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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/skills-catalog/skills/(creation)/cursor-subagent-creator/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

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

Highly actionable content with concrete Cursor-specific paths, field documentation, and copy-paste-ready templates, undermined by significant verbosity and a monolithic structure. Roughly a third of the body is duplicate templates or generic example prompts that belong in separate reference files.

Suggestions

Move the six 'Common Subagent Patterns' and two 'Complete Examples' into a references/examples.md file and keep only one or two short representative examples inline, cutting the body by roughly half.

Collapse the three near-identical template blocks (File Format, Recommended structure, Quick Template) into a single template, and merge the 'DO/AVOID' list with the 'Anti-Patterns to Avoid' section that repeats it verbatim.

Embed per-step validation in the creation workflow (e.g., after configuring frontmatter, verify required fields and kebab-case naming before proceeding) instead of only a final checklist.

Dimension	Reasoning	Score
Conciseness	The ~726-line body contains three near-identical template blocks (File Format, Recommended structure, Quick Template), a DO/AVOID list that repeats the Anti-Patterns section verbatim, and roughly 350 lines of full example subagent prompts that largely restate generic knowledge. Several padded sections push it below the 'mostly efficient' anchor.	2 / 5
Actionability	Fully executable guidance: exact file paths (.cursor/agents/agent-name.md), a complete frontmatter field table with defaults, copy-paste-ready example subagent files, a quality checklist, and a concrete output-message template covering the common cases.	5 / 5
Workflow Clarity	The creation process is a clear 5-step sequence (Define Purpose, Choose Location, Configure Frontmatter, Write Prompt, Be Focused) with a Quality Checklist and a test-the-description verification step. Not 5 because validation checkpoints appear only at the end rather than embedded as feedback loops between steps.	4 / 5
Progressive Disclosure	Sections are well-organized, but no references/ files exist and ~350 lines of pattern and example content (6 common patterns plus 2 complete examples) that clearly belongs in separate reference files are inlined in a single monolithic 726-line SKILL.md.	3 / 5
	Total	14 / 20 Passed

Description

87%Weight 40%Scale 1-5

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: it states what the skill does, when to use it, concrete Cursor-specific details (.cursor/agents/), explicit trigger phrases, and explicit boundary guidance against a sibling skill. Third-person voice is used correctly. Minor room for improvement in synonym coverage and mentioning the full range of actions (configure, test, resume subagents).

Dimension	Reasoning	Score
Specificity	Names the domain (Cursor subagents), the concrete action (creating subagent files with isolated context), and the concrete location/format ('.cursor/agents/'). Falls short of 5 because it covers only the creation action, not configuring, testing, or resuming.	4 / 5
Completeness	Clearly answers both 'what' ('Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows') and 'when' ('Use when creating subagents for Cursor editor specifically') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Explicitly lists natural trigger phrases ('cursor subagent', 'cursor agent') users would actually say. Not 5 because common variations like 'Cursor assistant' or 'specialized Cursor agent' are missing.	4 / 5
Distinctiveness Conflict Risk	Explicitly disambiguates against the sibling generic skill ('Do NOT use for generic subagent creation outside Cursor (use subagent-creator instead)') with a clear niche and distinct Cursor-specific triggers.	5 / 5
	Total	18 / 20 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
Path: packages/skills-catalog/skills/(creation)/cursor-subagent-creator/SKILL.md
Commit: 120b676

Reviewed: 5 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.