CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 body is highly actionable and workflow-safe: executable examples for every tool, explicit feedback loops for background waits, collision avoidance for parallel runs, and a pre-dispatch checklist. Its weaknesses are repetition of the wait/kill guidance across several sections and a monolithic single-file structure that could offload advanced material to reference files.

Suggestions

State the kill/collect rule once (e.g., in the wait_for_subagents section or the Checklist) and reference it elsewhere instead of repeating "use kill=True only when the delegated work is no longer needed" and "collect final results before finishing" in the timeout table, Handling `running` status, result-format bullets, and both example comments.

Merge "Handling `running` status" into the timeout/kill subsections it restates, keeping only the new information (doing independent work while waiting, sub-agents continuing during user questions).

Move the advanced checkpoint-pattern section, the prompt-brief template, and the per-parameter API reference into one-level-deep reference files (e.g. references/prompt-template.md, references/checkpoint-patterns.md) so SKILL.md stays a lean overview, and add clearly signaled links to them.

DimensionReasoningScore

Conciseness

Almost all content is tool-specific knowledge Claude cannot already know (session_id semantics, fork/resume lifecycle, POSIX timeout behavior, pattern matching), so there is no padding with known concepts — but the skill is noticeably repetitious: the rule "use kill=True only when the delegated work is no longer needed" plus "collect and process final results before finishing the parent task" appears at least five times (timeout table, Handling `running` status, result-format bullets, Parallel Example comments, Checkpoint rules), and "Handling `running` status" restates the timeout table directly above it. This is more than the "minor instances" of anchor 4, fitting anchor 3's "could be tightened".

3 / 5

Actionability

Fully executable, copy-paste-ready code covers every tool and the common cases: `find_agents` keyword search and full-list browsing, `call_subagent` sync/parallel/fork/checkpoint variants, a reusable `dispatch()` helper, and `wait_for_subagents` usage, plus concrete Good/Bad prompt examples with an explicit parallel-context template. This clearly matches the anchor for fully executable guidance with examples covering common cases, not anchor 4's "minor gaps".

5 / 5

Workflow Clarity

The multi-step process is clearly sequenced (when to delegate → select target → dispatch → wait → handle `running` → report) with explicit validation and feedback loops: timeout is defined as "still running" not failure, the parent must read `Last message:` and keep waiting or explicitly kill, parallel write collisions are guarded ("Never let multiple sub-agents write to the same file concurrently"), and a pre-dispatch Checklist verifies each step. This matches the anchor-5 example (explicit validation, error-recovery loops, checklists) rather than anchor 4's minor validation gaps.

5 / 5

Progressive Disclosure

The single file is well-organized with clear section headers, per-parameter reference subsections, worked examples, and a closing checklist, making navigation easy — but at ~430 lines with no bundle files, advanced material (checkpoint pattern matching, the prompt-brief template, the full parameter API reference) could be split into one-level-deep reference files to keep SKILL.md a leaner overview. Good structure with minor organization gaps fits anchor 4; not 3 because nothing is buried or clearly misplaced, not 5 because it is a monolithic file rather than an overview with well-signaled references.

4 / 5

Total

17

/

20

Passed

Description

78%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 with explicit, rich trigger guidance in multiple languages and concrete named actions. Its main gaps are a "what" that is embedded in the when-clause rather than stated independently (omitting result collection) and the absence of the natural term "subagent".

DimensionReasoningScore

Specificity

The description names several concrete actions ("find, select, call, or delegate work to an Agent/智能体, digital employee/数字员工, or Crew"), matching the anchor for several specific actions with minor coverage gaps. It is not 5 because it omits capabilities the skill covers, such as collecting results from background runs and parallel dispatch mechanics; it is not 3 because it lists more than 1-2 actions.

4 / 5

Completeness

Both elements are present: the "what" is stated via concrete actions ("find, select, call, or delegate work to an Agent") and the "when" is explicit with multiple concrete triggers ("when the target is unknown or must be selected by capability; when independent tasks can run in parallel"). It falls short of 5 because the "what" is embedded in the when-clause and is not fully comprehensive — result collection via wait_for_subagents, a core function, is not mentioned.

4 / 5

Trigger Term Quality

Good natural-term coverage including bilingual synonyms ("Agent/智能体", "digital employee/数字员工", "Crew", "delegate work", "run in parallel"), but a few natural terms are missing — most notably "subagent"/"sub-agent", arguably the most common English phrasing a user would say. Not 5 because coverage is not comprehensive; not 3 because far more than some relevant keywords are present, with synonym variants included.

4 / 5

Distinctiveness Conflict Risk

Clear niche (delegating work to subagents/Agents) with highly distinctive triggers ("Crew", "数字员工", "智能体", capability-based agent selection) that no generic skill would share, giving minimal conflict risk. This clearly matches the anchor-5 example of a clear niche with distinct triggers, rather than anchor 4's minor overlap risk.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

dtyq/magic

Path

backend/super-magic/agents/skills/subagents/SKILL.md

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.