worker-management

Use when admin requests hand-creating or resetting a Worker, starting/stopping a Worker, managing Worker skills, enabling peer mentions, or opening a QwenPaw console. Use agentteams-find-worker only as a helper for Nacos-backed market import or when task assignment needs you to discover a suitable Worker.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

78%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.

A well-organized, actionable skill body that assumes domain competence and delegates detail to real reference files and scripts. Its main weaknesses are mild runtime-guidance redundancy and the lack of explicit validate→fix→retry feedback loops for destructive operations.

Suggestions

Consolidate the runtime guidance so the five-way table and the destructive-switch gotcha each live in one place, cross-referenced instead of restated.

Add an explicit error-recovery loop for `--no-wait` creation and runtime switching: e.g. 'if phase is not Running after N polls, inspect `agt get workers -o json` for the failure reason and remediate before retrying'.

Make 'delete worker' a first-class operation in the Operation Reference (currently only implied via 'Reset a worker') so the destructive path is discoverable on its own.

Dimension	Reasoning	Score
Conciseness	Largely lean and operational (runtime table, gotchas, command examples) with little padding, though runtime guidance is repeated across the 'Before You Create', 'Gotchas', and 'Switching Runtime' sections and could be consolidated.	4 / 5
Actionability	Provides concrete, copy-paste-ready commands (`agt create worker --name ... --no-wait --soul ...`, `bash scripts/update-worker-config.sh ...`) and an operation table mapping intents to commands/scripts, with only minor gaps deferred to reference docs.	4 / 5
Workflow Clarity	Create and runtime-switch flows are clearly sequenced with checkpoints (poll `phase=Running`, confirm Worker not mid-task, confirm with admin before destructive runtime changes), though explicit error-recovery feedback loops if polling stalls are absent.	4 / 5
Progressive Disclosure	SKILL.md is a well-structured overview with an Operation Reference table that signals one-level-deep references (all of which exist in references/ and scripts/) and clear inline 'read references/...' pointers, making navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

92%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 tightly scoped, action-oriented description with an explicit 'Use when' trigger and a useful boundary clarification against the sibling find-worker skill. The only minor gap is that not every natural synonym (e.g. 'delete') appears as an explicit trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'hand-creating or resetting a Worker, starting/stopping a Worker, managing Worker skills, enabling peer mentions, or opening a QwenPaw console' — giving comprehensive coverage of the worker-management domain.	5 / 5
Completeness	Explicitly answers both what (the six worker-management actions) and when ('Use when admin requests...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger terms ('create', 'reset', 'start/stop', 'manage skills', 'peer mentions', 'QwenPaw console') with synonyms, but a few common variations (e.g. 'delete worker') are only implied via 'resetting'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (AgentTeams Worker lifecycle) and even adds a boundary clause ('Use agentteams-find-worker only as a helper...') that minimizes overlap with the discovery skill.	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: agentscope-ai/AgentTeams
Path: manager/agent/skills/worker-management/SKILL.md
Commit: acaed25

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.