CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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.

A well-structured, actionable guide with strong templates and examples, but it is monolithic and leans on some over-explanation of concepts Claude already knows. Splitting the pattern library into reference files and trimming the introductory concept section would improve it.

Suggestions

Trim or remove the 'What are Subagents?' section defining isolated context/parallel execution — Claude already knows this — to recover tokens.

Move the four 'Common Subagent Patterns' (verifier, debugger, security-auditor, code-reviewer) into a separate references/patterns.md and link to it from the body to improve progressive disclosure.

Add an explicit validation/feedback loop to the creation process, e.g. 'Test the description triggers the right subagent; if not, refine and re-test', to raise workflow clarity.

DimensionReasoningScore

Conciseness

Mostly efficient with clear sections, but it re-explains concepts Claude already knows ('What are Subagents?' with isolated context/parallel execution definitions) and the four full pattern templates plus the structure template add padding that could be trimmed.

3 / 5

Actionability

Provides concrete, copy-paste-ready markdown templates and worked examples (verifier, debugger, security-auditor, code-reviewer) with specific steps and output formats, though the core creation template is partially placeholder-driven.

4 / 5

Workflow Clarity

Clear sequenced creation process (Define purpose → Configure metadata → Write prompt) with a Quality Checklist checkpoint, but no explicit validate-and-iterate feedback loop after creating a subagent.

4 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers, but no bundle files exist and all content (patterns, templates, best practices) is inlined in one ~300-line SKILL.md rather than split into referenced detail files.

3 / 5

Total

14

/

20

Passed

Description

95%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, specific description that clearly states both purpose and trigger conditions with concrete user-facing phrases and an explicit exclusion to reduce conflict. Minor action-vs-role coverage gap keeps specificity just below a perfect score.

DimensionReasoningScore

Specificity

Lists several concrete actions/roles ('create a subagent, specialized agent, verifier, debugger, or orchestrator') tied to isolated context for multi-step workflows, but is somewhat role-list heavy rather than action-comprehensive.

4 / 5

Completeness

Explicitly answers both 'what' (guide for creating AI subagents with isolated context) and 'when' (Use when users want to create a subagent...) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user phrases and explicit trigger strings ('create subagent', 'new agent', 'specialized assistant', 'create verifier') plus common synonyms (verifier, debugger, orchestrator), giving comprehensive coverage.

5 / 5

Distinctiveness Conflict Risk

Has a clear niche (agent-agnostic subagent creation with isolated context) and an explicit exclusion ('Do NOT use for Cursor-specific subagents') minimizing overlap with the cursor-specific variant.

5 / 5

Total

19

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tech-leads-club/agent-skills
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.