agent-info

Query the list of all agents (employees) available to the current user. Use when generating code that requires a real agentId, or when the user asks "which agents/employees do I have".

Quality

87%

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

85%

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 well-structured for a simple single-script skill, with executable commands and concrete examples throughout. Its main weakness is token efficiency: the inline bilingual duplication (English plus Chinese in HTML comments) inflates the content without adding capability.

Suggestions

Move the Chinese translations out of inline HTML comments into a separate localized file (or a single language section) to cut the body's token cost roughly in half.

Drop the redundant restatement of capabilities — the 'Core Capabilities' bullets and 'list.py' description repeat the same 'query all agents' idea already in the intro.

Trim the duplicated agentId-usage explanation, which appears in both the OUTPUT notes and Use Case 1; keep it once.

Dimension	Reasoning	Score
Conciseness	The English guidance is reasonably lean, but every section is duplicated as a Chinese translation inside HTML comments (e.g. '<!--zh ... -->'), roughly doubling the token cost; the body could be tightened by separating localization rather than carrying both languages inline.	2 / 3
Actionability	It provides an executable synopsis ('python scripts/list.py [OPTIONS]'), a concrete options table, a real output JSON shape, runnable examples, and a copy-paste JavaScript snippet for using the returned code as agentId.	3 / 3
Workflow Clarity	This is a simple single-task skill whose two-step flow (query list.py, then use the returned code as agentId) is laid out unambiguously in the Typical Workflow section; being read-only, it needs no destructive-operation validation checkpoint.	3 / 3
Progressive Disclosure	For a short skill with no external references needed, the content is well-organized into clear sections (Core Capabilities, Quick Start, Available Scripts, Use Cases) and points one level deep to the real scripts/list.py bundle file.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 an explicit 'Use when' clause and natural trigger phrasing, with a clear distinct niche. Its only weakness is specificity, since it describes essentially one primary action rather than a list of concrete capabilities.

Dimension	Reasoning	Score
Specificity	It names the domain (agents/employees) and one concrete action ('Query the list of all agents'), plus an indirect second capability (supplying a real agentId for code), but it does not enumerate multiple distinct concrete actions the way the level-3 anchor does.	2 / 3
Completeness	It states what the skill does ('Query the list of all agents available to the current user') and provides an explicit 'Use when' clause with concrete triggers (generating code needing a real agentId, or the user asking which agents they have).	3 / 3
Trigger Term Quality	It surfaces natural terms a user would actually say — 'agents', 'employees', 'agentId', and the verbatim phrase 'which agents/employees do I have' — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow and distinctive — enumerating the user's available agents/agentIds — and its triggers (agentId lookup, 'which agents do I have') are unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/agent-info/SKILL.md
Commit: 41d7ef4

Reviewed: about 14 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.