Agent Task Mapping
- Leverage native parallel subagent dispatch and 200k+ context windows where available.
Activation Conditions
Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.
Use this skill when:
- Determining which specialized agent to delegate a task to
- Reviewing agent capabilities and expertise areas
- Trying to match a specific task to an appropriate specialist
- Needing quick reference for available agents and their purposes
Available Agents
See Agent Details for comprehensive information about each agent:
- Description and specialization areas
- When to use each agent
- Typical tasks handled by each
Cross-Client Portability
This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.
- GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the
workflow in project instructions when folder discovery is unavailable.
- Claude Code: keep the folder in a local skills directory or a compatible plugin source.
- Codex: install or sync the folder into
$CODEX_HOME/skills/agent-task-mapping and restart Codex after major changes.
MCP Availability And Fallback
Preferred MCP Server: None required
- Fallback prompt: "Use the Agent Task Mapping skill without MCP. Rely on its local instructions, bundled resources, standard shell or editor tools, and direct verification. Show the evidence used before concluding."
- Do not claim an MCP operation was used when the active host does not expose it.
- Treat local files, tests, rendered outputs, logs, or screenshots as the fallback evidence path.
Anti-Patterns
- Delegating or evaluating without a scoped success condition: The output becomes hard to review and easy to overbuild.
- Skipping the evidence step: A workflow that cannot be re-checked quickly is not ready for handoff.
- Bundling unrelated subtasks together: It creates noisy prompts, weaker ownership, and avoidable integration risk.
Verification Protocol
Before claiming "skill applied successfully":
- Pass/fail: The Agent Task Mapping workflow names the agent boundary, delegated scope, and expected return artifact.
- Pass/fail: Context passed to helpers is minimal, task-local, and free of hidden expected answers.
- Pass/fail: Results are integrated only after evidence, diffs, or citations are checked by the controller.
- Pressure-test scenario: Run the workflow on two similar tasks that must not share assumptions or leaked context.
- Success metric: Zero context leakage; every delegated output is independently reviewable.
Examples & Scripts
Quick Reference
| Agent Name |
Best For |
| Code Explainer |
Analyzing and documenting existing code |
| UI Designer |
UI/UX improvements and design implementations |
| Universal Janitor |
Code cleanup, simplification, and tech debt removal |
| Critical Thinking |
Challenging assumptions and exploring alternatives |
| Next.js Expert |
Next.js 15/16+ architecture and optimizations |
| Expert React Frontend Engineer |
React 19+ patterns and best practices |
| Playwright Tester Mode |
Comprehensive testing with exploratory testing |
| Tech Writer |
Creating formal developer documentation |
| Create PRD Chat Mode |
Generating Product Requirements Documents |
| Specification |
Generating or updating specification documents |
| Plan |
Research and outlining multi-step plans |
Decision Framework
When choosing an agent for delegation:
- Identify task type: Is it documentation, testing, two-stage review (spec compliance first, then code quality), or development?
- Match to specialization: Find agent whose description aligns with task
- Check availability: Verify agent exists and has proper frontmatter configuration
- Use specific agentName: Delegate using exact name from agent's frontmatter
Task Categories
Code Analysis & Documentation
- Use Code Explainer for analyzing existing code patterns
- Use Tech Writer for formal developer documentation
- Use Specification for generating feature specifications
Code Quality & Maintenance
- Use Universal Janitor for cleanup and tech debt remediation
- Use Critical Thinking for challenging assumptions
Development Work
- Use Next.js Expert for Next.js 15/16+ architecture and optimizations
- Use Expert React Frontend Engineer for React 19+ patterns
Testing
- Use Playwright Tester Mode for comprehensive web application testing
Planning & Requirements
- Use Plan for research and outlining multi-step plans
- Use Create PRD Chat Mode for generating Product Requirements Documents
Design
- Use UI Designer for UI/UX improvements and design implementations
Related Skills
- custom-agent-usage: Use it when the workflow also needs loading and invoking custom agent definitions safely.
- subagent-delegation: Use it when the workflow also needs safe, scoped delegation to helper agents.
- subagent-driven-development: Use it when the workflow also needs plan-driven implementation with reviewer loops.
- agentic-eval: Use it when the workflow also needs rubric-driven evaluation loops.
1---
2name: agent-task-mapping
3version: "2.0"
4last_updated: 2026-09-08
5tags: [task, mapping, agents, delegation, workflow]
6description: "Map tasks to specialist agents. Use when choosing which agent for a job, comparing agent capabilities, or routing to React/Next.js/Playwright/docs/code-quality experts. Keywords: which agent, best agent for this, delegate to expert, agent capability mapping."
7metadata:
8 source: https://skillmd.com/skills/practicalswan/agent-task-mapping
9---
10
11# Agent Task Mapping
12
13- Leverage native parallel subagent dispatch and 200k+ context windows where available.
14
15
16## Activation Conditions
17
18Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.
