subagent-creator
Guide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent, specialized agent, verifier, debugger, or orchestrator that requires isolated context and deep specialization. Works with any agent that supports subagent delegation. Triggers on "create subagent", "new agent", "specialized assistant", "create verifier". Do NOT use for Cursor-specific subagents (use cursor-subagent-creator instead).
86
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that excels across all dimensions. It clearly defines what the skill does, when to use it, includes natural trigger terms, and explicitly distinguishes itself from a related skill (cursor-subagent-creator). The exclusion clause is a particularly effective touch for reducing conflict risk in a multi-skill environment.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple concrete actions and concepts: creating AI subagents, isolated context, multi-step workflows, and specifies roles like verifier, debugger, orchestrator. It also clarifies what it does NOT do (Cursor-specific subagents). | 3 / 3 |
Completeness | Clearly answers both 'what' (guide for creating AI subagents with isolated context for complex multi-step workflows) and 'when' (explicit 'Use when' clause with specific scenarios, plus explicit trigger terms and a 'Do NOT use' exclusion clause). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'create subagent', 'new agent', 'specialized assistant', 'create verifier', 'debugger', 'orchestrator'. These are terms users would naturally use, and the explicit trigger list is very helpful. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (general subagent creation) and an explicit exclusion clause differentiating it from the Cursor-specific variant. The trigger terms are specific to subagent/agent creation, reducing conflict risk with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent concrete examples and templates that Claude can directly use. Its main weaknesses are verbosity (explaining concepts Claude already knows, four full pattern examples inline) and missing validation/feedback loops in the creation workflow. Tightening the content and adding explicit verification steps would significantly improve it.
Suggestions
Add an explicit validation step after subagent creation (e.g., 'Test by invoking the subagent with a sample task and verify it delegates correctly and produces expected output format').
Move the four common subagent patterns to a separate PATTERNS.md file and reference it from the main skill, keeping only one example inline.
Remove the 'What are Subagents?' section and the subagent-vs-skill decision tree—Claude already understands these concepts and the skill description provides sufficient context for when to use it.
Condense the metadata configuration section by combining the examples into a single annotated frontmatter block rather than separate subsections for each field.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations (e.g., 'What are Subagents?' section explaining concepts Claude already knows, the decision tree for subagents vs skills). The common patterns section is useful but verbose—four full examples when two would suffice. The content could be tightened by ~30%. | 2 / 3 |
Actionability | Provides fully concrete, copy-paste-ready markdown templates with frontmatter metadata, multiple complete subagent examples, specific good/bad description examples, and a clear output message format. The guidance is specific and executable rather than abstract. | 3 / 3 |
Workflow Clarity | The creation process has clear numbered steps (Define Purpose → Configure Metadata → Write Prompt), but lacks validation checkpoints. There's a quality checklist at the end but no explicit 'validate before proceeding' step or feedback loop for testing that the subagent works correctly after creation. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's monolithic—all four common patterns, best practices, and the full creation process are inline. The patterns section and detailed metadata configuration could be split into referenced files to keep the main skill leaner. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- tech-leads-club/agent-skills
- Commit
906a57d
- 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.