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

62%

Does it follow best practices?

Impact

94%

1.84x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/spawn/SKILL.md

Quality

Content

50%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.

The skill is highly actionable with concrete paths, frontmatter specs, and a detailed generation template, but it is notably verbose with redundant sections and lacks validation feedback loops for its batch file-creation operations. No bundle files exist, so referenced example agents are unverifiable.

Suggestions

Dedupe the scope/path guidance: state the project-vs-global path choice once and reference it, instead of repeating it in 'Agent File Format', 'Output Options', 'File Creation Process', and 'Implementation Steps'.

Add an explicit validation/feedback loop for batch and architecture-analysis generation: after writing each .md file, verify it parses and retry or report failures before declaring completion.

Move the long 'Claude Code Agent Documentation' link list and the 10-part template into a references/ file (e.g. AGENT_TEMPLATE.md) and link to it one level deep, rather than inlining everything in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~307-line body has multiple duplicated sections (scope/path choices repeated across 'Agent File Format', 'Output Options', 'File Creation Process', and 'Implementation Steps') and re-states subagent concepts Claude already knows, plus fluff like 'world-class' and 'PhD-level practitioner'.	2 / 5
Actionability	Provides concrete frontmatter specs, exact file paths with Windows variants, a full 10-part content template with line-count targets, and AskUserQuestion tab structures, with only minor gaps (no complete copy-paste example agent is shown).	4 / 5
Workflow Clarity	A clear numbered sequence and per-mode branches exist with a Quality Checklist gate, but batch/file-creation operations lack an explicit validate-then-fix-retry feedback loop, so the batch-validation cap of 3 applies.	3 / 5
Progressive Disclosure	Sections are well-headed, but the doc-link list and 10-part template are inlined rather than split into reference files, and the referenced agents/*.md examples are not present as bundle files.	3 / 5
	Total	12 / 20 Passed

Description

75%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.

The description clearly states what the skill does and provides explicit trigger phrases, landing solidly above midpoint on all dimensions. It is held back from top marks by vague adjectives ('PhD-level', 'comprehensive') and trigger phrasing that reads as commands rather than natural problem statements.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions (generate prompts, create 500-1000 line agents, patterns, code examples), but 'PhD-level'/'comprehensive' are partly fluff and the action list is not as exhaustive as the 5-anchor.	4 / 5
Completeness	Answers both 'what' (generate expert agent prompts) and 'when' (explicit 'Triggers on:' list), clearing the missing-trigger cap; the 'when' is a bare keyword list rather than the richer user-mention phrasing of the 5-anchor, so it sits at 4.	4 / 5
Trigger Term Quality	Five explicit natural triggers ('spawn agent', 'create agent', 'generate expert', 'new agent', 'agent genesis') give good keyword coverage, though the phrases are somewhat command-like and miss synonyms like 'build an agent'.	4 / 5
Distinctiveness Conflict Risk	The expert-agent-generation niche is mostly distinct with distinctive triggers like 'agent genesis', but generic 'create agent'/'new agent' could overlap with manual agent-creation or template skills.	4 / 5
	Total	16 / 20 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
Path: data/skills-md/0xdarkmatter/claude-mods/spawn/SKILL.md
Commit: 2f57aec

Reviewed: about 22 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.