---
Generates comprehensive development task specifications from validated investigation results for Dev agent implementation.
/plugin marketplace add resolve-io/.prism/plugin install prism-devtools@prismThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Generate a development task document for the Dev agent to implement based on validated issue and investigation.
Create a comprehensive development task that describes WHAT needs fixing and WHY, not HOW to code it. The Dev agent will use this specification to implement the actual fix.
inputs:
- Issue validation report with evidence
- Root cause analysis findings
- Affected components identified
- Business impact assessment
- QA test specification (if created)
dev_task_specification:
ticket_id: "ISSUE-{number}"
priority: "P0|P1|P2|P3"
estimated_effort: "1-2 hours|2-4 hours|1 day|2-3 days"
problem_statement: |
When {user action}, the system {current behavior}
instead of {expected behavior}, causing {impact}.
investigation_summary:
root_cause: "{Brief description of why it happens}"
affected_areas:
- "{Component/Service 1}"
- "{Component/Service 2}"
first_occurred: "{Date or version}"
frequency: "{Always|Sometimes|Under specific conditions}"
fix_requirements:
functional_requirements:
- System must {specific behavior}
- Error handling for {edge case}
- Maintain backward compatibility
non_functional_requirements:
- Performance: Response time < {threshold}
- Security: Validate {input/authorization}
- Reliability: Handle {failure scenario}
constraints:
- Minimal code changes preferred
- No breaking changes to API
- Must be deployable without downtime
suggested_approach: |
Based on investigation, consider:
- {High-level approach 1}
- {High-level approach 2}
Note: Dev agent determines actual implementation
# Dev Task: Fix for Issue #{ticket}
## Issue Summary
**Customer Impact:** {severity and scope}
**Business Priority:** {P0|P1|P2|P3}
**First Reported:** {date}
**Frequency:** {occurrence rate}
## Problem Description
### What's Happening
{Detailed description of the issue from user perspective}
### Root Cause Analysis
**Investigation Result:** {what was found}
**Component:** {affected component/service}
**Introduced:** {when/which version if known}
### Evidence
- Screenshot: {reference to validation evidence}
- Error Logs: {key error messages}
- Stack Trace: {if available}
- Reproduction Rate: {percentage}
## Requirements for Fix
### Functional Requirements
1. {Requirement 1}
2. {Requirement 2}
3. {Requirement 3}
### Technical Constraints
- {Constraint 1}
- {Constraint 2}
### Suggested Investigation Areas
- Check: {file/component 1}
- Review: {logic/flow}
- Consider: {potential approach}
## Definition of Done
- [ ] Issue no longer reproduces with validation steps
- [ ] QA test passes (will be created separately)
- [ ] No performance regression
- [ ] Code reviewed and approved
- [ ] Deployment plan documented
## Testing Requirements
- QA team will create regression test
- Dev to ensure fix doesn't break existing tests
- Manual validation in staging required
## Deployment Considerations
- Risk Level: {Low|Medium|High}
- Rollback Strategy: {approach if issues}
- Monitoring: {what to watch}
## Handoff Notes
- Support validated issue via Playwright
- QA task created for test implementation
- Architecture team consulted if needed
risk_assessment:
fix_complexity:
low: "Single line/simple logic change"
medium: "Multiple files, moderate logic"
high: "Architecture change, multiple services"
regression_risk:
low: "Isolated feature, good test coverage"
medium: "Shared component, some dependencies"
high: "Core functionality, many dependencies"
deployment_risk:
low: "Feature flag available, easy rollback"
medium: "Standard deployment, monitoring needed"
high: "Database changes, careful coordination"
sprint_planning:
story_points: {1|2|3|5|8}
acceptance_criteria:
- Customer issue resolved
- QA test passes
- No new issues introduced
- Performance maintained
dependencies:
- QA test implementation
- Environment access
- External team approval (if needed)
deliverables:
- Code fix implemented
- Tests passing
- Documentation updated
- Deployment plan ready
## Dev Team Handoff
**Ticket:** #{ticket}
**Priority:** {priority}
**Assigned to:** Dev Agent
**Summary:** Customer experiencing {issue}. Support has validated and investigated. Need fix implementation.
**Key Files:**
- Investigation report: {link}
- Validation evidence: {link}
- QA test spec: {link}
**Timeline:**
- Target Sprint: {sprint}
- Customer Commitment: {date if any}
**Questions:** Contact Support team via {channel}
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.