agent-workflow-designer

Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.

Quality

83%

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

78%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.

A tidy, well-structured body with executable quick-start commands and clean progressive disclosure into real reference files. It loses points mainly for abstract workflow/best-practice steps lacking an explicit validation feedback loop.

Suggestions

Add an explicit validate→fix→retry feedback loop to the Recommended Workflow (e.g., 'After scaffolding, dry-run; if handoff validation fails, fix the contract and re-scaffold') to reach the top workflow_clarity anchor.

Make the Recommended Workflow and Best Practices steps more concrete by attaching the actual command or contract field to each step instead of describing it abstractly.

Drop or repurpose the Overview section so it does not restate the frontmatter description, recovering tokens for more actionable detail.

Dimension	Reasoning	Score
Conciseness	The body is lean — short bullets, brief code, no over-explanation of concepts Claude already knows — but the Overview section near-duplicates the description and Core Capabilities overlaps it, so a few tokens could be trimmed.	4 / 5
Actionability	Quick Start gives copy-paste-ready, real commands (the scaffold script exists and runs), but the Recommended Workflow and Best Practices sections stay high-level and abstract rather than executable.	4 / 5
Workflow Clarity	A clear five-step Recommended Workflow sequence with dry-run and validation-gate checkpoints is present, but there is no explicit validate→fix→retry feedback loop tying checkpoints back to recovery actions.	4 / 5
Progressive Disclosure	Well-organized overview body with clearly signaled one-level-deep references to real bundle files (references/workflow-patterns.md and scripts/workflow_scaffolder.py), making navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

87%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-targeted description that concretely states capabilities and gives explicit, natural trigger guidance for a distinct niche. Only minor tightening (buzzword and synonym coverage) would push specificity and trigger quality to the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls' — with only minor coverage gaps; the 'production-grade' modifier is a mild buzzword but the actions themselves are specific.	4 / 5
Completeness	Explicitly answers both 'what' (designing multi-agent workflows with handoffs/failure handling/cost controls) and 'when' via a concrete 'Use when architecting... or refactoring...' trigger clause.	5 / 5
Trigger Term Quality	Strong natural-term coverage ('multi-step agent pipeline', 'single-agent vs multi-agent', 'refactoring an LLM workflow', 'context bloat', 'unreliable handoffs') that a user would actually say, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear multi-agent orchestration niche with distinctive triggers (handoff contracts, context bloat, single-vs-multi-agent choice) that minimize overlap with unrelated skills.	5 / 5
	Total	18 / 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-workflow-designer/SKILL.md
Commit: 19392f7

Reviewed: ~3 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.