spawn

Generate PhD-level expert agent prompts for Claude Code. Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices. Triggers on: spawn agent, create agent, generate expert, new agent, agent genesis.

1.84x

Quality

—

Does it follow best practices?

Impact

94%

1.84x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

The body is highly actionable with a clear, well-sequenced workflow and validation checklist, but it is verbose with repeated scope/path detail and makes no use of progressive disclosure — everything lives in one ~300-line file with no real bundle to offload detail into.

Suggestions

Deduplicate the repeated project-vs-global path and scope/output definitions that appear in 'Agent File Format', 'Output Options', and 'Implementation Steps'; state each once and reference it.

Move the inline 10-part template and the long documentation URL list into reference files (e.g., references/agent-template.md, references/docs.md) and link to them from SKILL.md, turning the body into a lean overview.

Either ship the referenced example agents (python-expert.md, react-expert.md) in an agents/ bundle or remove the 'See ... in agents/' references so signaled references resolve to real files.

Dimension	Reasoning	Score
Conciseness	The ~300-line body is mostly instructional but repeats scope/output choices and file paths across 'Agent File Format', 'Output Options', and 'Implementation Steps', and restates doc concepts in 'Key Concepts from Documentation' — efficient in places but padded with redundancy that could be tightened.	2 / 3
Actionability	Provides concrete executable guidance: exact AskUserQuestion structure (headers/options), file paths, a YAML frontmatter template, a 10-part content template, and concrete example dialogs, matching the level-3 anchor of copy-paste-ready specifics.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (Implementation Steps 1-6, File Creation Process) with an explicit Quality Checklist validation checkpoint and a 'verify file was created' step, satisfying level-3 sequenced validation even for batch generation.	3 / 3
Progressive Disclosure	Content is monolithic — the 10-part template, documentation URL list, and examples are all inline in SKILL.md with no reference files; the referenced 'agents/python-expert.md' examples are not part of any provided bundle, so references are present but not clearly signaled and content that could be separate stays inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 description that clearly states what it does and when to invoke it with explicit, mostly-natural trigger phrases. Minor over-claim ('PhD-level') and one jargon trigger ('agent genesis') could be tightened but do not undermine clarity.

Suggestions

Soften the over-claim 'PhD-level expert' to a concrete quality bar (e.g., 'comprehensive expert agent prompts with production-ready code examples') to avoid buzzword inflation.

Replace the jargon trigger 'agent genesis' with a phrase users would actually say (e.g., 'make an expert agent').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Generate PhD-level expert agent prompts', 'Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices'), matching the level-3 anchor of several specific actions rather than a single domain mention.	3 / 3
Completeness	Explicitly answers both what (generate expert agent prompts) and when ('Triggers on: ...'), satisfying the level-3 requirement of an explicit trigger clause rather than capping at 2.	3 / 3
Trigger Term Quality	Triggers 'spawn agent, create agent, generate expert, new agent' are natural phrases a user would say; 'agent genesis' is mild jargon but overall coverage of natural terms is good, fitting the level-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The niche of generating comprehensive expert agent prompts for Claude Code is distinct and unlikely to conflict with unrelated skills, though 'create agent'/'new agent' are slightly generic triggers that lean toward level 2; the overall distinct niche keeps it at 3.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 days 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.