Tessl • The management layer for AI agent skills

SkillPublic

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

82%

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

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 body is highly actionable with executable code and dense reference tables, and it points to real, well-signaled reference files. Its main weakness is conciseness: marketing-style prose and scattered time-sensitive details pad the guide beyond what Claude needs to know.

Suggestions

Cut promotional framing ('best model in the world', star intelligence ratings, 'previously requiring human expertise') and keep the benchmark/spec tables as the source of truth — Claude needs the numbers, not the sales pitch.

Consolidate time-sensitive details (release dates, knowledge cutoffs, model IDs) into one clearly marked section or a reference file so the body stays stable as versions change.

Add a brief inline model-selection decision rule (e.g., 'complex reasoning/agents -> Opus 4.5, fast routine tasks -> Sonnet/Haiku') so the most common question is answerable without opening the reference file.

Dimension	Reasoning	Score
Conciseness	Mostly efficient data-dense tables and code, but padded marketing prose ('best model in the world for complex coding', 'previously requiring human expertise', star-based intelligence ratings) assumes no competence, and time-sensitive dates/versions ('released November 24, 2025', knowledge cutoffs) are scattered rather than isolated. Could be tightened by cutting the promotional framing.	3 / 5
Actionability	Fully executable, copy-paste-ready Python for basic usage and all three effort levels, with the real model ID ('claude-opus-4-5-20251101'), output_config, and beta header, plus concrete pricing and model-ID tables covering common cases.	5 / 5
Workflow Clarity	As a reference skill there is no multi-step process, and lookup paths are clear ('When to Use This Skill', effort-level table with use cases, 'Best Practice: Default to high effort, then measure and decrease strategically'). Not 5 because the actual model-selection decision flow is deferred to a reference file rather than stated inline, leaving a minor gap for the most common question.	4 / 5
Progressive Disclosure	Three real, one-level-deep reference files (references/effort-parameter-guide.md, model-selection-guide.md, model-capabilities.md) are clearly signaled with purpose statements at the end. Not 5 because the full specification and benchmark tables inlined in the body duplicate what the references cover, and the 'Related Skills' links point to unverifiable ../ sibling skill paths.	4 / 5
	Total	16 / 20 Passed

Description

83%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 that explicitly covers both what the skill contains and when to use it, with natural trigger terms centered on the Opus 4.5 model name and effort parameter. Minor improvements possible by trimming the 'Comprehensive guide' opener and adding model-selection synonyms.

Dimension	Reasoning	Score
Specificity	The description lists several specific coverage areas ('Covers model capabilities, benchmarks, effort levels (high/medium/low), hybrid reasoning, and model selection'), but opens with mild fluff ('Comprehensive guide') and names topics rather than concrete actions. Not 5 because it lacks the action-verb specificity of the top anchor; not 3 because coverage goes well beyond 1-2 items.	4 / 5
Completeness	It clearly answers both what ('Comprehensive guide to Claude Opus 4.5... Covers model capabilities, benchmarks, effort levels (high/medium/low), hybrid reasoning, and model selection') and when ('Use when working with Opus 4.5, optimizing reasoning depth, choosing models, or understanding effort parameter trade-offs') with concrete trigger phrases. Third person voice is used throughout.	5 / 5
Trigger Term Quality	'Use when working with Opus 4.5, optimizing reasoning depth, choosing models, or understanding effort parameter trade-offs' includes good natural trigger terms users would say. Not 5 because common variations like 'which Claude model', 'reasoning effort', or 'model comparison' are missing.	4 / 5
Distinctiveness Conflict Risk	Naming the specific model and the exclusive 'effort parameter' creates a clear niche with distinct triggers. Not 5 because 'choosing models' is broad and could overlap with general Claude API or model-selection skills.	4 / 5
	Total	17 / 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: skills/claude-opus-4-5-guide/SKILL.md
Revision: 93ed392

Reviewed: 11 days ago

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.

claude-opus-4-5-guide

Table of Contents

Is this your skill?