CtrlK
BlogDocsLog inGet started
Tessl Logo

llm-integration

LLM integration patterns including API usage, streaming, function calling, RAG pipelines, and cost optimization

63

Quality

73%

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 ./skills/llm-integration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and highly actionable with complete executable code across all major LLM integration patterns. The main gap is the absence of explicit validation/retry feedback loops in the code itself, despite anti-patterns calling them out.

Suggestions

Add an explicit retry-with-exponential-backoff wrapper to the API call examples so the code matches the anti-pattern/checklist guidance.

Include a short validation checkpoint in the RAG and function-calling flows (e.g., verify retrieved chunks are non-empty or validate tool inputs before execution).

Surface token-usage tracking in an actual code example rather than only in the checklist to make the cost-control workflow concrete.

DimensionReasoningScore

Conciseness

The body is lean: mostly executable TypeScript with minimal prose, no explanation of what an LLM is or how libraries work, and every section earns its place.

3 / 3

Actionability

Every section provides complete, executable TypeScript (API client, streaming, function-calling agent loop, RAG, chunking, model selection) that is copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

Sections are sequenced and the function-calling loop has a clear cycle, but there are no explicit validation/feedback checkpoints for risky operations (API calls, batch requests); the anti-patterns mention retry/backoff yet the code omits it, capping this at 2.

2 / 3

Progressive Disclosure

No bundle files exist; the skill is a single well-organized file with clearly delineated sections, which per the simple-skills note can score 3 without external references.

3 / 3

Total

11

/

12

Passed

Description

60%

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 concretely enumerates LLM integration capabilities but lacks an explicit usage trigger clause and leans on technical jargon rather than natural user phrasing. Adding a 'Use when...' clause with user-facing trigger terms would lift completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause stating when to invoke this skill, e.g. 'Use when integrating LLM APIs, building streaming responses, function calling, or RAG pipelines'.

Include natural user-facing trigger terms (e.g. 'chat with an LLM', 'add tool use', 'build a retrieval-augmented chatbot') rather than only technical labels like 'RAG pipelines'.

Narrow the scope or add a distinguishing qualifier to reduce overlap with generic coding/API-helper skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — 'API usage, streaming, function calling, RAG pipelines, and cost optimization' — matching the anchor that names several specific actions rather than vague abstractions.

3 / 3

Completeness

It clearly states what the skill does but provides no explicit 'when to use it' trigger; per the guidelines a missing 'Use when...' clause caps completeness at 2.

2 / 3

Trigger Term Quality

Terms like 'RAG pipelines', 'function calling', and 'streaming' are technical jargon rather than natural phrasings a user would say, and there is no 'Use when...' clause introducing common user variations.

2 / 3

Distinctiveness Conflict Risk

The LLM-integration niche is somewhat specific but broad enough that it could overlap with general coding or API-helper skills, so it is not a clearly conflict-free trigger set.

2 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rohitg00/awesome-claude-code-toolkit
Reviewed

Table of Contents

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.