CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

resource-management

Manage AgentTeams resources through the Controller as Manager.

Quality

69%

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/teamharness/skills/manager/resource-management/SKILL.md

The canonical home for this skill is resource-management in agentscope-ai/AgentTeams

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.

The body is an efficient, highly actionable operator guide: concrete agt commands, explicit failure-path handling (timeouts, batch waits, destructive-operation gating), and a clean pointer to the worker-management skill for details. Its main weaknesses are minor — team-creation specifics are deferred to CLI help, and the external skill reference could be more clearly labeled.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and free of concept explanations or padding — lines like "The CLI owns readiness polling; you do not need a shell polling loop" and "Read ~/skills/worker-management/SKILL.md before creating or resetting a Worker" add only non-obvious operational constraints. Every token carries guidance Claude could not infer, matching the lean anchor.

5 / 5

Actionability

Most guidance is copy-paste ready: `agt create worker --name example-worker --runtime qwenpaw --model MODEL --wait-timeout 45s -o json`, the full JSON `message` example, and the installer script invocation with arguments. It falls short of 5 because team creation via `agt apply -f FILE` is never shown concretely and some fields are deferred to `--help` and the CRD schema.

4 / 5

Workflow Clarity

Multi-step flows are clearly sequenced with explicit failure handling: wait timeout means "report the last status and stop", batch creation uses `--no-wait` followed by one bounded `wait-ready`, and destructive operations are gated by "Ask before destructive operations or irreversible external side effects unless the admin already authorized them". Minor gap: no explicit verification checkpoint after `agt apply`.

4 / 5

Progressive Disclosure

No bundle files exist, and the body is organized into three well-scoped sections with a single, clearly signaled one-level external reference ("Read ~/skills/worker-management/SKILL.md before creating or resetting a Worker"). It is not a 5 only because that reference is a bare path rather than a labeled, discoverable pointer, and the skill runs past the under-50-lines simple-skill case.

4 / 5

Total

17

/

20

Passed

Description

41%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 a distinct niche (AgentTeams administration via the Controller, in the Manager role) but says almost nothing actionable about what the skill does and nothing about when to invoke it. It reads as a role assignment rather than a capability description with trigger guidance.

Suggestions

Enumerate the concrete operations in the description, e.g. "Create, configure, sleep, and delete Workers; assemble Teams; apply desired-state changes via the agt CLI".

Add an explicit trigger clause, e.g. "Use when the admin requests creating workers, building or changing teams, or managing AgentTeams resources".

Include natural user phrasings as trigger terms ("create a worker", "set up a team", "reset a worker") so the skill matches how requests are actually worded.

DimensionReasoningScore

Specificity

"Manage AgentTeams resources through the Controller as Manager" names the domain, mechanism, and role, but "Manage" is a single generic action with no concrete operations (create workers, build teams, apply desired state) listed. It matches the anchor for naming the domain with minimal or generic actions, not the level above which requires 1-2 concrete actions.

2 / 5

Completeness

The "what" is stated but only at a generic level (manage resources via the Controller in the Manager role), and the "when" is completely absent — there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3. It sits above anchor 2 because the what is domain- and role-scoped rather than purely vague.

3 / 5

Trigger Term Quality

The only keywords are product jargon ("AgentTeams", "Controller") plus the entirely generic "resources" and "Manage". It misses the natural phrases a user would actually say, such as "create a worker", "set up a team", or "sleep/delete a worker".

2 / 5

Distinctiveness Conflict Risk

"AgentTeams" plus the role qualifier "as Manager" carves out a clear niche with minimal conflict risk against unrelated skills. It is not a 5 because "Manage... resources" could overlap with sibling AgentTeams skills (e.g., a worker-management skill) that share the same product vocabulary.

4 / 5

Total

11

/

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/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.