Initial commit
This commit is contained in:
Zhongwei Li
56
commands/analyze.md
Normal file
56
commands/analyze.md
Normal file
@@ -0,0 +1,56 @@
|
||||
# Analyze File with Ollama
|
||||
|
||||
Analyze the specified file using the ollama agent pipeline.
|
||||
|
||||
**Usage:** `/analyze <file_path> [focus_area]`
|
||||
|
||||
**Examples:**
|
||||
- `/analyze src/auth.py security` - Security analysis
|
||||
- `/analyze README.md` - General analysis
|
||||
- `/analyze implementation-plan.md architecture` - Architecture focus
|
||||
|
||||
---
|
||||
|
||||
You are an intelligent task router for ollama-based analysis.
|
||||
|
||||
**Task:** Analyze the file at path: $1
|
||||
**Focus Area:** $2
|
||||
|
||||
**Your Process:**
|
||||
|
||||
1. **Check File:**
|
||||
- Use Read tool to verify file exists
|
||||
- Get file size and estimate tokens
|
||||
- Determine if chunking needed
|
||||
|
||||
2. **Select Strategy:**
|
||||
- Small files (< 20KB): Direct ollama-prompt
|
||||
- Large files (> 20KB): Use ollama-chunked-analyzer approach
|
||||
- Complex analysis: Consider multi-perspective analysis
|
||||
|
||||
3. **Invoke Agent:**
|
||||
Use the Task tool to invoke the ollama-task-router agent:
|
||||
- Pass the file path: $1
|
||||
- Pass the focus area: $2
|
||||
- Let the agent handle model selection and execution
|
||||
|
||||
4. **Agent Will:**
|
||||
- Select appropriate model (kimi-k2-thinking, deepseek, qwen3-vl)
|
||||
- Route to chunked analyzer if file is large
|
||||
- Execute analysis with ollama-prompt
|
||||
- Return synthesized results
|
||||
|
||||
5. **Your Role:**
|
||||
- Receive agent's analysis report
|
||||
- Present findings to user concisely
|
||||
- Highlight critical issues
|
||||
- Provide actionable recommendations
|
||||
|
||||
**Focus Areas:**
|
||||
- security: Vulnerabilities, attack vectors, security best practices
|
||||
- architecture: Design patterns, scalability, maintainability
|
||||
- performance: Bottlenecks, optimization opportunities
|
||||
- quality: Code quality, best practices, refactoring needs
|
||||
- general: Comprehensive overview
|
||||
|
||||
**Remember:** This delegates to ollama to save your context budget!
|
||||
101
commands/architect.md
Normal file
101
commands/architect.md
Normal file
@@ -0,0 +1,101 @@
|
||||
# Architecture Analysis with Ollama
|
||||
|
||||
Analyze system architecture, design patterns, and structural decisions.
|
||||
|
||||
**Usage:** `/architect <file_or_directory> [aspect]`
|
||||
|
||||
**Aspects:**
|
||||
- `patterns`: Design patterns and architectural patterns
|
||||
- `scalability`: Scalability analysis
|
||||
- `security`: Security architecture
|
||||
- `dependencies`: Dependency analysis
|
||||
- `all`: Comprehensive architecture review (default)
|
||||
|
||||
**Examples:**
|
||||
- `/architect src/` - Full architecture analysis
|
||||
- `/architect docs/architecture.md patterns` - Pattern analysis
|
||||
- `/architect src/api/ scalability` - Scalability review
|
||||
|
||||
---
|
||||
|
||||
You are performing architecture analysis by orchestrating ollama agents.
