Assesses agent capabilities by analyzing agent files and determining what tasks they can handle. Use when you need to evaluate if an existing agent can handle a task or if a new agent is needed. Reviews agent descriptions, skills, and workflows to determine capability match.
npx skills add https://github.com/majiayu000/claude-skill-registry --skill agent-capability-assessor
.cursor/agents/## Agent Capability Assessment
### Agent: [agent-name]
**File**: `.cursor/agents/[agent-name].md`
### Agent Capabilities
- [Capability 1]
- [Capability 2]
- [Capability 3]
### Task Requirements
- [Requirement 1]
- [Requirement 2]
- [Requirement 3]
### Capability Match Analysis
**Overall Match**: [Excellent/Good/Fair/Poor/No Match]
**Strengths**:
- [Strength 1]
- [Strength 2]
**Gaps**:
- [Gap 1]
- [Gap 2]
**Recommendation**: [Use existing / Create new / Enhance existing]
**Rationale**: [Explanation of recommendation]
Input: Assess if implementation-engineer can handle "Implement user login API endpoint"
Output:
## Agent Capability Assessment
### Agent: implementation-engineer
**File**: `.cursor/agents/implementation-engineer.md`
### Agent Capabilities
- Implements tasks from scrum-master
- Handles both frontend and backend implementation
- Uses api-implementer skill for API endpoints
- Submits to code review and iterates
- Commits changes when approved
### Task Requirements
- Implement API endpoint
- Handle authentication logic
- Write tests
- Submit for review
### Capability Match Analysis
**Overall Match**: Excellent
**Strengths**:
- Primary purpose is implementation
- Has api-implementer skill for API endpoints
- Handles backend implementation
- Includes review and commit workflow
**Gaps**: None
**Recommendation**: Use existing agent
**Rationale**: Implementation-engineer is perfectly suited for this task. It has the api-implementer skill and handles the full implementation workflow including review and commit.
Input: Assess if ui-ux-designer can handle "Set up PostgreSQL database schema"
Output:
## Agent Capability Assessment
### Agent: ui-ux-designer
**File**: `.cursor/agents/ui-ux-designer.md`
### Agent Capabilities
- Creates design specifications
- Focuses on UI/UX design
- Works with design systems
- Creates markdown design specs (not code)
### Task Requirements
- Set up database schema
- Create tables and relationships
- Write SQL migrations
- Configure database
### Capability Match Analysis
**Overall Match**: No Match
**Strengths**: None relevant
**Gaps**:
- Agent focuses on design, not database work
- Agent creates design specs, not code
- Agent has no database-related skills
- Task is outside agent's domain
**Recommendation**: Create new agent or use infrastructure-engineer
**Rationale**: ui-ux-designer is focused on UI/UX design work and cannot handle database schema setup. This task should be handled by infrastructure-engineer or a specialized database agent.
Input: Assess if implementation-engineer can handle "Design user dashboard layout"
Output:
## Agent Capability Assessment
### Agent: implementation-engineer
**File**: `.cursor/agents/implementation-engineer.md`
### Agent Capabilities
- Implements tasks from specifications
- Implements design specs from ui-ux-designer
- Handles implementation work
- Does not create design specs
### Task Requirements
- Design dashboard layout
- Create design specifications
- Plan responsive design
- Define component structure
### Capability Match Analysis
**Overall Match**: Poor
**Strengths**:
- Can implement designs once created
- Works with design specifications
**Gaps**:
- Agent does not create design specs
- Agent implements designs, doesn't design them
- Task requires design work, not implementation
**Recommendation**: Use ui-ux-designer instead
**Rationale**: Implementation-engineer implements designs but doesn't create them. This task requires design work, which should be handled by ui-ux-designer. Implementation-engineer would handle the implementation after design is complete.
When assessing multiple agents for a task:
## Multi-Agent Capability Assessment
### Task: [task description]
### Agent 1: [agent-name]
**Match**: [Excellent/Good/Fair/Poor]
**Recommendation**: [Use / Don't use]
### Agent 2: [agent-name]
**Match**: [Excellent/Good/Fair/Poor]
**Recommendation**: [Use / Don't use]
### Best Match: [agent-name]
**Rationale**: [Why this agent is best]
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Take majiayu000/agent-capability-assessor from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.