agentleFS
Tony363Tony363/SuperClaude/.claude/skills/sc-analyze/SKILL.md

sc-analyze

Skill19 starsChanged 8 months agoMITView on GitHub

Comprehensive code analysis, quality assessment, and issue diagnosis. Use when analyzing code quality, security vulnerabilities, performance bottlenecks, architecture reviews, or troubleshooting bugs and build failures.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Recommend: - Create actionable recommendations

    line 28
  2. Very specific:

    When --troubleshoot is enabled:

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Analysis & Troubleshooting Skill

Multi-domain code analysis with issue diagnosis and resolution capabilities.

Quick Start

# Quality analysis
/sc:analyze [target] --focus quality|security|performance|architecture

# Troubleshooting mode
/sc:analyze [issue] --troubleshoot --focus bug|build|performance|deployment

# With auto-fix
/sc:analyze "TypeScript errors" --troubleshoot --focus build --fix

Behavioral Flow

  1. Discover - Categorize source files, detect languages
  2. Scan - Apply domain-specific analysis techniques
  3. Evaluate - Generate prioritized findings with severity
  4. Recommend - Create actionable recommendations
  5. Report - Present comprehensive analysis with metrics

Flags

FlagTypeDefaultDescription
--focusstringqualityquality, security, performance, architecture, bug, build, deployment
--troubleshootboolfalseEnable issue diagnosis mode
--traceboolfalseDetailed trace analysis for debugging
--fixboolfalseAuto-apply safe fixes
--depthstringstandardquick, standard, deep
--formatstringtexttext, json, report

Analysis Domains

Quality Analysis

  • Code smells and maintainability issues
  • Pattern violations and anti-patterns
  • Technical debt assessment

Security Analysis

  • Vulnerability scanning
  • Compliance validation
  • Authentication/authorization review

Performance Analysis

  • Bottleneck identification
  • Resource utilization patterns
  • Optimization opportunities

Architecture Analysis

  • Component coupling assessment
  • Dependency analysis
  • Design pattern evaluation

Troubleshooting Mode

When --troubleshoot is enabled:

FocusBehavior
bugError analysis, stack traces, code inspection
buildBuild logs, dependencies, config validation
performanceMetrics analysis, bottleneck identification
deploymentEnvironment analysis, service validation

Examples

Security Deep Dive

/sc:analyze src/auth --focus security --depth deep

Build Failure Fix

/sc:analyze "compilation errors" --troubleshoot --focus build --fix

Performance Diagnosis

/sc:analyze "slow API response" --troubleshoot --focus performance --trace

MCP Integration

PAL MCP (Always Use)

ToolWhen to UsePurpose
mcp__pal__thinkdeepComplex issuesMulti-stage investigation with hypothesis testing
mcp__pal__debugBug troubleshootingSystematic root cause analysis
mcp__pal__codereviewQuality analysisComprehensive code quality, security, performance review
mcp__pal__consensusCritical findingsMulti-model validation of security/architecture issues
mcp__pal__challengeUncertain findingsForce critical thinking on ambiguous issues
mcp__pal__apilookupDependency issuesGet current API docs for version conflicts

PAL Usage Patterns

# Deep investigation (--depth deep)
mcp__pal__thinkdeep(
    step="Investigating performance bottleneck in API layer",
    hypothesis="Database queries lack proper indexing",
    confidence="medium",
    relevant_files=["/src/api/users.py"]
)

# Security analysis (--focus security)
mcp__pal__codereview(
    review_type="security",
    findings="Authentication, authorization, injection vectors",
    issues_found=[{"severity": "high", "description": "SQL injection risk"}]
)

# Critical finding validation
mcp__pal__consensus(
    models=[
        {"model": "gpt-5.2", "stance": "for"},
        {"model": "gemini-3-pro", "stance": "against"}
    ],
    step="Evaluate: Is this a critical security vulnerability?"
)

Rube MCP (When Needed)

ToolWhen to UsePurpose
mcp__rube__RUBE_SEARCH_TOOLSExternal analysisFind security scanners, linters
mcp__rube__RUBE_MULTI_EXECUTE_TOOLIssue trackingCreate tickets for findings
mcp__rube__RUBE_REMOTE_WORKBENCHBulk analysisProcess large codebases

Rube Usage Patterns

# Find and create Jira tickets for findings
mcp__rube__RUBE_SEARCH_TOOLS(queries=[
    {"use_case": "create jira issue", "known_fields": "project:SECURITY"}
])

# Notify team of critical findings
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
    {"tool_slug": "SLACK_SEND_MESSAGE", "arguments": {"channel": "#security", "text": "Critical finding..."}}
])

Flags (Extended)

FlagTypeDefaultDescription
--pal-deepboolfalseUse PAL thinkdeep for multi-stage analysis
--pal-reviewboolfalseUse PAL codereview for comprehensive review
--consensusboolfalseUse PAL consensus for critical findings
--notifystring-Notify via Rube (slack, jira, email)
--create-ticketsboolfalseCreate tickets for findings via Rube

Tool Coordination

  • Glob - File discovery and structure analysis
  • Grep - Pattern analysis and code search
  • Read - Source inspection and config analysis
  • Bash - External tool execution
  • Write - Report generation
  • PAL MCP - Multi-model analysis, debugging, code review
  • Rube MCP - External notifications, ticket creation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.