model-selection

Per-agent model selection with 4-layer hierarchy and fallback chains

Quality

66%

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

Fix and improve this skill with Tessl

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

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.

The body is highly actionable and clearly sequenced, with concrete decision tables, fallback chains, and copy-paste spawn formatting. Its main weakness is progressive disclosure: it is a single monolithic file with no reference files, despite containing lookup material (model lists, role mappings) that would benefit from being split out.

Suggestions

Move the stable lookup material (Valid Models list, full fallback chains, role-to-model table) into a references file (e.g. references/models.md) and link to it one level deep, keeping the decision procedure and examples in SKILL.md.

Trim the redundancy between the 'Valid Models' section and the inline tables to tighten conciseness toward a lean 5.

Add an explicit final checkpoint in the workflow (e.g. 'Confirm resolved model, then pass as the model parameter') so the selection-to-spawn handoff is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is dense and well-sectioned with tables and code blocks (e.g. 'Check these layers in order — first match wins', the task/role tables, the fallback chain blocks, the 'agent_type/model/mode' spawn block) and avoids explaining concepts Claude already knows; minor redundancy (the 'Valid Models' list re-states table contents) keeps it just below lean.	4 / 5
Actionability	Fully actionable: an ordered 4-layer decision procedure, concrete task→model and role→model tables, explicit complexity adjustments, copy-paste fallback chains with exact model identifiers, and a ready spawn code block; four worked examples cover the common cases.	5 / 5
Workflow Clarity	The 4-layer hierarchy is a clear ordered sequence and the fallback chain provides an explicit error-recovery loop ('Maximum 3 retries before using the platform default fallback'); this is non-destructive so no validation cap applies, but there is no explicit checkpoint confirming the resolved model before spawning.	4 / 5
Progressive Disclosure	There are no bundle files and all content lives inline in a ~135-line SKILL.md; sectioning is good, but material that could be split out (the full role-to-model table, fallback chains, valid-models list) is inlined rather than surfaced via one-level-deep references.	3 / 5
	Total	16 / 20 Passed

Description

53%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 specific and identifiable but reads as an internal structural summary rather than a user-facing trigger: it states what the skill does without saying when to invoke it. Adding a 'Use when...' clause with natural phrasing would raise completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when spawning agents in Team Mode and deciding which model each agent should run on.'

Replace jargon ('4-layer hierarchy', 'fallback chains') or supplement it with natural trigger terms users would actually say ('which model', 'pick a model', 'model for this agent', 'save costs').

Surface 1-2 more concrete actions (e.g. 'maps roles to models, adjusts for task complexity, and retries on unavailable models') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Per-agent model selection') plus two concrete structural mechanisms ('4-layer hierarchy', 'fallback chains'), but does not enumerate several distinct actions, so it sits at the domain-plus-1-2-actions anchor rather than comprehensive.	3 / 5
Completeness	The description gives a clear 'what' (per-agent model selection with hierarchy and fallback) but no 'when'/'Use when...' trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	'model selection' is a relevant keyword a user might say, but '4-layer hierarchy' and 'fallback chains' are technical jargon rather than natural phrasing, and no synonyms or common variations are present.	3 / 5
Distinctiveness Conflict Risk	'Per-agent model selection' is a mostly distinct niche with minor overlap risk against general orchestration skills, though the absence of explicit triggers keeps it just below the clear-niche anchor.	4 / 5
	Total	13 / 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: .copilot/skills/model-selection/SKILL.md
Commit: 6ce1221

Reviewed: 4 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.