anthropic-expert

Comprehensive Anthropic product expertise covering Claude models, Claude API, Python SDK, Agent SDK, Claude Code, and Model Context Protocol. Six integrated capabilities with complete documentation, searchable references, code examples, and cross-product integration patterns. Use when working with Claude API, building agents, using SDKs, developing with Claude Code, integrating MCP servers, learning Anthropic products, optimizing costs, implementing Anthropic features, managing context, using Opus 4.5, or implementing advanced tool patterns.

Quality

73%

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/anthropic-expert/SKILL.md

Quality

Content

67%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-organized navigation hub with executable examples and clear integration workflows. It loses points mainly to repetition-driven verbosity and a handful of dangling cross-references to non-existent sibling skill files.

Suggestions

Deduplicate the code examples (Common Workflows repeats Quick Start) and collapse the Product Navigator / Feature Finder / per-capability Quick Navigation tables into a single reference index to tighten conciseness.

Resolve or remove dangling references to missing files (README.md and claude-opus-4-5-guide, claude-context-management, claude-advanced-tool-use, claude-cost-optimization SKILL.md) so every signaled path resolves.

Complete the tool-use code example (replace the '...' ellipsis with a full tool definition) so all inline examples are copy-paste ready.

Dimension	Reasoning	Score
Conciseness	At ~661 lines the body repeats itself: the Quick Start code is restated in Common Workflows, multiple navigation tables (Product Navigator, Feature Finder, per-capability Quick Navigation) restate the same reference paths, and the Overview restates the description; mostly efficient but padded.	3 / 5
Actionability	Provides executable code (Quick Start, streaming, tool use, prompt caching), concrete search commands ('python scripts/search-docs.py "prompt caching"'), and Admin API endpoints; minor gaps such as the tool-use example ending in an ellipsis ('...').	4 / 5
Workflow Clarity	Integration Scenarios 1-4 and 'Leverage Progressive Features' give clear numbered sequences (Development -> Agent Creation -> Production; Basic API -> Streaming -> Caching -> Tools -> ...); these are conceptual rather than destructive/batch ops so the validation cap does not apply, leaving only minor gaps.	4 / 5
Progressive Disclosure	Clear overview structure with well-signaled one-level-deep references to 8 existing reference files plus search-docs.py and a Documentation Structure tree; gap is that README.md and four sibling SKILL.md paths referenced in See Also / Feature Finder do not exist in the bundle.	4 / 5
	Total	15 / 20 Passed

Description

80%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 clearly states what the skill covers and when to use it with abundant natural trigger phrases. Its main weakness is breadth: it is a mega-skill whose triggers overlap with more specialized sibling skills, creating real conflict risk.

Suggestions

Narrow the 'Use when' list or reword overlapping triggers ('using Opus 4.5', 'managing context', 'optimizing costs', 'advanced tool patterns') to defer to the dedicated sibling skills and reduce conflict risk.

Soften 'Comprehensive Anthropic product expertise' toward concrete actions (e.g., 'Navigates, searches, and cross-references documentation for...') to lift specificity from descriptive to actionable.

Tighten the capability list to the distinct value this skill adds over its specialized peers.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities across 6 product areas plus 'complete documentation, searchable references, code examples, and cross-product integration patterns', though the actions skew descriptive rather than concrete verbs; coverage is broad with minor gaps.	4 / 5
Completeness	Explicitly answers both what ('Comprehensive Anthropic product expertise covering...Six integrated capabilities...') and when ('Use when working with Claude API, building agents...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The 'Use when...' clause packs natural phrases ('working with Claude API, building agents, using SDKs, developing with Claude Code, integrating MCP servers, optimizing costs, managing context, using Opus 4.5') giving good keyword coverage with a few synonyms missing.	4 / 5
Distinctiveness Conflict Risk	The 'Anthropic products' niche is identifiable but triggers like 'using Opus 4.5', 'managing context', 'optimizing costs', and 'advanced tool patterns' overlap with dedicated sibling skills, and the 'Comprehensive' framing is a broad over-claim.	3 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (662 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/anthropic-expert/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.