CtrlK
BlogDocsLog inGet started
Tessl Logo

model-cost-compare

Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or "/model-cost-compare". Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4, then recommends the cheapest model capable of the task.

80

Quality

100%

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

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable single-file skill that gives an executable cost model, a worked example, and a clear workflow with verification affordances. It respects token budget and avoids over-explanation.

DimensionReasoningScore

Conciseness

Lean and efficient: a terse pricing table, imperative instructions, and a worked arithmetic example with no padding or explanation of concepts Claude already knows; the only mild redundancy is the 'check provider docs' caveat appearing twice.

3 / 3

Actionability

Provides an executable cost formula, a fully worked example table with shown arithmetic, a recommendation output template, and a defined output table format — copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

A clear five-step sequence (parse, rule out via capability floor, compute, present, recommend) with an explicit capability-floor checkpoint and a 'sanity-check your arithmetic' verification affordance; the task is advisory/non-destructive so the strict batch-cap does not apply.

3 / 3

Progressive Disclosure

A single self-contained, well-organized SKILL.md (~76 lines) with no bundle files and no need for external references; content like the pricing table is appropriately kept inline with no deep nesting or broken references.

3 / 3

Total

12

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, specific description that clearly states both capability and trigger conditions with natural user phrasings and a dedicated slash command. It uses appropriate third-person imperative voice and avoids vague fluff.

DimensionReasoningScore

Specificity

Names concrete actions ('Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4', 'recommends the cheapest model capable of the task') and enumerates specific models rather than vague language.

3 / 3

Completeness

Explicitly states what it does (estimate token cost and recommend cheapest capable model) and when to trigger ('Trigger when the user asks...'), satisfying both what and when with an explicit trigger clause.

3 / 3

Trigger Term Quality

Includes natural phrases users would actually say ('which model to use', 'compare model costs', "what's cheapest for this task", 'should I use Opus or Sonnet', 'can a smaller model handle this') plus the '/model-cost-compare' slash command, giving broad coverage.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear model-cost-comparison niche with a distinct slash command and specific trigger phrasings, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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
mergisi/awesome-openclaw-agents
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.