|
||||
|
||||
**Target:** $1
|
||||
**Aspect:** ${2:-all}
|
||||
|
||||
**Your Process:**
|
||||
|
||||
1. **Understand Scope:**
|
||||
- Read architecture documentation if available
|
||||
- Identify key components and modules (via Glob/Grep)
|
||||
- Map dependencies and relationships
|
||||
|
||||
2. **Invoke Appropriate Agent:**
|
||||
|
||||
**Specific Aspect Analysis:**
|
||||
Use ollama-task-router agent with focused prompt:
|
||||
- Target: $1
|
||||
- Aspect: ${2:-all}
|
||||
- Request specific analysis (patterns, scalability, security, dependencies)
|
||||
|
||||
**Comprehensive Analysis (aspect=all):**
|
||||
Use ollama-parallel-orchestrator agent:
|
||||
- Perspectives: architecture, security, scalability, maintainability
|
||||
- Target: $1
|
||||
- Multi-angle deep analysis
|
||||
|
||||
3. **Analysis Framework (for agent to apply):**
|
||||
|
||||
**Structure:**
|
||||
- Separation of Concerns: Are responsibilities clearly separated?
|
||||
- Modularity: Are modules cohesive and loosely coupled?
|
||||
- Layering: Is there clear layering (presentation, business, data)?
|
||||
- Abstraction: Are abstractions at appropriate levels?
|
||||
|
||||
**Quality Attributes:**
|
||||
- Scalability: Can system handle growth?
|
||||
- Maintainability: Is code easy to modify?
|
||||
- Testability: Can components be tested independently?
|
||||
- Security: Are security principles followed?
|
||||
- Performance: Are performance requirements met?
|
||||
|
||||
**Design Principles:**
|
||||
- SOLID principles
|
||||
- DRY (Don't Repeat Yourself)
|
||||
- YAGNI (You Aren't Gonna Need It)
|
||||
- KISS (Keep It Simple)
|
||||
|
||||
4. **Your Role:**
|
||||
- Invoke appropriate agent based on aspect
|
||||
- Receive architectural analysis
|
||||
- Format findings for user
|
||||
- Highlight key insights and recommendations
|
||||
|
||||
5. **Report Format:**
|
||||
```
|
||||
## Architecture Analysis
|
||||
|
||||
**Target:** $1
|
||||
**Aspect:** ${2:-all}
|
||||
|
||||
### Architecture Overview
|
||||
- High-level structure
|
||||
- Key components
|
||||
- Design patterns identified
|
||||
|
||||
### Strengths
|
||||
- What's working well
|
||||
- Good architectural decisions
|
||||
|
||||
### Concerns
|
||||
- Architectural issues
|
||||
- Anti-patterns found
|
||||
- Technical debt
|
||||
|
||||
### Recommendations
|
||||
- Specific improvements
|
||||
- Refactoring suggestions
|
||||
- Pattern applications
|
||||
```
|
||||
|
||||
**Remember:** Delegate deep architectural analysis to agents. You focus on presenting clear, actionable insights.
|
||||
163
commands/deep-analyze.md
Normal file
163
commands/deep-analyze.md
Normal file
@@ -0,0 +1,163 @@
|
||||
# Deep Multi-Perspective Analysis
|
||||
|
||||
Comprehensive analysis using parallel orchestrator with multiple perspectives.
|
||||
|
||||
**Usage:** `/deep-analyze <file> [perspectives]`
|
||||
|
||||
**Perspectives:** (comma-separated, max 4)
|
||||
- `security`: Security vulnerabilities and threat modeling
|
||||
- `architecture`: Design patterns and structural analysis
|
||||
- `implementation`: Code quality and best practices
|
||||
- `testing`: Test coverage and validation strategies
|
||||
- `performance`: Bottlenecks and optimization opportunities
|
||||
|
||||
**Examples:**
|
||||
- `/deep-analyze implementation-plan.md` - Auto-select perspectives
|
||||
- `/deep-analyze src/auth.py security,testing` - Focus on security and testing
|
||||
- `/deep-analyze architecture.md architecture,scalability` - Architecture focused
|
||||
|
||||
---
|
||||
|
||||
You are performing deep multi-perspective analysis using the parallel orchestrator agent.
