model-cost-compare

Starter: compare model costs for a described task — maps task shape to the cheapest adequate seat and shows the price spread

Quality

71%

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 ./skills/octopus-starter-pack/model-cost-compare/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 skill body is a tight, actionable decision procedure with clear sequencing and a risk-escalation checkpoint, scoring well across all dimensions. It could improve by adding a worked cost example and an explicit feedback/retry loop for ambiguous classifications.

Suggestions

Add a short worked example showing the cost computation and the three-row spread for one sample task.

Add an explicit feedback step for when the classification is ambiguous (re-classify or ask the user) to strengthen the workflow loop.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly efficient, listing the roster and rules without explaining concepts Claude already knows; a few sentences could be trimmed (e.g. repeated Fable/Astra opt-in reminders) but it generally respects the token budget.	4 / 5
Actionability	It gives concrete pricing, a concrete classification scheme, and a specific three-row spread output format; minor gaps are that cost math is described rather than shown as a worked example.	4 / 5
Workflow Clarity	Six clearly sequenced steps cover classify, estimate, price, recommend, check risk, and show spread, with an explicit $1 estimate escalation checkpoint; it lacks an explicit validate/retry feedback loop but the operations are advisory rather than destructive.	4 / 5
Progressive Disclosure	Content is well organized into When-to-use, Steps, and Guardrails sections with one external reference (CLAUDE.md cost table, skills/blocks/fable5-prompting.md); no bundle files exist, so structure is appropriate for a short single-file skill with minor gaps.	4 / 5
	Total	16 / 20 Passed

Description

67%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 reasonably distinctive, clearly conveying the skill's purpose of cost-based model selection. Its main weakness is the absence of an explicit 'Use when...' trigger clause and thinner natural keyword coverage, which cap completeness and trigger quality at 4 and 3.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks which model to use for a task or what it will cost'.

Include natural phrasing variations users actually say, e.g. 'cheapest model', 'how much will this cost', 'which model should I use'.

Dimension	Reasoning	Score
Specificity	Names the domain (model cost comparison) and several concrete actions (map task shape, find cheapest adequate seat, show price spread) with only minor gaps in coverage.	4 / 5
Completeness	It states what it does (maps task shape to cheapest adequate seat, shows price spread) and implies when via 'for a described task', but the 'when' is not an explicit 'Use when...' clause so it falls short of a 5.	4 / 5
Trigger Term Quality	Phrases like 'compare model costs', 'described task', and 'price spread' are relevant but it lacks the common natural variations users would say (e.g. 'which model', 'how much will it cost', 'cheapest model').	3 / 5
Distinctiveness Conflict Risk	The niche (cost-driven model/seat selection) is fairly distinct and unlikely to conflict with unrelated skills, with only minor overlap risk against general model-selection helpers.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: skills/octopus-starter-pack/model-cost-compare/SKILL.md
Commit: 805d58c

Reviewed: 1 day 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.