Agent skill
pm-organization-task-research
Codebase research specialist for PM task assignment. Use proactively before assigning tasks to understand existing patterns, dependencies, and implementation approaches.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/pm-organization-task-research
SKILL.md
PM Task Research
"Research before assignment - prevent misallocation and blockers."
Explore the codebase and return structured summaries for task assignment. This helps ensure tasks are assigned to the right agent with accurate complexity estimates.
When to Use
Use proactively before assigning tasks to understand:
- Existing patterns in the codebase
- Files/components the task will touch
- Potential blockers or dependencies
- Which agent should handle the task
- Complexity estimate
Research Process
- Use
Grepto find related implementations - Use
Readto examine relevant files - Use
Globto find related components - Provide a structured summary (not raw exploration)
What to Research
For Each Task
- Existing Patterns: What similar implementations exist?
- Dependencies: What files/components will this task touch?
- Blockers: Are there any blocking issues or missing dependencies?
- Agent Fit: Should this go to Developer or Tech Artist?
- Complexity Estimate: Micro/Simple/Medium/Complex based on codebase state
Agent Selection Guide
| Category | Default Agent | When to Reassign |
|---|---|---|
architectural |
developer | If visual-heavy → techartist |
functional |
developer | If shader/VFX work → techartist |
integration |
developer | - |
visual |
techartist | If logic-heavy → developer |
shader |
techartist | - |
polish |
techartist | If functional changes → developer |
Complexity Estimation
| Level | Criteria | Example |
|---|---|---|
| Micro | Single line change, config update | Fix typo, change color value |
| Simple | Single file, well-defined pattern | Add utility function, simple component |
| Medium | 2-5 files, some coordination | Add feature to existing system |
| Complex | 5+ files, new patterns, architecture | New system, refactoring, multiplayer |
Output Format
## Task Research: {TASK_ID}
### Task Summary
- **Title:** {task title}
- **Category:** {architectural|functional|visual|shader|polish|integration}
- **Description:** {brief description}
### Existing Patterns
- Pattern 1: {location} - {brief description}
- Pattern 2: {location} - {brief description}
### Dependencies
- {file/path} - {reason for dependency}
- {file/path} - {reason for dependency}
### Files That Will Be Modified
- {file/path} - {what needs to change}
- {file/path} - {what needs to change}
### Blockers
- (if none, state "No blockers identified")
- (if blockers exist, list them with severity)
### Recommended Agent
- {developer|techartist} - {justification}
### Complexity Estimate
- {Micro|Simple|Medium|Complex} - {justification}
### Implementation Notes
- Any relevant notes for the implementing agent
- Potential gotchas or areas requiring extra care
Important
- Keep analysis concise and actionable
- Don't return verbose file contents
- Focus on what the PM needs to know for assignment
- If you find critical issues, flag them prominently
- Always identify which agent should handle the task
- Be realistic about complexity estimates
See Also
- pm-organization-task-selection — Priority algorithm for selecting tasks
- dev-research-codebase-exploration — Developer codebase exploration patterns
- dev-research-pattern-finding — Pattern finding for implementations
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?