team-management

Use when admin requests creating a team, importing a team, managing team composition, adding/removing workers from a team, or delegating tasks to a Team Leader.

Quality

90%

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

80%Weight 40%Scale 1-3

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

The body is a tight, actionable overview with good reference navigation, but the main workflow lacks an in-body validation checkpoint and one referenced script path does not exist in the bundle.

Suggestions

Add an explicit verify checkpoint to the Quick Create workflow in the body — e.g., run `agt get team <TEAM_NAME>` to confirm reconciliation succeeded before @mentioning the Leader — so validation is not only in the reference.

Fix the broken script reference: the Operation Reference table cites `scripts/lifecycle-worker.sh`, which is not present in the bundle; either add the script or replace the reference with an existing one.

Surface the existing `scripts/create-team.sh` helper from Quick Create or the Operation Reference, since it validates that referenced Worker CRs exist before creating the team — a useful checkpoint currently only implied by the prose.

Dimension	Reasoning	Score
Conciseness	The body is lean: a compact intro, an executable Quick Create snippet, terse Gotchas bullets, and a small Operation Reference table. It assumes Claude knows generic concepts and only adds domain-specific architecture (CR, Matrix rooms, MinIO), so most tokens earn their place.	3 / 3
Actionability	It provides a copy-paste-ready `agt create team` command with named flags and placeholders, a concrete `Worker.spec.resources` pointer, and per-intent commands in the reference table — fully executable guidance rather than vague direction.	3 / 3
Workflow Clarity	Quick Create lists a 2-step sequence and notes a failure mode ('fails if a referenced Worker does not exist') plus a resource-change checkpoint, but explicit validation/verify steps (e.g., confirming reconciliation succeeded) live only in the reference, not the body, leaving checkpoints implicit. It is not a 3 because there is no in-body verify or error-recovery feedback loop.	2 / 3
Progressive Disclosure	The overview is well split with a clearly signaled one-level reference table, and the three referenced `references/*.md` files exist. However, checking the actual bundle shows the Operation Reference points to `scripts/lifecycle-worker.sh`, which is absent from the bundle (only `scripts/create-team.sh` exists), so navigation includes a dead path.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concise, specific, and uses the recommended 'Use when...' trigger form with third-person-style action phrasing. It clearly conveys both capability and trigger conditions with low conflict risk.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — 'creating a team, importing a team, managing team composition, adding/removing workers from a team, or delegating tasks to a Team Leader' — matching the anchor that lists several specific concrete actions rather than vague language.	3 / 3
Completeness	It states what the skill does (the enumerated actions) and gives an explicit 'Use when admin requests...' trigger clause, clearly answering both what and when; it is not capped at 2 because the trigger guidance is explicit.	3 / 3
Trigger Term Quality	Phrases like 'creating a team', 'importing a team', 'adding/removing workers', and 'delegating tasks to a Team Leader' are natural terms an admin would say, giving good coverage of the domain's common variations.	3 / 3
Distinctiveness Conflict Risk	The team/Team Leader/worker delegation niche is specific and unlikely to fire for unrelated skills; the triggers are distinct and not generic. It does not match the score-2 anchor of overlapping with similar skills.	3 / 3
	Total	12 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: agentscope-ai/AgentTeams
Path: manager/agent/skills/team-management/SKILL.md
Commit: 785c2db

Reviewed: 7 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.