subagents

Use when the user asks to find, select, call, or delegate work to an Agent/智能体, digital employee/数字员工, or Crew; when the target is unknown or must be selected by capability; when independent tasks can run in parallel; or when isolated research or a specialized Agent would improve the result.

Quality

88%

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

Quality

Content

82%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.

The content is a well-structured, highly actionable reference for two tools with strong examples and verification guidance. Its main weaknesses are minor redundancy around running-status handling and a monolithic single-file layout that could benefit from splitting detailed reference material.

Suggestions

Consolidate the running-status guidance into one place; it currently appears in the "Handling running status" section, the result-format bullets, and the parallel-example comments.

Consider moving the full parameter reference and/or the advanced checkpoint-pattern example into a separate reference file to reduce the inline length and improve progressive disclosure.

Add one short canonical end-to-end workflow (dispatch -> wait -> handle running -> collect) as a numbered sequence so the lifecycle is visible as a single linear path rather than across reference sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient tool documentation with no padded concept explanations, but the guidance for handling "running" status is repeated in the Handling section, the result-format bullets, and the parallel-example comments, which could be tightened.	4 / 5
Actionability	Multiple complete, copy-paste runnable examples (sync, parallel, checkpoint), full parameter signatures with types/defaults, and a Good/Bad prompt contrast give fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	A dispatch checklist plus explicit running-status decision logic (wait vs. kill) and a pattern-match feedback loop provide clear checkpoints, but the workflow is presented as reference sections rather than one linear sequenced pipeline.	4 / 5
Progressive Disclosure	No bundle files exist; the single file is well-sectioned with clear headers enabling easy navigation, and the cohesive two-tool scope justifies one file, though at ~390 lines the detailed parameter reference or advanced examples could be split out.	4 / 5
	Total	17 / 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.

The description is strong: it answers both what and when with concrete, multilingual trigger terms and a clear use-when clause. The only minor weakness is the abstractness of the word "work" in the action list.

Dimension	Reasoning	Score
Specificity	"find, select, call, or delegate work" lists four concrete dispatch-lifecycle verbs, but the delegated "work" itself is left abstract, so coverage has a minor gap rather than being fully comprehensive.	4 / 5
Completeness	An explicit "Use when..." clause supplies four concrete trigger conditions (capability-based selection, parallel tasks, isolated research) while the lead verbs clearly state what the skill does.	5 / 5
Trigger Term Quality	Includes natural synonyms across two languages ("Agent/智能体, digital employee/数字员工") plus the product term "Crew" and natural verb phrases users would actually say, giving comprehensive synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (subagent dispatch) with distinct, specific triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/subagents/SKILL.md
Commit: f9973c5

Reviewed: 2 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.