agent-designer

Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Tight, well-sequenced content with strong validation checkpoints and feedback loops. The main weakness is bundle integrity: the three core scripts the workflow invokes and the expected_outputs/ directory referenced for verification are not present in the skill folder.

Suggestions

Bundle the three referenced scripts (agent_planner.py, tool_schema_generator.py, agent_evaluator.py) into the skill, or state explicitly where they live — the workflow commands cannot run as written because these files are missing.

Ship the expected_outputs/ directory referenced in the verification loop, or replace that step with a concrete schema-shape check that does not depend on files absent from the bundle.

Add a short note in the Workflow intro confirming the scripts are bundled at the skill root so users know the commands are runnable without locating the tools elsewhere.

Dimension	Reasoning	Score
Conciseness	Lean and directive throughout — 'The scripts are the workflow — do not freehand an architecture when the planner can score one from requirements' — with a dense pattern table and no explaining of concepts Claude already knows.	5 / 5
Actionability	Commands are concrete and copy-paste ready with flags and output schemas ('python3 agent_planner.py requirements.json --format json -o arch'), but the three referenced scripts are absent from the bundle so they will not execute as written — a gap that keeps it from fully executable.	4 / 5
Workflow Clarity	Clear four-step sequence with explicit validation gates ('Gate: every tool must print ✓ Valid'), a feedback loop ('apply the top item... re-run the pilot, and re-evaluate'), and a verification checklist — matching the top anchor.	5 / 5
Progressive Disclosure	Good structure with one-level-deep references to real files (references/*.md all exist), but several referenced paths — agent_planner.py, tool_schema_generator.py, agent_evaluator.py, and expected_outputs/ — are dead links in the actual bundle, a navigation gap that prevents a 5.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-scoped description: concrete actions, natural example triggers, explicit what/when, and clear disambiguation from neighboring skills. No padding or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'design a multi-agent system', 'pick an orchestration pattern (supervisor/swarm/pipeline)', 'generate tool schemas for agents', 'evaluate agent execution logs for cost, latency, and failure bottlenecks' — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both what (design, schema-generate, evaluate multi-agent systems) and when ('Use when the user asks to...') with concrete trigger phrases, plus negative-scope guidance.	5 / 5
Trigger Term Quality	Natural trigger phrases ('design an agent architecture', 'generate Anthropic tool schemas', 'analyze these agent run logs for bottlenecks') are given as example user utterances, covering synonyms and concrete phrasings users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (multi-agent system architecture) with explicit NOT-for clauses naming sibling skills (workflow-builder, agent-workflow-designer, agenthub), minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: engineering/skills/agent-designer/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.