model-selection

Resolve explicit and persistent model preferences for Squad spawns without pinning stale defaults

Quality

73%

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

92%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 a lean, well-structured decision procedure: a six-step resolution order with explicit validation, fallback, and stop conditions, and concrete config field names throughout. Its only weakness is the absence of a small worked example (e.g. a sample .squad/config.json merge) that would make the guidance fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Every line carries operational content (e.g. "Merge model fields into the existing .squad/config.json; do not replace unrelated settings") with no padding and no explanation of concepts Claude already knows. Not 4 because there is essentially nothing left to trim.	5 / 5
Actionability	Concrete field names (".squad/config.json agentModelOverrides.{specialist-id}", "defaultModel", ".squad/casting/registry.json") and a numbered six-step resolution order make the guidance executable, but there is no example config snippet or concrete command for the validation steps. Not 5 because copy-paste-ready examples are absent; not 3 because the guidance is specific and directly followable, not pseudocode.	4 / 5
Workflow Clarity	The resolution order is an explicit sequence with a concrete validation checkpoint ("Validate a requested model against the runtime's currently supported model list"), explicit error recovery ("If a requested model is unavailable, report that failure and fall back"), and stop conditions for unsafe cases ("Stop rather than rewriting configuration when .squad/config.json cannot be parsed safely"). Not 4 because validation and failure-handling checkpoints are explicit rather than implicit.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references, and its four well-labeled sections (Resolution Order, Persistent Preferences, Spawn Behavior, Stop Conditions) make navigation trivial, which scores 5 under the simple-skill guideline. Not 4 because there is no content that should be split out and no organization gap.	5 / 5
	Total	19 / 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 concise, third-person, and names a specific niche (Squad spawn model resolution), but it omits any explicit "when to use" trigger guidance and offers thin keyword synonym coverage. It reads more like a purpose statement than a discoverability description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user requests a specific model for a Squad spawn, a saved model preference exists in .squad/config.json, or a specialist charter mandates a model."

Include natural trigger synonyms users would actually say, such as "default model", "model override", or "switch the model for an agent".

Enumerate the concrete capabilities (resolve requested model, merge saved overrides, validate against supported models, fall back to automatic routing) so the "what" is comprehensive, not just a single action.

Dimension	Reasoning	Score
Specificity	"Resolve explicit and persistent model preferences for Squad spawns" names the domain and one concrete action with qualifiers, but does not list several specific actions, matching the 1-2 concrete actions anchor. It is not 4 because no broader set of capabilities (saving, merging, validating overrides) is enumerated.	3 / 5
Completeness	The "what" is clear (resolving explicit and persistent model preferences for Squad spawns), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is specific, not 4 because "when" is entirely absent.	3 / 5
Trigger Term Quality	Terms like "model", "model preferences", and "Squad spawns" are relevant to the domain, but natural user phrasings such as "default model", "model override", or "use a different model" are missing. It is not 4 because synonym coverage is thin, and not 2 because the keywords are domain-specific rather than generic.	3 / 5
Distinctiveness Conflict Risk	"Squad spawns" plus "model preferences" carves out a mostly distinct niche with minor overlap risk against generic model-selection or config-management skills. Not 5 because it lacks a distinguishing trigger phrase that would fully separate it from general model-choice requests.	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: .squad/skills/model-selection/SKILL.md
Commit: 29e69f5

Reviewed: 5 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.