PAL Analyze - Code Analysis
Systematic code analysis covering architecture, performance, maintainability, and patterns.
When to Use
- Understanding unfamiliar codebases
- Architectural review and assessment
- Performance analysis and optimization
- Code quality evaluation
- Pattern identification
- Technical debt assessment
Quick Start
# Start architecture analysis
result = mcp__pal__analyze(
step="Analyzing authentication system architecture",
step_number=1,
total_steps=2,
next_step_required=True,
findings="Beginning architecture review",
analysis_type="architecture",
output_format="detailed",
relevant_files=[
"/app/auth/service.py",
"/app/auth/middleware.py"
],
confidence="exploring"
)
Analysis Types
| Type |
Focus |
architecture |
System design, patterns, modularity |
performance |
Bottlenecks, optimization opportunities |
security |
Vulnerabilities, auth issues |
quality |
Code smells, maintainability |
general |
Comprehensive overview |
Output Formats
| Format |
Description |
summary |
High-level overview |
detailed |
In-depth analysis |
actionable |
Prioritized recommendations |
Required Parameters
| Parameter |
Type |
Description |
step |
string |
Analysis narrative |
step_number |
int |
Current step |
total_steps |
int |
Estimated total |
next_step_required |
bool |
More analysis needed? |
findings |
string |
Discoveries and insights |
Optional Parameters
| Parameter |
Type |
Description |
analysis_type |
enum |
architecture/performance/security/quality/general |
output_format |
enum |
summary/detailed/actionable |
confidence |
enum |
exploring → certain |
relevant_files |
list |
Files under analysis |
files_checked |
list |
All files examined |
issues_found |
list |
Issues with severity |
continuation_id |
string |
Continue session |
model |
string |
Override model |
Example: Performance Analysis
mcp__pal__analyze(
step="Identifying performance bottlenecks in data processing pipeline",
step_number=1,
total_steps=2,
next_step_required=True,
findings="Scanning for N+1 queries, inefficient loops, missing caching",
analysis_type="performance",
output_format="actionable",
relevant_files=[
"/app/services/data_processor.py",
"/app/models/report.py"
],
confidence="exploring"
)
What to Document in Findings
Include both strengths and concerns:
- Architecture: Patterns used, coupling, cohesion
- Performance: Complexity, caching, query patterns
- Security: Auth flows, input validation, secrets
- Quality: Duplication, naming, test coverage
Best Practices
- Be systematic - Cover all relevant aspects
- Document strengths - Not just problems
- Prioritize issues - By severity and impact
- Consider context - Team size, timeline, constraints
- Provide evidence - Reference specific code
1---2name: pal-analyze3description: Comprehensive code analysis for architecture, performance, security, and quality using PAL MCP. Use when reviewing codebases, assessing technical decisions, or planning improvements. Triggers on analysis requests, architecture reviews, or code quality assessments.4---5
6# PAL Analyze - Code Analysis
7
8Systematic code analysis covering architecture, performance, maintainability, and patterns.
9
10## When to Use
11
12- Understanding unfamiliar codebases
13- Architectural review and assessment
14- Performance analysis and optimization
15- Code quality evaluation
16- Pattern identification
17- Technical debt assessment
18
19## Quick Start
20
21```python
22# Start architecture analysis
23result = mcp__pal__analyze(
24 step="Analyzing authentication system architecture",
25 step_number=1,
26 total_steps=2,
27 next_step_required=True,
28 findings="Beginning architecture review",
29 analysis_type="architecture",
30 output_format="detailed",
31 relevant_files=[
32 "/app/auth/service.py",
33 "/app/auth/middleware.py"
34 ],
35 confidence="exploring"
36)
37```
38
39## Analysis Types
40
41| Type | Focus |
42|------|-------|
43| `architecture` | System design, patterns, modularity |
44| `performance` | Bottlenecks, optimization opportunities |
45| `security` | Vulnerabilities, auth issues |
46| `quality` | Code smells, maintainability |
47| `general` | Comprehensive overview |
48
49## Output Formats
50
51| Format | Description |
52|--------|-------------|
53| `summary` | High-level overview |
54| `detailed` | In-depth analysis |
55| `actionable` | Prioritized recommendations |
56
57## Required Parameters
58
59| Parameter | Type | Description |
60|-----------|------|-------------|
61| `step` | string | Analysis narrative |
62| `step_number` | int | Current step |
63| `total_steps` | int | Estimated total |
64| `next_step_required` | bool | More analysis needed? |
65| `findings` | string | Discoveries and insights |
66
67## Optional Parameters
68
69| Parameter | Type | Description |
70|-----------|------|-------------|
71| `analysis_type` | enum | architecture/performance/security/quality/general |
72| `output_format` | enum | summary/detailed/actionable |
73| `confidence` | enum | exploring → certain |
74| `relevant_files` | list | Files under analysis |
75| `files_checked` | list | All files examined |
76| `issues_found` | list | Issues with severity |
77| `continuation_id` | string | Continue session |
78| `model` | string | Override model |
79
80## Example: Performance Analysis
81
82```python
83mcp__pal__analyze(
84 step="Identifying performance bottlenecks in data processing pipeline",
85 step_number=1,
86 total_steps=2,
87 next_step_required=True,
88 findings="Scanning for N+1 queries, inefficient loops, missing caching",
89 analysis_type="performance",
90 output_format="actionable",
91 relevant_files=[
92 "/app/services/data_processor.py",
93 "/app/models/report.py"
94 ],
95 confidence="exploring"
96)
97```
98
99## What to Document in Findings
100
101Include both strengths and concerns:
102
103- **Architecture**: Patterns used, coupling, cohesion
104- **Performance**: Complexity, caching, query patterns
105- **Security**: Auth flows, input validation, secrets
106- **Quality**: Duplication, naming, test coverage
107
108## Best Practices
109
1101. **Be systematic** - Cover all relevant aspects
1112. **Document strengths** - Not just problems
1123. **Prioritize issues** - By severity and impact
1134. **Consider context** - Team size, timeline, constraints
1145. **Provide evidence** - Reference specific code
majiayu000