor/.env
+    claude_env = project_dir / '.cursor' / '.env'
+    if claude_env.exists():
+        api_key = load_env_file(claude_env)
+        if api_key:
+            print(f"✓ Using API key from {claude_env}", file=sys.stderr)
+            return api_key
+
+    # Step 4: Check ./.cursor/skills/.env
+    claude_skills_env = project_dir / '.cursor' / 'skills' / '.env'
+    if claude_skills_env.exists():
+        api_key = load_env_file(claude_skills_env)
+        if api_key:
+            print(f"✓ Using API key from {claude_skills_env}", file=sys.stderr)
+            return api_key
+
+    # Step 5: Check skill directory .env
+    skill_env = skill_dir / '.env'
+    if skill_env.exists():
+        api_key = load_env_file(skill_env)
+        if api_key:
+            print(f"✓ Using API key from {skill_env}", file=sys.stderr)
+            return api_key
+
+    return None
+
+
+def load_env_file(env_path: Path) -> Optional[str]:
+    """
+    Load GEMINI_API_KEY from .env file
+
+    Args:
+        env_path: Path to .env file
+
+    Returns:
+        API key or None
+    """
+    try:
+        with open(env_path, 'r') as f:
+            for line in f:
+                line = line.strip()
+                if line.startswith('GEMINI_API_KEY='):
+                    # Extract value, removing quotes if present
+                    value = line.split('=', 1)[1].strip()
+                    value = value.strip('"').strip("'")
+                    if value:
+                        return value
+    except Exception as e:
+        print(f"Warning: Error reading {env_path}: {e}", file=sys.stderr)
+
+    return None
+
+
+def load_env_var(env_path: Path, var_name: str) -> Optional[str]:
+    """
+    Load a specific environment variable from .env file
+
+    Args:
+        env_path: Path to .env file
+        var_name: Name of the environment variable
+
+    Returns:
+        Variable value or None
+    """
+    try:
+        with open(env_path, 'r') as f:
+            for line in f:
+                line = line.strip()
+                if line.startswith(f'{var_name}='):
+                    value = line.split('=', 1)[1].strip()
+                    value = value.strip('"').strip("'")
+                    if value:
+                        return value
+    except Exception as e:
+        print(f"Warning: Error reading {env_path}: {e}", file=sys.stderr)
+
+    return None
+
+
+def find_env_var(var_name: str, skill_dir: Optional[Path] = None) -> Optional[str]:
+    """
+    Find environment variable using 5-step lookup (same as API key)
+
+    Args:
+        var_name: Name of environment variable
+        skill_dir: Path to skill directory (optional)
+
+    Returns:
+        Variable value or None
+    """
+    # Step 1: Check process environment
+    value = os.getenv(var_name)
+    if value:
+        return value
+
+    # Determine paths
+    if skill_dir is None:
+        skill_dir = Path(__file__).parent.parent
+    project_dir = skill_dir.parent.parent.parent
+
+    # Step 2-5: Check .env files in order
+    env_files = [
+        project_dir / '.env',
+        project_dir / '.cursor' / '.env',
+        project_dir / '.cursor' / 'skills' / '.env',
+        skill_dir / '.env'
+    ]
+
+    for env_path in env_files:
+        if env_path.exists():
+            value = load_env_var(env_path, var_name)
+            if value:
+                return value
+
+    return None
+
+
+def get_vertex_config(skill_dir: Optional[Path] = None) -> Dict[str, Any]:
+    """
+    Get Vertex AI configuration from environment variables
+
+    Args:
+        skill_dir: Path to skill directory (optional)
+
+    Returns:
+        Dictionary with Vertex AI configuration:
+        {
+            'use_vertex': bool,
+            'project_id': str or None,
+            'location': str (default: 'us-central1')
+        }
+    """
+    use_vertex_str = find_env_var('GEMINI_USE_VERTEX', skill_dir)
+    use_vertex = use_vertex_str and use_vertex_str.lower() in ('true', '1', 'yes')
+
+    config = {
+        'use_vertex': use_vertex,
+        'project_id': find_env_var('VERTEX_PROJECT_ID', skill_dir) if use_vertex else None,
+        'location': find_env_var('VERTEX_LOCATION', skill_dir) or 'us-central1'
+    }
+
+    return config
+
+
+def get_api_key_or_exit(skill_dir: Optional[Path] = None) -> str:
+    """
+    Get API key or exit with helpful error message
+
+    Args:
+        skill_dir: Path to skill directory (optional, auto-detected if None)
+
+    Returns:
+        API key string
+    """
+    api_key = find_api_key(skill_dir)
+
+    if not api_key:
+        print("\n❌ Error: GEMINI_API_KEY not found!", file=sys.stderr)
+        print("\n📋 Please set your API key using one of these methods (in priority order):", file=sys.stderr)
+
+        if skill_dir is None:
+            skill_dir = Path(__file__).parent.parent
+        project_dir = skill_dir.parent.parent.parent
+
+        print("\n1️⃣  Environment variable (recommended for development):", file=sys.stderr)
+        print("   export GEMINI_API_KEY='your-api-key'", file=sys.stderr)
+
+        print("\n2️⃣  Project root .env file:", file=sys.stderr)
+        print(f"   echo 'GEMINI_API_KEY=your-api-key' > {project_dir}/.env", file=sys.stderr)
+
+        print("\n3️⃣  .cursor/.env file:", file=sys.stderr)
+        print(f"   echo 'GEMINI_API_KEY=your-api-key' > {project_dir}/.cursor/.env", file=sys.stderr)
+
+        print("\n4️⃣  .cursor/skills/.env file (shared across all Gemini skills):", file=sys.stderr)
+        print(f"   echo 'GEMINI_API_KEY=your-api-key' > {project_dir}/.cursor/skills/.env", file=sys.stderr)
+
+        print("\n5️⃣  Skill directory .env file:", file=sys.stderr)
+        print(f"   echo 'GEMINI_API_KEY=your-api-key' > {skill_dir}/.env", file=sys.stderr)
+
+        print("\n🔑 Get your API key at: https://aistudio.google.com/apikey", file=sys.stderr)
+        print("\n💡 Tip: Add .env files to .gitignore to avoid committing API keys", file=sys.stderr)
+        sys.exit(1)
+
+    return api_key
+
+
+def get_client(skill_dir: Optional[Path] = None):
+    """
+    Get appropriate Gemini client (AI Studio or Vertex AI)
+
+    Args:
+        skill_dir: Path to skill directory (optional)
+
+    Returns:
+        genai.Client or vertexai client
+    """
+    vertex_config = get_vertex_config(skill_dir)
+
+    if vertex_config['use_vertex']:
+        # Use Vertex AI
+        import vertexai
+        from vertexai.generative_models import GenerativeModel
+
+        if not vertex_config['project_id']:
+            print("\n❌ Error: VERTEX_PROJECT_ID required when GEMINI_USE_VERTEX=true!", file=sys.stderr)
+            print("\n📋 Set your GCP project ID:", file=sys.stderr)
+            print("   export VERTEX_PROJECT_ID='your-project-id'", file=sys.stderr)
+            print("   Or add to .env file: VERTEX_PROJECT_ID=your-project-id", file=sys.stderr)
+            sys.exit(1)
+
+        print(f"✓ Using Vertex AI endpoint", file=sys.stderr)
+        print(f"  Project: {vertex_config['project_id']}", file=sys.stderr)
+        print(f"  Location: {vertex_config['location']}", file=sys.stderr)
+
+        vertexai.init(
+            project=vertex_config['project_id'],
+            location=vertex_config['location']
+        )
+
+        return {'type': 'vertex', 'config': vertex_config}
+    else:
+        # Use AI Studio
+        from google import genai
+
+        api_key = get_api_key_or_exit(skill_dir)
+        client = genai.Client(api_key=api_key)
+
+        return {'type': 'aistudio', 'client': client}
+
+
+if __name__ == '__main__':
+    # Test the API key detection
+    api_key = get_api_key_or_exit()
+    print(f"✓ Found API key: {api_key[:8]}..." + "*" * (len(api_key) - 8))
+
+    # Test Vertex AI config
+    vertex_config = get_vertex_config()
+    if vertex_config['use_vertex']:
+        print(f"\n✓ Vertex AI enabled:")
+        print(f"  Project: {vertex_config['project_id']}")
+        print(f"  Location: {vertex_config['location']}")