|
||||
|
||||
**Target:** $1
|
||||
**Perspectives:** ${2:-auto}
|
||||
|
||||
**Your Process:**
|
||||
|
||||
1. **Validate Target:**
|
||||
- Verify file/directory exists (use Read/Glob tools)
|
||||
- Check size and estimate tokens
|
||||
- Ensure suitable for deep analysis (not trivial files)
|
||||
|
||||
2. **Determine Perspectives:**
|
||||
|
||||
**Auto-Select (if perspectives=$ARGUMENTS or empty):**
|
||||
Based on file type:
|
||||
- Code files (.py, .js, .ts, etc.): security, quality, testing
|
||||
- Architecture docs: architecture, scalability, security
|
||||
- Implementation plans: security, architecture, implementation
|
||||
- API specs: security, architecture, performance
|
||||
|
||||
**User-Specified:**
|
||||
Parse comma-separated list from $2
|
||||
Validate 2-4 perspectives
|
||||
|
||||
3. **Invoke Parallel Orchestrator Agent:**
|
||||
|
||||
Use Task tool to invoke ollama-parallel-orchestrator:
|
||||
- Target file: $1
|
||||
- Perspectives: Parsed list (2-4 perspectives)
|
||||
- Agent will:
|
||||
* Decompose into parallel analyses
|
||||
* Execute concurrently
|
||||
* Track sessions
|
||||
* Synthesize results
|
||||
|
||||
4. **Perspectives Explained:**
|
||||
|
||||
**Security:**
|
||||
- Vulnerabilities and attack vectors
|
||||
- Threat modeling
|
||||
- Authentication/authorization
|
||||
- Input validation
|
||||
- Secrets management
|
||||
|
||||
**Architecture:**
|
||||
- Design patterns
|
||||
- Structural organization
|
||||
- Separation of concerns
|
||||
- Modularity and coupling
|
||||
- Scalability considerations
|
||||
|
||||
**Implementation:**
|
||||
- Code quality and readability
|
||||
- Best practices adherence
|
||||
- Error handling
|
||||
- Edge case coverage
|
||||
- Refactoring opportunities
|
||||
|
||||
**Testing:**
|
||||
- Test coverage assessment
|
||||
- Testing strategy
|
||||
- Edge cases and corner cases
|
||||
- Integration points
|
||||
- Test quality
|
||||
|
||||
**Performance:**
|
||||
- Bottleneck identification
|
||||
- Algorithm efficiency
|
||||
- Resource utilization
|
||||
- Caching opportunities
|
||||
- Optimization recommendations
|
||||
|
||||
5. **Your Role:**
|
||||
- Invoke ollama-parallel-orchestrator agent via Task tool
|
||||
- Receive comprehensive synthesized analysis
|
||||
- Format report for user
|
||||
- Highlight critical findings
|
||||
- Present prioritized recommendations
|
||||
|
||||
6. **Expected Report Format (from agent):**
|
||||
```
|
||||
# Deep Analysis Report
|
||||
|
||||
**Target:** $1
|
||||
**Perspectives:** [list]
|
||||
**Orchestration ID:** [id]
|
||||
|
||||
## Executive Summary
|
||||
[High-level summary across all perspectives]
|
||||
|
||||
## Critical Findings
|
||||
### Security Critical
|
||||
- [Issues requiring immediate attention]
|
||||
|
||||
### Architecture Critical
|
||||
- [Structural issues with major impact]
|
||||
|
||||
### Implementation Critical
|
||||
- [Code quality issues needing urgent fix]
|
||||
|
||||
## Analysis by Perspective
|
||||
[Detailed findings from each perspective]
|
||||
|
||||
## Cross-Perspective Insights
|
||||
[Common themes and patterns]
|
||||
|
||||
## Prioritized Recommendations
|
||||
1. [Highest priority]
|
||||
2. [Second priority]
|
||||
...
|
||||
|
||||
## Next Steps
|
||||
[Actionable items]
|
||||
```
|
||||
|
||||
7. **Session Tracking:**
|
||||
- Agent saves results to `~/.claude/orchestrations/[id].json`
|
||||
- Session includes all perspective analyses
|
||||
- Synthesis strategy applied
|
||||
- Full audit trail maintained
|
||||
|
||||
**When to Use Deep Analysis:**
|
||||
- Comprehensive code reviews
|
||||
- Architecture decision making
|
||||
- Security audits
|
||||
- Pre-production validation
|
||||
- Complex refactoring planning
|
||||
- Technical debt assessment
|
||||
|
||||
**When NOT to Use:**
|
||||
- Simple file reviews (use `/analyze` instead)
|
||||
- Quick checks (use `/review quick`)
|
||||
- Small files < 100 lines
|
||||
- Trivial changes
|
||||
|
||||
**Token Efficiency:**
|
||||
- Deep analysis delegates to ollama-parallel-orchestrator
|
||||
- Saves ~70% of Claude's context
|
||||
- Enables multiple comprehensive analyses per session
|
||||
- Parallel execution faster than sequential
|
||||
|
||||
**Remember:** This invokes the most comprehensive analysis. The parallel orchestrator handles all complexity. You just present the synthesized results clearly.
|
||||
181
commands/models.md
Normal file
181
commands/models.md
Normal file
@@ -0,0 +1,181 @@
|
||||
# Manage Ollama Models
|
||||
|
||||
Discover, list, and manage ollama models for the agent pipeline.
|
||||
|
||||
**Usage:** `/models [action] [target]`
|
||||
|
||||
**Actions:**
|
||||
- `discover`: Scan and register all installed ollama models
|
||||
- `list`: Show all registered models and capabilities
|
||||
- `check <model>`: Verify specific model availability
|
||||
- `defaults`: Show default models for each task type
|
||||
|
||||
**Examples:**
|
||||
- `/models discover` - Scan for new models
|
||||
- `/models list` - Show all models
|
||||
- `/models check kimi-k2-thinking:cloud` - Check if model available
|
||||
- `/models defaults` - Show default selections
|
||||
|
||||
---
|
||||
|
||||
You are managing the ollama model registry.
|
||||
|
||||
**Action:** ${1:-list}
|
||||
**Target:** $2
|
||||
|
||||
**Your Process:**
|
||||
|
||||
1. **Execute Action:**
|
||||
|
||||
**Discover:**
|
||||
```bash
|
||||
# Scan ollama and update registry
|
||||
~/.claude/scripts/discover-models.sh
|
||||
|
||||
# Show results
|
||||
cat ~/.claude/model-capabilities.json | python3 -c "
|
||||
import json, sys
|
||||
data = json.load(sys.stdin)
|
||||
print(f'Discovered {len(data[\"models\"])} models:')
|
||||
for model, info in data['models'].items():
|
||||
caps = ', '.join(set(info['capabilities']))
|
||||
print(f' - {model}: {caps}')
|
||||
"
|
||||
```
|
||||
|
||||
**List:**
|
||||
```bash
|
||||
# Show all models with capabilities
|
||||
cat ~/.claude/model-capabilities.json | python3 -c "
|
||||
import json, sys
|
||||
from pathlib import Path
|
||||
|
||||
registry_file = Path.home() / '.claude' / 'model-capabilities.json'
|
||||
with open(registry_file, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
|
||||
print('## Registered Models\n')
|
||||
for model, info in sorted(data['models'].items()):
|
||||
caps = ', '.join(set(info['capabilities']))
|
||||
family = info.get('family', 'unknown')
|
||||
context = info.get('context_window', 'unknown')
|
||||
cost = info.get('cost', 'unknown')
|
||||
|
||||
print(f'### {model}')
|
||||
print(f' - Family: {family}')
|
||||
print(f' - Capabilities: {caps}')
|
||||
