deepgram-sdk-patterns

Apply production-ready Deepgram SDK patterns for TypeScript and Python. