subagents

Use when multiple independent subtasks can run in parallel, when a research or exploration task is large enough to keep separate rather than do inline (doing it inline fills the conversation with intermediate steps you'll carry through to the end), or when you need a specialized agent type (explore for deep search, shell for system commands). Any task with a clear deliverable and no dependency on the current thread is a good candidate to delegate.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./backend/super-magic/agents/skills/subagents/SKILL.md

Quality

Content

80%

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

The body is lean, operational, and highly actionable with executable examples, but it lacks an explicit validation checkpoint in its dispatch/wait workflow and keeps all content inline with no progressive disclosure into reference files.

Suggestions

Add an explicit post-wait verification checkpoint (e.g. check each status and validate output before reporting) to lift workflow clarity past the batch-operation cap.

Extract the agent-type catalog and/or full sync/parallel examples into a reference file with a one-level-deep pointer from SKILL.md to improve progressive disclosure.

Add an explicit error/interrupted recovery step to the wait_for_subagents workflow so the feedback loop is concrete rather than implied.

Dimension	Reasoning	Score
Conciseness	The ~200-line body contains no conceptual padding Claude already knows; every section is operational (tool signatures, parameter tables, bad/good prompts, a checklist), assuming Claude's competence.	3 / 3
Actionability	Fully executable tool.call signatures with real parameters, two complete runnable examples (sync and parallel), a bad/good prompt contrast, status enums, and structured result fields make it copy-paste ready.	3 / 3
Workflow Clarity	The dispatch-to-wait sequence and a 'Before dispatching' checklist are present with status handling, but there is no explicit verify-output-before-proceeding checkpoint, and the batch/parallel-operation guideline caps clarity at 2 when validation is missing.	2 / 3
Progressive Disclosure	The skill is a single well-organized monolithic file with no bundle files and no external references; sections are clear but nothing is split out for a ~200-line body, which is the 2-anchor rather than the file-split 3-anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 has an explicit 'Use when' trigger and states both what and when, but its actions are situational rather than concrete and some trigger phrasing is jargon-leaning with mild overlap risk against explore/search skills.

Suggestions

Replace jargon ('do inline', 'current thread') with user-natural phrasings like 'keep the main conversation clean' to improve trigger term quality.

Lead with the concrete capability ('Delegate tasks to parallel subagents') before the 'Use when' clause to raise specificity toward the 3-anchor.

Tighten the exploration trigger so it does not read as a generic research/exploration skill, reducing conflict risk.

Dimension	Reasoning	Score
Specificity	Names the delegation domain and several actions ('run in parallel', 'keep separate rather than do inline', 'specialized agent type (explore for deep search, shell for system commands)'), but these are situational triggers rather than the concrete operations that define the 3-anchor.	2 / 3
Completeness	Explicit 'Use when...' clause supplies the trigger, and the what (delegate tasks to subagents for parallel/specialized execution) is stated, satisfying both halves with an explicit trigger.	3 / 3
Trigger Term Quality	Contains relevant natural keywords ('run in parallel', 'delegate', 'research', 'exploration') but mixes in jargon ('do inline', 'current thread', 'specialized agent type') and misses common user phrasings.	2 / 3
Distinctiveness Conflict Risk	The delegation niche is fairly distinct, but triggers like 'research or exploration task' and 'explore for deep search' could overlap with a dedicated explore/search skill, so it is not cleanly conflict-free.	2 / 3
	Total	9 / 12 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: 41d7ef4

Reviewed: about 13 hours 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.