agentskills.codes
AN

Internal helper called by /resolve. Analyzes ticket complexity (SIMPLE, MEDIUM, COMPLEX) to determine exploration depth and planning approach. Not intended for direct invocation.

Install

mkdir -p .claude/skills/analyze-ticket && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16920" && unzip -o skill.zip -d .claude/skills/analyze-ticket && rm skill.zip

Installs to .claude/skills/analyze-ticket

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Internal helper called by /resolve. Analyzes ticket complexity (SIMPLE, MEDIUM, COMPLEX) to determine exploration depth and planning approach. Not intended for direct invocation.
178 charsno explicit “when” trigger

About this skill

Analyze Ticket Skill

This skill analyzes a ticket's content to determine its complexity and decide which workflow phases are required.

Complexity Levels

LevelScoreExplorationPlanningAEPArchitect
SIMPLE0-2SkipBasicNoNo
MEDIUM3-5LightStandardPartialOptional
COMPLEX6+Full AEPDetailedFullYes

Scoring Factors

Analyze the ticket content and assign points for each applicable factor:

Technical Complexity

FactorPointsDetection Signals
Multi-component changes+2Mentions multiple services, modules, or layers
Database schema changes+2Keywords: migration, schema, table, column, index
API breaking changes+3Keywords: breaking, deprecate, remove endpoint, change contract
New external dependency+2Keywords: integrate, new library, third-party, SDK
Performance requirements+2Keywords: optimize, performance, latency, throughput
Security implications+2Keywords: auth, permission, encryption, sensitive data

Scope Indicators

FactorPointsDetection Signals
Cross-team coordination+2Mentions other teams, external dependencies
Multiple file types+1Backend + frontend, or multiple languages
Test infrastructure changes+1Keywords: test framework, CI/CD, pipeline
Documentation required+1Explicit doc requirements or public API changes

Uncertainty Factors

FactorPointsDetection Signals
Vague requirements+2Ambiguous language, missing acceptance criteria
Research needed+2Keywords: investigate, explore, POC, spike
Unknown impact+2Cannot determine affected components
No clear success criteria+1Missing "done when" or validation steps

Negative Factors (Reduce Complexity)

FactorPointsDetection Signals
Well-defined scope-1Clear, specific requirements
Single file change-1Obvious single-file fix
Existing pattern-1Similar to existing code/feature
Has acceptance criteria-1Clear validation steps provided

Label-Based Override

Certain labels can force complexity level:

Simple Labels (force SIMPLE)

  • quick-fix, typo, documentation, trivial, minor
  • Config: complexity.simple_labels

Complex Labels (force COMPLEX)

  • needs-analysis, architecture, breaking-change, migration, epic
  • Config: complexity.complex_labels

Analysis Process

Step 1: Extract Keywords

Parse ticket content for complexity signals:

  • Title
  • Description
  • Labels/Tags
  • Comments (if available)

Step 2: Calculate Base Score

Sum points from all applicable factors.

Step 3: Apply Label Override

Check for forcing labels that override calculated score.

Step 4: Determine Level

if has_simple_label:
    level = SIMPLE
elif has_complex_label:
    level = COMPLEX
elif score <= simple_threshold (default: 2):
    level = SIMPLE
elif score >= complex_threshold (default: 6):
    level = COMPLEX
else:
    level = MEDIUM

Step 5: Recommend Actions

Based on complexity level, recommend workflow phases:

SIMPLE

  • Skip exploration phase
  • Create direct implementation plan
  • No AEP methodology
  • Basic validation only

MEDIUM

  • Light exploration (1 agent, focused search)
  • Standard implementation plan
  • Partial AEP (Analyse + Plan, skip deep Explore)
  • Standard validation

COMPLEX

  • Full AEP workflow (3 parallel explore agents)
  • Invoke Architect skill for planning
  • Detailed implementation plan with phases
  • Comprehensive validation strategy

Output Format

## Complexity Analysis

### Score Breakdown

| Factor | Points | Reason |
|--------|--------|--------|
| Multi-component changes | +2 | Affects API and frontend |
| Database changes | +2 | Requires migration |
| Well-defined scope | -1 | Clear acceptance criteria |
| **Total** | **3** | |

### Classification

**Complexity Level**: MEDIUM (score: 3)

### Label Analysis
- Labels found: `feature`, `backend`
- No complexity-forcing labels detected

### Recommended Workflow

1. **Exploration**: Light (1 focused agent)
2. **Planning**: Standard approach
3. **AEP**: Partial (Analyse + Plan)
4. **Architect Skill**: Optional

### Key Concerns

- Database migration requires careful ordering
- Consider rollback strategy for schema changes

### Suggested Focus Areas

1. Existing migration patterns in codebase
2. Related API endpoints
3. Test coverage for affected components

Integration with Workflow

This skill is invoked by:

  1. /resolve command - after fetch, before workspace setup
  2. /analyze-ticket standalone command
  3. Planning phase to determine approach

Configuration

Reads from .claude/ticket-config.json:

{
  "complexity": {
    "auto_detect": true,
    "simple_labels": ["quick-fix", "typo"],
    "complex_labels": ["architecture", "migration"],
    "simple_threshold": 2,
    "complex_threshold": 6
  }
}

Exploration Guidelines by Level

SIMPLE - No Exploration

Proceed directly to implementation planning.

MEDIUM - Light Exploration

Launch 1 explore agent to:

  • Find similar existing code
  • Identify files to modify
  • Check test patterns

COMPLEX - Full AEP Exploration

Launch up to 3 parallel explore agents:

Agent 1: Implementation Patterns

  • Search for similar features
  • Find reusable code patterns
  • Identify coding conventions

Agent 2: Impact Analysis

  • Trace dependencies
  • Find all affected components
  • Check for breaking changes

Agent 3: Test Coverage

  • Find related tests
  • Check testing patterns
  • Identify test utilities

Language

Analysis output in French for user communication. Technical terms and factor names in English.

Search skills

Search the agent skills registry