if isinstance(context, int):
|
||||
print(f' - Context: {context:,} tokens')
|
||||
else:
|
||||
print(f' - Context: {context}')
|
||||
print(f' - Cost: {cost}')
|
||||
print()
|
||||
"
|
||||
```
|
||||
|
||||
**Check:**
|
||||
```bash
|
||||
# Check if specific model is available
|
||||
~/.claude/scripts/check-model.sh $2
|
||||
```
|
||||
|
||||
**Defaults:**
|
||||
```bash
|
||||
# Show default model selections
|
||||
cat ~/.claude/model-capabilities.json | python3 -c "
|
||||
import json, sys
|
||||
from pathlib import Path
|
||||
|
||||
registry_file = Path.home() / '.claude' / 'model-capabilities.json'
|
||||
with open(registry_file, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
|
||||
print('## Default Models by Task\n')
|
||||
defaults = data.get('user_defaults', {})
|
||||
for task, model in sorted(defaults.items()):
|
||||
print(f'- **{task}**: {model}')
|
||||
|
||||
print('\n## Task Preferences with Fallbacks\n')
|
||||
prefs = data.get('task_preferences', {})
|
||||
for task, config in sorted(prefs.items()):
|
||||
if config.get('preferred'):
|
||||
print(f'### {task}')
|
||||
print(f' Preferred: {config[\"preferred\"][0]}')
|
||||
if config.get('fallback'):
|
||||
fallbacks = config['fallback'][:3]
|
||||
print(f' Fallbacks: {\" -> \".join(fallbacks)}')
|
||||
print()
|
||||
"
|
||||
```
|
||||
|
||||
2. **Model Capability Reference:**
|
||||
|
||||
**Vision Models:**
|
||||
- qwen3-vl:235b-instruct-cloud (best vision, 262K context)
|
||||
- qwen3:1.7b (lightweight, has vision)
|
||||
|
||||
**Code Models:**
|
||||
- kimi-k2-thinking:cloud (reasoning + code, 262K context)
|
||||
- deepseek-v3.1:671b-cloud (strong code, 163K context)
|
||||
- qwen2.5-coder:3b (lightweight coder)
|
||||
|
||||
**Reasoning Models:**
|
||||
- kimi-k2-thinking:cloud (explicit thinking)
|
||||
- deepseek-v3.1:671b-cloud (strong reasoning)
|
||||
|
||||
**General Purpose:**
|
||||
- All models have general capability
|
||||
- Prefer larger models for complex tasks
|
||||
|
||||
3. **Registry Location:**
|
||||
- File: `~/.claude/model-capabilities.json`
|
||||
- Contains: Models, capabilities, defaults, task preferences
|
||||
- Auto-updated: By discover-models.sh
|
||||
|
||||
4. **Capability Taxonomy:**
|
||||
- `vision`: Image analysis, OCR, screenshots
|
||||
- `code`: Code review, refactoring, security
|
||||
- `reasoning`: Multi-step logic, complex analysis
|
||||
- `general`: General purpose tasks
|
||||
|
||||
**Common Operations:**
|
||||
|
||||
```bash
|
||||
# After installing new ollama model
|
||||
/models discover
|
||||
|
||||
# Before using specific model
|
||||
/models check deepseek-v3.1:671b-cloud
|
||||
|
||||
# See what's available
|
||||
/models list
|
||||
|
||||
# Check your defaults
|
||||
/models defaults
|
||||
```
|
||||
|
||||
**Registry Structure:**
|
||||
```json
|
||||
{
|
||||
"models": {
|
||||
"model-name": {
|
||||
"capabilities": ["code", "reasoning"],
|
||||
"context_window": 128000,
|
||||
"family": "deepseek",
|
||||
"cost": "cloud"
|
||||
}
|
||||
},
|
||||
"user_defaults": {
|
||||
"code": "kimi-k2-thinking:cloud",
|
||||
"vision": "qwen3-vl:235b-instruct-cloud"
|
||||
},
|
||||
"task_preferences": {
|
||||
"code": {
|
||||
"preferred": ["kimi-k2-thinking:cloud"],
|
||||
"fallback": ["deepseek-v3.1:671b-cloud", ...]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Remember:** Keep your model registry up to date for best agent performance!
