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. Its main weakness is that the capability description relies on somewhat vague qualifiers ('PhD-level', 'comprehensive', 'best practices') rather than listing more concrete specific actions. The trigger terms are well-chosen and distinctive.
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 requesting this functionality. 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 highly repetitive and verbose, restating file paths, scope options, and output formats multiple times across sections. While it provides a structured 10-part template and clear interaction examples, it lacks concrete output examples (what does a good generated agent actually look like?) and validation checkpoints in the workflow. The monolithic structure with no supporting bundle files makes it difficult to navigate despite covering a complex multi-mode generation task.
Suggestions
Eliminate redundancy by stating file paths, scope options, and output format choices once in a single reference section, then referring back to it - this alone could cut 30-40% of content.
Add a concrete truncated example of a generated agent's content (even 50-100 lines) so Claude can calibrate the expected output quality and format.
Split the 10-part template details, quality checklist, and YAML frontmatter reference into separate bundle files (e.g., TEMPLATE.md, CHECKLIST.md) to improve progressive disclosure.
Add explicit validation steps in the workflow: verify URL count meets minimum, check line count of generated content, validate YAML frontmatter parses correctly before writing to file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines with significant redundancy. File paths (project vs global) are repeated 6+ times. The YAML frontmatter fields are explained in excessive detail that Claude already knows. The documentation links section lists 12 URLs without context on which matter most. The quality checklist, output options, and implementation steps all repeat the same information in slightly different forms. | 1 / 3 |
Actionability | The 10-part template structure provides a concrete framework, and the examples show interaction flows. However, the actual code examples are minimal - mostly just file path strings rather than executable code. The skill describes what to generate but doesn't include a concrete example of a generated agent's content (even a truncated one), making it hard to calibrate quality expectations. | 2 / 3 |
Workflow Clarity | The Implementation Steps section provides a clear sequence for the three modes, and the examples illustrate the interaction flow well. However, there are no validation checkpoints - no step to verify generated content meets the 500-1000 line target, no feedback loop if URL research fails, and no error recovery if file creation fails. The Quality Checklist exists but is presented as a post-hoc verification rather than integrated into the workflow. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files to support it. References to `python-expert.md` and `react-expert.md` as benchmark agents are mentioned but not provided. The 12 documentation URLs are dumped in a flat list. Content that could be split (e.g., the 10-part template details, the YAML frontmatter reference, the quality checklist) is all inline, making the skill overwhelming to parse. | 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
3ae408c
- 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.