model-selection

Determines which LLM model to use for each agent spawn

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./.squad/skills/model-selection/SKILL.md

Quality

Content

75%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 orchestration decision skill with clear layered workflows, explicit config schema, and a STOP boundary. Its main weakness is mild verbosity in a few justifications and the absence of an explicit verify-after-write feedback loop for config mutations.

Dimension	Reasoning	Score
Conciseness	Mostly lean and well-structured (layer table, terse workflow steps, terse fallback chains) with minor restating sentences such as the 'intentional — the user explicitly chose quality over cost' justification and the 'A fast task won't land on a premium model' restatement.	4 / 5
Actionability	Provides concrete, directly usable guidance — exact config keys, file path, model IDs in a decision table, acknowledgment templates, and a copy-paste config schema; the only gap is the config-write step being described ('merge, don't overwrite') rather than given as executable code/tooling.	4 / 5
Workflow Clarity	Clear numbered sequences for session start, per-spawn resolution, and preference set/clear with an explicit STOP list and a validate-against-catalog checkpoint; the missing piece is an explicit post-write verification/feedback loop for the config mutation.	4 / 5
Progressive Disclosure	No bundle files exist, but the single-file body is well-sectioned (SCOPE, Context, 5-Layer Hierarchy, AGENT WORKFLOW, Config Schema, Fallback Chains) and easy to navigate; the inline 18-model fallback catalog is arguably reference material that could be externalized but its placement is justified.	4 / 5
	Total	16 / 20 Passed

Description

46%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 concise and states a clear purpose but reads as a bare technical label: it lacks any 'when to use' trigger guidance and contains only jargon rather than natural user keywords. Adding a 'Use when...' clause with conversational phrases would lift the weakest dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when deciding which LLM to assign to an agent, or when the user asks to switch, pin, or clear a model preference.'

Replace jargon-only language with natural user terms like 'pick a model', 'always use opus', 'use sonnet for code' to improve trigger_term_quality.

Expand the 'what' to name concrete actions: resolves models per spawn, validates model IDs, and persists per-agent or default preferences to .squad/config.json.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Determines which LLM model to use for each agent spawn') but does not enumerate the several capabilities it actually supports (validation, persistence, per-agent overrides).	3 / 5
Completeness	Provides a clear 'what' but entirely omits 'when' guidance — there is no 'Use when...' clause or equivalent trigger, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Uses technical jargon ('agent spawn', 'LLM model') with no natural user phrases or trigger terms; users would not naturally say these words when reaching for the skill.	2 / 5
Distinctiveness Conflict Risk	Carves a fairly distinct niche (per-spawn model resolution) with minor overlap risk against general orchestration/agent-spawning skills, though it lacks explicit triggers that would make it airtight.	4 / 5
	Total	12 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .squad/skills/model-selection/SKILL.md
Commit: a0d2563

Reviewed: about 16 hours 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.