package/.antigravity/skills/comprehensive-review/complexity.md

@@ -0,0 +1,11 @@
+RULE:
+
+- Keep it simple, stupid (KISS)
+- Avoid premature optimization
+- Avoid deep nesting (max 3 levels)
+
+REVIEW CRITERIA:
+
+- Is this the simplest solution?
+- Is there over-engineering?
+- Cyclomatic complexity high?

package/.antigravity/skills/comprehensive-review/index.yaml

@@ -0,0 +1,19 @@
+skill_pack: comprehensive-review
+
+skills:
+  readability:
+    role: critic
+    applies_to: [/review]
+
+  maintainability:
+    role: critic
+    applies_to: [/review]
+
+  complexity:
+    role: critic
+    applies_to: [/review]
+
+  # Quality Gate aggregation
+  quality-gate:
+    requires: [readability, maintainability, complexity]
+    action: block_if_failed

package/.antigravity/skills/comprehensive-review/maintainability.md

@@ -0,0 +1,12 @@
+RULE:
+
+- Code MUST be easy to change in future
+- DRY (Don't Repeat Yourself)
+- Decoupled components
+- Config hardcoded? -> BAD
+
+REVIEW CRITERIA:
+
+- Hardcoded string/magic numbers?
+- Tight coupling between modules?
+- Duplicate logic?

package/.antigravity/skills/comprehensive-review/readability.md

@@ -0,0 +1,12 @@
+RULE:
+
+- Code MUST be readable by a junior developer
+- Variable names: Descriptive, no single letters
+- Functions: Small, single responsibility
+- Comments: Explain WHY, not WHAT
+
+REVIEW CRITERIA:
+
+- Is logic obvious?
+- Are names meaningful?
+- Is formatting consistent?