CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

claude-sdk-integration-patterns

Expert integration patterns for Claude API and TypeScript SDK covering Messages API, streaming responses, tool use, error handling, token optimization, and production-ready implementations for building AI-powered applications

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/luxor-ai-integration/skills/claude-sdk-integration-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 content is highly actionable with extensive executable code, but it is verbose in places that explain concepts Claude already knows and is a monolithic wall of text with no progressive disclosure into reference files. Organization is decent via clear section headers.

Suggestions

Remove or tighten the 'Core Concepts' and 'Best Practices' sections that restate knowledge Claude already has; keep only non-obvious, SDK-specific guidance.

Split the pattern catalog into one-level-deep reference files (e.g., references/streaming.md, references/tool-use.md, references/error-handling.md) with the SKILL.md serving as a concise overview with clearly signaled links.

Fix inaccurate guidance in Pattern 12 (the comment claims Claude uses GPT-like tokenization; recommend the SDK's token-counting endpoint or Anthropic's tokenizer instead).

DimensionReasoningScore

Conciseness

Mostly efficient code blocks, but several padded sections explain concepts Claude already knows ('Core Concepts' defines Messages API fundamentals and model selection; 'Best Practices' restates 'Never hardcode API keys'/'Always catch API errors'; repeated per-pattern 'When to use' lists).

3 / 5

Actionability

16 patterns provide fully executable, copy-paste-ready TypeScript covering the common cases (create, multi-turn, stream, tool use, retry, batch) with concrete imports and parameters.

5 / 5

Workflow Clarity

Well-organized pattern catalog where each recipe is unambiguous and grouped by section, but it lacks explicit validation/feedback-loop checkpoints that would warrant a 5.

4 / 5

Progressive Disclosure

No bundle files exist and the entire ~590-line content is inlined in one monolithic SKILL.md; section headers give some structure, but content that should be split (full pattern catalog, troubleshooting) is inline with no one-level-deep references.

3 / 5

Total

15

/

20

Passed

Description

66%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 uses natural developer trigger terms, but it omits any explicit 'Use when...' guidance, which is the primary weakness. It is mostly distinct from sibling skills though slightly broad at the tail.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger scenarios (e.g., 'Use when integrating Claude into Node.js/TypeScript apps, implementing streaming or tool use, or handling API errors and retries').

Replace buzzword padding ('Expert integration patterns', 'production-ready implementations for building AI-powered applications') with concrete verbs describing what the skill does.

Include natural synonyms/variations users might say (e.g., 'function calling', 'Claude SDK', 'Anthropic API') to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists several specific coverage areas ('Messages API, streaming responses, tool use, error handling, token optimization') beyond just naming the domain, though they are noun-topics rather than concrete verbs and 'Expert integration patterns'/'production-ready implementations' add buzzword padding.

4 / 5

Completeness

Clearly states the 'what' (integration patterns and covered capabilities) but provides no 'Use when...' or equivalent explicit trigger guidance, capping completeness at 3 per the missing-trigger rule.

3 / 5

Trigger Term Quality

Contains natural developer terms ('Claude API', 'TypeScript SDK', 'streaming', 'tool use') that users would actually say, but misses common synonyms and variations.

4 / 5

Distinctiveness Conflict Risk

The Claude API + TypeScript SDK niche is mostly distinct, with only minor overlap risk against a general claude-api skill and some breadth from 'building AI-powered applications'.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (591 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

manutej/luxor-claude-marketplace

Path

plugins/luxor-ai-integration/skills/claude-sdk-integration-patterns/SKILL.md

Revision

1861cc9

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill