cursor-subagent-creator
Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents for Cursor editor specifically, following Cursor's patterns and directories (.cursor/agents/). Triggers on "cursor subagent", "cursor agent". Do NOT use for generic subagent creation outside Cursor (use subagent-creator instead).
76
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/skills-catalog/skills/(creation)/cursor-subagent-creator/SKILL.mdQuality
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 an excellent skill description that clearly defines its scope, provides explicit trigger terms, and proactively disambiguates from a related skill. It covers what the skill does, when to use it, and when NOT to use it, making it highly effective for skill selection among many options.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: creates subagents with isolated context for complex multi-step workflows, follows Cursor's patterns and directories (.cursor/agents/). Specific about what it produces and the structure involved. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates Cursor-specific AI subagents with isolated context for complex multi-step workflows) and 'when' (explicit 'Use when' clause with triggers and a 'Do NOT use' anti-trigger for disambiguation). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'cursor subagent', 'cursor agent', 'Cursor editor', 'subagent'. Also explicitly distinguishes from generic subagent creation, which helps with routing. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit disambiguation from a related skill ('use subagent-creator instead' for generic cases). The Cursor-specific scope, directory pattern (.cursor/agents/), and explicit anti-triggers make conflicts very unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%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 excellent concrete examples and templates, but is severely undermined by extreme verbosity and poor content organization. It explains many concepts Claude already understands, repeats itself (anti-patterns duplicating the AVOID list), and inlines massive amounts of reference material that should be in separate files. Trimming this to ~100-150 lines with references to pattern/example files would dramatically improve its effectiveness.
Suggestions
Cut content by 60-70%: Remove the 'What are Subagents?' explainer, the performance/cost table, the decision tree, and redundant anti-patterns section. Claude understands these concepts.
Extract the 6 common subagent patterns into a separate PATTERNS.md file and reference it with a single link from the main skill.
Move the complete examples (code-reviewer, performance-optimizer) into an EXAMPLES.md file, keeping only the quick template inline.
Add an explicit verification step to the creation workflow: after creating the file, test invocation with a sample prompt and verify the Agent delegates correctly, with guidance on fixing description if it doesn't.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Explains concepts Claude already knows (what subagents are, what isolated context means, basic concepts like kebab-case). Massive redundancy: anti-patterns section repeats the AVOID section nearly verbatim. The 'What are Subagents?' section, decision tree explanations, and performance trade-off tables add bulk without teaching Claude anything new. Six full example subagents when 1-2 would suffice. | 1 / 3 |
Actionability | Provides fully concrete, copy-paste-ready templates and examples. The file format, frontmatter fields, directory locations, naming conventions, and invocation syntax are all specific and executable. Multiple complete subagent examples with valid YAML frontmatter and markdown body content. | 3 / 3 |
Workflow Clarity | The 5-step creation process is clearly sequenced and the quality checklist provides validation. However, there are no explicit validation/verification checkpoints within the creation workflow itself—no step to test that the subagent actually works, no feedback loop for fixing issues if the Agent doesn't delegate correctly. The 'Creation Outputs' section lists what to do but lacks error recovery guidance. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. Six complete subagent examples, a full decision tree, performance tables, and extensive best practices are all inlined. The common patterns section alone could be a separate PATTERNS.md file. The content would benefit enormously from splitting examples, patterns, and reference tables into separate files with clear links. | 1 / 3 |
Total | 7 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (726 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- tech-leads-club/agent-skills
- Commit
81e7e0d
- 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.