CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

choose-model

Recommend a currently supported model capability and effort for a described task, considering uncertainty, error cost, scope and latency. Use when the user asks which model or reasoning level to use, or needs routing advice for authorised subagents. Verify current availability before naming a model or control.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-sequenced, concise, single-purpose instruction skill with a clear verification gate and fallback path. Its weakness is actionability: key steps are directional rather than executable, and a substantial share of the text is negative constraints instead of positive instructions.

Suggestions

Make the first step concrete: specify how to establish current choices (e.g., which tool call, schema field, or documentation page to inspect) rather than "Inspect the current host's exposed model inventory and tool schema".

Convert negative constraints into positive instructions — instead of "do not use paid API workarounds, install missing skills or change credentials", state what to do when a route is unavailable (e.g., "recommend a capability class and continue with authorised work").

Trim or consolidate policy-style sentences (e.g., "Respect applicable project allocation, independent review and explicitly selected specialist programme floors") into a single line to tighten the token budget.

DimensionReasoningScore

Conciseness

The ~36-line body is terse and directive with no explanation of concepts Claude already knows, but a few policy-style sentences (e.g., "Respect applicable project allocation, independent review and explicitly selected specialist programme floors") could be trimmed or consolidated, keeping it below the lean 5 anchor.

4 / 5

Actionability

"Weigh the task" gives a concrete task-type-to-route mapping and "Output" specifies a concrete format ("recommendation, the deciding factor, and any availability limitation"), but the opening step ("Inspect the current host's exposed model inventory and tool schema") gives no concrete method, and much of the text is negative constraints ("do not use paid API workarounds, install missing skills or change credentials") rather than executable steps — matching the 3 anchor's 'concrete guidance but incomplete, missing key details'.

3 / 5

Workflow Clarity

A clear three-phase sequence (establish current choices → weigh the task → output) with an explicit verification gate ("Name an exact model, argument or effort value only when that evidence supports it") and a fallback loop ("If availability cannot be verified, recommend a capability class and state that limitation"), but minor gaps remain — e.g., no final check tying the chosen route back to the task factors before answering.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the body references none, so nothing is dangling; at under 50 lines with a single purpose and three well-organized sections, it fits the simple-skill guideline for a top structure score.

5 / 5

Total

16

/

20

Passed

Description

82%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.

A strong description: it explicitly states what the skill does and when to use it, with concrete trigger phrases and a distinct niche. Its main weakness is that the capability list is limited to roughly two actions (recommend, verify availability) rather than a broader set of specific operations.

DimensionReasoningScore

Specificity

Names the domain with two concrete actions — "Recommend a currently supported model capability and effort" and "Verify current availability before naming a model or control" — plus decision factors ("uncertainty, error cost, scope and latency"), but this is 1-2 actions rather than the several listed actions of the 4 anchor.

3 / 5

Completeness

Explicitly answers both: what ("Recommend a currently supported model capability and effort for a described task, considering uncertainty, error cost, scope and latency") and when ("Use when the user asks which model or reasoning level to use, or needs routing advice for authorised subagents") with concrete trigger phrases, matching the 5 anchor rather than the 4 anchor whose 'when' is less specific.

5 / 5

Trigger Term Quality

Contains good natural phrases users would say — "which model or reasoning level to use", "routing advice" — but misses common variations like "choose/pick a model", "model selection", or "fast mode", so it does not reach the synonym-level coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — model/effort selection and subagent routing advice — with distinct triggers ("which model", "reasoning level", "routing advice for authorised subagents") that are unlikely to fire for unrelated skills.

5 / 5

Total

17

/

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

BigSimmo/PsychSift

Path

.claude/cloud-profile/skills/choose-model/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.