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.
71
58%
Does it follow best practices?
Impact
94%
1.84xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/spawn/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates its purpose and includes explicit trigger terms. The main weakness is that the capability description relies on somewhat vague qualifiers ('PhD-level', 'comprehensive', 'best practices') rather than listing more concrete actions. Overall it performs well for skill selection purposes.
Suggestions
Replace vague qualifiers like 'PhD-level' and 'best practices' with more concrete actions, e.g., 'Generates agent prompts with tool-use patterns, error handling strategies, multi-step reasoning flows, and domain-specific code examples.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agent prompt generation) and some actions ('Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices'), but the actions are somewhat vague — 'detailed patterns' and 'best practices' are not concrete enough to fully qualify as specific actions. | 2 / 3 |
Completeness | Clearly answers both 'what' (generates PhD-level expert agent prompts with detailed patterns, code examples, and best practices) and 'when' (explicit 'Triggers on:' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms ('spawn agent', 'create agent', 'generate expert', 'new agent', 'agent genesis') that are natural phrases a user would say when needing this skill. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | The niche is very specific — generating expert agent prompts for Claude Code — with distinct trigger terms like 'agent genesis' and 'spawn agent' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive in scope but severely over-engineered for a SKILL.md file. It repeats information extensively (file paths, scope options, output formats appear 4-5 times each), includes lengthy conversational UI examples that aren't executable, and packs everything into a single monolithic document. The 10-part agent template is a useful structural contribution, but the surrounding content could be reduced by 60%+ without losing actionable information.
Suggestions
Reduce repetition dramatically: file paths, scope choices, and output options are each stated 4-5 times. Define them once in a reference section and refer back.
Extract the 10-part agent template, YAML frontmatter documentation, and documentation links into separate referenced files (e.g., TEMPLATE.md, REFERENCES.md) to improve progressive disclosure.
Add validation checkpoints: after generation, verify line count meets 500-1000 target, verify URL count >= 10, verify code block count >= 10. These are measurable quality gates that are currently missing.
Replace the verbose conversation-flow examples with a single concise example showing actual generated output (a truncated agent file) rather than UI interaction patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Repeats file paths (project vs global) at least 5 times, explains YAML frontmatter fields Claude already knows, includes lengthy examples of UI interaction flows that are essentially pseudocode, and restates the same information (scope choices, output options, documentation links) across multiple sections. The quality checklist duplicates requirements already stated in the generation template. | 1 / 3 |
Actionability | Provides a concrete 10-part template structure and specific file paths, but the actual code examples are minimal - mostly showing file path patterns rather than executable generation logic. The 'Implementation Steps' section describes a workflow but relies on abstract tool references (AskUserQuestion, Write tool, WebSearch) without concrete invocation syntax. The examples show conversation flows rather than executable code. | 2 / 3 |
Workflow Clarity | The implementation steps are numbered and sequenced across 3 modes, and there's a quality checklist. However, there are no validation checkpoints or feedback loops - no step to verify generated content meets the 500-1000 line target, no error recovery if URL research fails, and no verification that generated code examples are syntactically valid. The post-generation section mentions 'test agent with sample questions' but this is vague. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files for detailed content. The 10-part template, all three usage modes, complete YAML documentation, full examples, implementation steps, quality checklist, and post-generation notes are all inline. The documentation links section alone is 12 URLs that could be in a separate reference file. References to benchmark agents (python-expert.md, react-expert.md) exist but the skill itself should split its own content better. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
9f4534c
- Reviewed
Table of Contents
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.