Name: claude-opus-4-5-guide
Rating: 63.2 (1 reviews)
Author: fernandezbaptiste

claude-opus-4-5-guide

Comprehensive guide to Claude Opus 4.5, Anthropic's most intelligent model with effort parameter for reasoning control. Covers model capabilities, benchmarks, effort levels (high/medium/low), hybrid reasoning, and model selection. Use when working with Opus 4.5, optimizing reasoning depth, choosing models, or understanding effort parameter trade-offs.

Quality

75%

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 ./.claude/skills/claude-opus-4-5-guide/SKILL.md

The canonical home for this skill is claude-opus-4-5-guide in fernandezbaptiste/Skrillz

Quality

Content

61%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 well-organized with executable code and properly signaled reference files that exist in the bundle. Its main weaknesses are marketing-fluff verbosity in the Overview and the absence of an explicit multi-step workflow with checkpoints, which limits workflow clarity for a reference-style skill.

Suggestions

Trim marketing language in the Overview (e.g., "revolutionary", "best model in the world", "model tier reduction") to lean factual statements Claude can act on.

Move the full benchmark and model-spec comparison tables into the existing references, keeping only a compact summary inline to improve token efficiency and progressive disclosure.

Add a short explicit decision flow (e.g., pick model → pick effort level → call API) with a validation note to raise workflow clarity from a reference path to a guided sequence.

Dimension	Reasoning	Score
Conciseness	The Overview is padded with marketing language ("revolutionary", "best model in the world", "state-of-the-art", "model tier reduction") that Claude does not need, though the tables and code sections are mostly efficient.	3 / 5
Actionability	Quick Start provides copy-paste-ready Python with real model IDs and effort-parameter beta flags, plus concrete spec/benchmark tables; minor gaps in TypeScript examples and edge-case coverage.	4 / 5
Workflow Clarity	The guide offers a reasonable When-to-Use → Quick-Start → Key-Features → References navigation path, but it is a reference skill with no multi-step process or validation checkpoints, so sequence clarity is implicit rather than explicit.	3 / 5
Progressive Disclosure	Body is well-structured with clear sections and three real, well-signaled one-level-deep references (effort-parameter-guide.md, model-selection-guide.md, model-capabilities.md) that exist on disk; minor gap is that full benchmark and spec tables are inlined rather than fully delegated to references.	4 / 5
	Total	14 / 20 Passed

Description

88%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, third-person, and answers both what and when with concrete trigger phrases. It is a strong, well-targeted description with only minor gaps in synonym/extension coverage and slight overlap risk on model-selection triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete coverage areas—"model capabilities, benchmarks, effort levels (high/medium/low), hybrid reasoning, and model selection"—giving comprehensive, specific scope rather than vague language.	5 / 5
Completeness	Explicitly states what ("Comprehensive guide... Covers...") and when ("Use when working with Opus 4.5, optimizing reasoning depth, choosing models..."), with concrete trigger phrases in third person.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ("working with Opus 4.5", "optimizing reasoning depth", "choosing models", "effort parameter trade-offs") but omits some synonyms and concrete identifiers like model IDs or "Claude API".	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to the Opus 4.5 niche with distinct triggers, though "choosing models" creates minor overlap risk with broader model-selection skills.	4 / 5
	Total	18 / 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: .claude/skills/claude-opus-4-5-guide/SKILL.md
Commit: 93ed392

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.