|
||||
93
commands/review.md
Normal file
93
commands/review.md
Normal file
@@ -0,0 +1,93 @@
|
||||
# Code Review with Ollama
|
||||
|
||||
Perform comprehensive code review using ollama agents.
|
||||
|
||||
**Usage:** `/review <file_or_directory> [strictness]`
|
||||
|
||||
**Strictness Levels:**
|
||||
- `quick`: Fast review, major issues only
|
||||
- `standard`: Balanced review (default)
|
||||
- `thorough`: Deep analysis with security, quality, and architecture
|
||||
|
||||
**Examples:**
|
||||
- `/review src/auth.py` - Standard review of auth module
|
||||
- `/review src/api/ thorough` - Deep review of API directory
|
||||
- `/review main.py quick` - Quick check
|
||||
|
||||
---
|
||||
|
||||
You are performing a code review by orchestrating ollama agents.
|
||||
|
||||
**Target:** $1
|
||||
**Strictness:** ${2:-standard}
|
||||
|
||||
**Your Process:**
|
||||
|
||||
1. **Determine Scope:**
|
||||
- Single file: Direct analysis via ollama-task-router
|
||||
- Directory: Review key files (main entry points, complex modules)
|
||||
- Large codebase: Focus on changed files or critical paths
|
||||
|
||||
2. **Select Review Strategy:**
|
||||
|
||||
**Quick Review:**
|
||||
Invoke ollama-task-router agent:
|
||||
- Request: Quick code review focusing on critical bugs and security
|
||||
- Target: $1
|
||||
- Agent handles model selection and execution
|
||||
|
||||
**Standard Review:**
|
||||
Invoke ollama-task-router agent:
|
||||
- Request: Standard code review
|
||||
- Checklist: Security, quality, bugs, performance, best practices
|
||||
- Target: $1
|
||||
|
||||
**Thorough Review:**
|
||||
Invoke ollama-parallel-orchestrator agent:
|
||||
- Perspectives: security, quality, architecture, testing
|
||||
- Target: $1
|
||||
- Multi-angle comprehensive analysis
|
||||
|
||||
3. **Review Checklist (for agent to cover):**
|
||||
- Security: Injection, XSS, auth issues, secrets in code
|
||||
- Quality: Naming, structure, complexity, duplication
|
||||
- Bugs: Logic errors, edge cases, error handling
|
||||
- Performance: Inefficient algorithms, memory leaks
|
||||
- Best Practices: Language idioms, design patterns
|
||||
- Testing: Test coverage, test quality
|
||||
|
||||
4. **Your Role:**
|
||||
- Invoke appropriate agent based on strictness level
|
||||
- Receive agent's analysis
|
||||
- Format results for user
|
||||
- Prioritize findings by severity
|
||||
|
||||
5. **Report Format:**
|
||||
```
|
||||
## Code Review Summary
|
||||
|
||||
**File/Directory:** $1
|
||||
**Strictness:** ${2:-standard}
|
||||
|
||||
### Critical Issues (Fix Immediately)
|
||||
- [From agent analysis]
|
||||
|
||||
### Major Issues (Fix Soon)
|
||||
- [From agent analysis]
|
||||
|
||||
### Minor Issues (Consider Fixing)
|
||||
- [From agent analysis]
|
||||
|
||||
### Positive Observations
|
||||
- [From agent analysis]
|
||||
|
||||
### Recommendations
|
||||
- [Actionable items]
|
||||
```
|
||||
|
||||
6. **Priority Levels:**
|
||||
- CRITICAL: Security vulnerabilities, data loss risks
|
||||
- MAJOR: Bugs, performance issues, maintainability problems
|
||||
- MINOR: Style issues, minor optimizations
|
||||
|
||||
**Remember:** Agents handle the heavy analysis. You orchestrate and present results clearly.
|
||||
Reference in New Issue
Block a user