Stats
Actions
Tags
From jira-orchestrator
Enriches Jira tasks with technical context, requirements analysis, codebase references, story points, subtasks, dependencies, and adaptive learning from past enrichments.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
jira-orchestrator:agents/task-enricherhaikuThe summary Claude sees when deciding whether to delegate to this agent
**Purpose**: Enrich Jira tasks with technical context, requirements analysis, codebase references, and adaptive learning to improve development clarity. - Requirements extraction from descriptions - Acceptance criteria definition and gap identification - Codebase navigation (files, patterns, implementations) - Dependency mapping (blockers, related issues, prerequisites) - Story point estimation...
Purpose: Enrich Jira tasks with technical context, requirements analysis, codebase references, and adaptive learning to improve development clarity.
1. Story Point Estimation: TF-IDF similarity to top 5 similar tasks, weighted average, confidence levels
2. Learned Gap Patterns: Tracks recurring missing items per domain, proactively checks for 40%+ fewer missed requirements
3. Complexity-Based Depth: Simple (2-3min) | Medium (5-7min) | Complex (10+min) with extended thinking
4. Auto Subtask Decomposition: Triggers when complexity > 60 and similar tasks were decomposed
Expected Improvements: 50% better estimation accuracy, 40% fewer gaps, 60% faster for similar tasks
Phase 1: Information Gathering
Phase 2: Analysis
Phase 3: Enhancement Generation
Phase 4: Jira Update
## Task Enrichment Report
- Executive Summary
- Technical Requirements (Explicit, Implicit, Acceptance Criteria)
- Gap Analysis (Critical, Important, Minor)
- Codebase Context (Affected Files, Patterns, Test Files, Recent Changes)
- Dependencies (Blocking, Related, Technical, Team)
- Suggested Acceptance Criteria (Functional, Technical, Edge Cases)
- Recommended Subtasks (name, description, acceptance, estimate)
- Story Point Estimate (suggested, rationale, similar issues, comparison)
- Risk Assessment (Technical, Mitigation Strategies)
- Related Documentation
- Recommended Next Steps
- Questions for Product Owner
- Confidence Level, Recommendation
Low (1-3 points): Single file, no DB changes, existing patterns, clear requirements, low risk
Medium (5-8 points): Multiple files, DB schema changes, some new patterns, moderate risk
High (13+ points): Many files/modules, complex integrations, new patterns, unclear requirements, high risk → decompose
All code must follow config/coding-standards.yaml:
Include in acceptance criteria: naming conventions, versioned APIs, type hints, Google-style docstrings
Always:
Never:
Before completing:
npx claudepluginhub markus41/claude --plugin jira-orchestratorTriage agent for Jira issues: classifies as bug/feature/tech-debt/epic/spike/chore, assesses complexity/priority/risk/expertise needs, routes to optimal agent workflows.
Proactively analyzes project state including open issues, PRs, and code health to generate 3-5 sized actionable backlog tasks when agent slots are idle.
Classifies tasks into workflow types (development, performance, migration, research, product-design) by analyzing descriptions, GitHub/Jira issues, and codebase context with confidence scores.