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).

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced instruction skill with ready-to-use templates and a verification checklist, but it is verbose and monolithic, repeating conceptual explanations and bundling every example inline rather than offloading detail to reference files.

Suggestions

Move the eight complete example subagents (verifier, debugger, security-auditor, etc.) into a separate EXAMPLES.md referenced one level deep, keeping only one or two inline as quick-start illustration.

Remove the duplicated 'Anti-Patterns to Avoid' section or fold it into the existing 'AVOID' list to eliminate near-verbatim redundancy.

Cut conceptual orientation Claude already knows ('What are Subagents?', foreground/background, and the Performance/Cost trade-off table) or compress each to one line, preserving only Cursor-specific guidance.

Dimension	Reasoning	Score
Conciseness	The body carries genuine actionable templates, but it explains concepts Claude already knows ('What are Subagents?', foreground vs background, performance/cost trade-offs) and duplicates the AVOID list with a near-identical 'Anti-Patterns to Avoid' section, plus eight largely redundant full example subagents that could be tightened.	2 / 3
Actionability	Provides copy-paste-ready frontmatter templates, a field configuration table, naming conventions, eight complete worked examples, an output-message template, and a creation-output sequence, giving concrete executable guidance.	3 / 3
Workflow Clarity	The 'Subagent Creation Process' is a clear five-step sequence and the 'Quality Checklist' acts as an explicit verification gate before finalizing, with 'Test the description' as a feedback loop.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is a monolithic ~710-line file with no reference files; the eight full examples and multiple templates are content that should be split into separate one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that uses third person, states a concrete action, and gives explicit when-to-use triggers plus disambiguation against a sibling skill. Its only weakness is specificity, since it describes one primary action rather than enumerating several concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and action ('Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows'), but lists only one main action rather than multiple distinct concrete actions, matching the score-2 anchor.	2 / 3
Completeness	Clearly answers both 'what' (creates Cursor subagents with isolated context) and 'when' ('Use when creating subagents for Cursor editor specifically... Triggers on...'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Explicit natural triggers ('Triggers on "cursor subagent", "cursor agent"') are exactly the phrases a user would say, giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear Cursor niche ('following Cursor's patterns and directories (.cursor/agents/)') and explicitly disambiguates from the sibling skill ('Do NOT use for generic subagent creation outside Cursor (use subagent-creator instead)'), making conflict unlikely.	3 / 3
	Total	11 / 12 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
skill_md_line_count	SKILL.md is long (726 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: tech-leads-club/agent-skills
Commit: 9026164

Reviewed: 4 days 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.