using-llm

List available large language models and send chat completion requests programmatically. Use this skill when you need to call an LLM within a snippet, including model comparison, visual understanding, batch inference, and model performance testing.

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

72%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.

Highly actionable with complete executable examples, but the long single-file body repeats boilerplate and lacks both error-recovery checkpoints and any progressive disclosure into reference files.

Suggestions

Add a brief validate/retry loop for batch and vision calls (e.g., check finish_reason and retry on errors) so the batch-inference workflow has an explicit feedback checkpoint.

Factor the repeated create_openai_sync_client() + SUPER_MAGIC_CURRENT_MODEL_ID boilerplate into a single canonical snippet and reference it, or move the full parameter/return-value tables into a REFERENCES.md to shorten SKILL.md.

Consolidate the three near-identical thinking extra_body examples into one block showing disabled/enabled/auto side by side.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the create_openai_sync_client() + SUPER_MAGIC_CURRENT_MODEL_ID boilerplate repeats across ~4 code blocks and the thinking extra_body snippet is shown three times, so a few tokens could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready Python examples cover the common cases (list models, chat, custom provider, vision) alongside concrete parameter and return-value reference tables.	5 / 5
Workflow Clarity	A list-models-then-call sequence and timeout guidance are present, but there are no explicit validation or error-recovery feedback loops; because the skill covers batch inference, the missing feedback-loop cap holds this at 3.	3 / 5
Progressive Disclosure	The body is well-sectioned but entirely inline with no bundle files or one-level-deep references, and reference-style material (full parameter tables, return-value docs) lives in SKILL.md rather than being split out.	3 / 5
	Total	15 / 20 Passed

Description

92%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, concrete description that clearly states both capabilities and trigger conditions with minimal fluff. The only minor gap is trigger-term synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "List available large language models", "send chat completion requests", "visual understanding", "batch inference", "model comparison", "model performance testing" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (list models, send chat completions, vision, batch, comparison, performance testing) and when ("Use this skill when you need to call an LLM within a snippet, including...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("call an LLM", "model comparison", "batch inference", "visual understanding") but lacks some common synonyms and variants, so coverage is good rather than exhaustive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — calling LLMs programmatically within snippets — with distinct triggers, making it unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/using-llm/SKILL.md
Commit: f9973c5

Reviewed: 2 days 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.