19
20Use this skill when:
21- Determining which specialized agent to delegate a task to
22- Reviewing agent capabilities and expertise areas
23- Trying to match a specific task to an appropriate specialist
24- Needing quick reference for available agents and their purposes
25
26## Available Agents
27
28See [Agent Details](./references/agent-details.md) for comprehensive information about each agent:
29- Description and specialization areas
30- When to use each agent
31- Typical tasks handled by each
32
33<!-- MCP:START -->
34
35<!-- PORTABILITY:START -->
36## Cross-Client Portability
37
38This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.
39
40- GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the
41 workflow in project instructions when folder discovery is unavailable.
42- Claude Code: keep the folder in a local skills directory or a compatible plugin source.
43- Codex: install or sync the folder into
44 `$CODEX_HOME/skills/agent-task-mapping` and restart Codex after major changes.
45
46<!-- PORTABILITY:END -->
47
48## MCP Availability And Fallback
49
50Preferred MCP Server: None required
51
52- Fallback prompt: "Use the Agent Task Mapping skill without MCP. Rely on its local instructions, bundled resources, standard shell or editor tools, and direct verification. Show the evidence used before concluding."
53- Do not claim an MCP operation was used when the active host does not expose it.
54- Treat local files, tests, rendered outputs, logs, or screenshots as the fallback evidence path.
55
56<!-- MCP:END -->
57
58## Anti-Patterns
59
60- Delegating or evaluating without a scoped success condition: The output becomes hard to review and easy to overbuild.
61- Skipping the evidence step: A workflow that cannot be re-checked quickly is not ready for handoff.
62- Bundling unrelated subtasks together: It creates noisy prompts, weaker ownership, and avoidable integration risk.
63
64## Verification Protocol
65
66Before claiming "skill applied successfully":
67
681. Pass/fail: The Agent Task Mapping workflow names the agent boundary, delegated scope, and expected return artifact.
692. Pass/fail: Context passed to helpers is minimal, task-local, and free of hidden expected answers.
703. Pass/fail: Results are integrated only after evidence, diffs, or citations are checked by the controller.
714. Pressure-test scenario: Run the workflow on two similar tasks that must not share assumptions or leaked context.
725. Success metric: Zero context leakage; every delegated output is independently reviewable.
73
74## Examples & Scripts
75
76- [Delegation Examples](./examples/delegation-example.md) — Code examples for delegating to different agents
77- [Agent Discovery Script](./scripts/agent-discovery.js) — Node.js script to discover available agents
78
79## Quick Reference
80
81| Agent Name | Best For |
82|------------|-----------|
83| Code Explainer | Analyzing and documenting existing code |
84| UI Designer | UI/UX improvements and design implementations |
85| Universal Janitor | Code cleanup, simplification, and tech debt removal |
86| Critical Thinking | Challenging assumptions and exploring alternatives |
87| Next.js Expert | Next.js 15/16+ architecture and optimizations |
88| Expert React Frontend Engineer | React 19+ patterns and best practices |
89| Playwright Tester Mode | Comprehensive testing with exploratory testing |
90| Tech Writer | Creating formal developer documentation |
91| Create PRD Chat Mode | Generating Product Requirements Documents |
92| Specification | Generating or updating specification documents |
93| Plan | Research and outlining multi-step plans |
94
95## Decision Framework
96
97When choosing an agent for delegation:
98
991. **Identify task type**: Is it documentation, testing, two-stage review (spec compliance first, then code quality), or development?
1002. **Match to specialization**: Find agent whose description aligns with task
1013. **Check availability**: Verify agent exists and has proper frontmatter configuration
1024. **Use specific agentName**: Delegate using exact name from agent's frontmatter
103
104## Task Categories
105
106### Code Analysis & Documentation
107- Use **Code Explainer** for analyzing existing code patterns
108- Use **Tech Writer** for formal developer documentation
109- Use **Specification** for generating feature specifications
110
111### Code Quality & Maintenance
112- Use **Universal Janitor** for cleanup and tech debt remediation
113- Use **Critical Thinking** for challenging assumptions
114
115### Development Work
116- Use **Next.js Expert** for Next.js 15/16+ architecture and optimizations
117- Use **Expert React Frontend Engineer** for React 19+ patterns
118
119### Testing
120- Use **Playwright Tester Mode** for comprehensive web application testing
121
122### Planning & Requirements
123- Use **Plan** for research and outlining multi-step plans
124- Use **Create PRD Chat Mode** for generating Product Requirements Documents
125
126### Design
127- Use **UI Designer** for UI/UX improvements and design implementations
128
129
130---
131
132## Related Skills
133
134- [custom-agent-usage](../custom-agent-usage/SKILL.md): Use it when the workflow also needs loading and invoking custom agent definitions safely.
135- [subagent-delegation](../subagent-delegation/SKILL.md): Use it when the workflow also needs safe, scoped delegation to helper agents.
136- [subagent-driven-development](../subagent-driven-development/SKILL.md): Use it when the workflow also needs plan-driven implementation with reviewer loops.
137- [agentic-eval](../agentic-eval/SKILL.md): Use it when the workflow also needs rubric-driven evaluation loops.