CtrlK
BlogDocsLog inGet started
Tessl Logo

model-switch

Switch the Manager Agent's own LLM model. Use when the human admin requests changing the Manager's model.

65

Quality

77%

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 ./manager/agent/skills/model-switch/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 content is highly actionable with a clear, validated workflow and an explicit error-recovery loop. Minor conciseness and organization gains are available by de-duplicating restart instructions and moving the reference table to a separate file.

Suggestions

Consolidate the repeated RESTART_REQUIRED / gateway-restart guidance into one section to improve conciseness.

Consider moving the pre-configured models reference table into a separate reference file to reduce body density and improve progressive_disclosure.

DimensionReasoningScore

Conciseness

The body is largely efficient with direct sections and no over-explanation of concepts Claude already knows, though the RESTART_REQUIRED / gateway-restart instruction is repeated across several sections and could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready bash commands with concrete flags, multiple worked examples, explicit error codes (ERROR: MODEL_NOT_REACHABLE, RESTART_REQUIRED), and a reference table covering the common cases.

5 / 5

Workflow Clarity

Sequences the operation clearly (connectivity test, patch config, RESTART_REQUIRED, restart) with an explicit validation checkpoint (model reachability test before any change) and a feedback loop for error recovery via provider/route setup and retry.

5 / 5

Progressive Disclosure

Well-organized with clear section headers and a single one-level-deep script reference that exists on disk, though the inline model reference table and detailed failure procedure make the body somewhat dense and could be split out.

4 / 5

Total

18

/

20

Passed

Description

66%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 is clear, specific, and explicitly pairs a what with a when, with minimal conflict risk. It could be strengthened by listing a few more concrete actions and broader trigger synonyms.

Suggestions

Add 1-2 more concrete actions (e.g., 'adds new models to the config and switches the primary') to lift specificity.

Broaden trigger terms with synonyms like 'update' or 'change the Manager model' for better trigger_term_quality.

DimensionReasoningScore

Specificity

Names one concrete action ("Switch the Manager Agent's own LLM model") but offers only a single action with no broader coverage, matching the score-3 anchor of domain plus 1-2 concrete actions.

3 / 5

Completeness

Explicitly answers both what (switch the Manager's own LLM model) and when (Use when the human admin requests changing the Manager's model), but the when clause covers a single narrow scenario and could be more specific.

4 / 5

Trigger Term Quality

Includes a natural trigger phrase ("when the human admin requests changing the Manager's model") but lacks synonyms or variations such as "update model" or specific model IDs, fitting the some-keywords-but-missing-variations anchor.

3 / 5

Distinctiveness Conflict Risk

Targets a very specific niche (switching the Manager Agent's own model) with a distinct trigger, giving it minimal overlap risk with other skills.

5 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentscope-ai/AgentTeams
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.