CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

resource-management

Manage AgentTeams resources through the Controller as Manager.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/agentteams-teamharness/skills/manager/resource-management/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

This is a strong instruction-only skill body: nearly every line is an executable directive with concrete CLI syntax, explicit failure/timeout handling, and sensible guardrails against destructive shortcuts. The main improvement opportunities are consolidating the repetitive negative instructions and tightening the overlap with the referenced worker-management skill.

DimensionReasoningScore

Conciseness

The body is dense with operational directives and explains nothing Claude already knows, but the stream of "Do not ..." guardrail sentences ("Do not scan your environment, image files, or CLI help", "Do not invent background follow-up promises") has some redundancy that could be tightened.

4 / 5

Actionability

Commands are copy-paste ready with named placeholders and cover the common cases: full `agt create worker` and `agt update worker` invocations, the `install-worker-skill.sh` script call, a complete `message` tool JSON example, and `agt apply -f FILE` with explicit field-preservation rules.

5 / 5

Workflow Clarity

Per-operation sequences are clear with checkpoints: bounded `wait-ready` verification for batch creation, read-before-apply for desired-state changes, a Human CR pre-check before Team creation, and explicit failure handling ("If its wait times out ... report the last status and stop"). The gap keeping it below 5 is that `agt delete worker` has only a general "ask before destructive operations" gate rather than an operation-specific validation step.

4 / 5

Progressive Disclosure

A single-file skill with three clear sections and clearly signaled one-level external references ("Read ~/skills/worker-management/SKILL.md before creating or resetting a Worker"), though the inline worker-creation playbook overlaps that sibling skill's territory and the ~93-line body is not split across files.

4 / 5

Total

17

/

20

Passed

Description

37%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.

The description identifies the domain and role context but relies on a single generic action verb and provides no trigger guidance or concrete capability list. It would rarely be selected confidently from a user's natural request. Adding a "Use when..." clause and naming the concrete operations (create/update/delete workers, teams, humans) would substantially improve it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the admin asks to create, update, delete, or inspect AgentTeams workers, teams, humans, or managers."

Replace the generic verb "Manage" with the concrete operations the skill performs: create/reset/delete Workers, configure heartbeats, apply desired-state changes, and delegate to team Leaders.

Include natural user phrasings as trigger terms (e.g. "spin up a worker", "add a skill to a worker", "put the worker to sleep") so the description matches how requests are actually worded.

DimensionReasoningScore

Specificity

The description names the domain ("AgentTeams resources through the Controller") but its only action is the generic verb "Manage" — no concrete operations like creating, updating, or deleting workers/teams are listed, matching the anchor for minimal or generic actions.

2 / 5

Completeness

The "what" is stated (manage resources via the Controller as Manager) but the "when" is entirely absent — there is no "Use when..." clause or equivalent trigger guidance, which caps this dimension at 3.

3 / 5

Trigger Term Quality

"AgentTeams", "Controller", and "as Manager" are role/jargon terms rather than natural phrases a user would say when needing this skill (e.g. "create a worker", "set up a team"), leaving only one or two generic keywords ("manage", "resources").

2 / 5

Distinctiveness Conflict Risk

The niche terms (AgentTeams, Controller) give it some distinctiveness, but "Manage ... resources" is broad and the skill body references a closely related worker-management skill that the description does not distinguish it from, so overlap risk with similar skills remains.

3 / 5

Total

10

/

20

Passed

Validation

100%

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

plugins/agentteams-teamharness/skills/manager/resource-management/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.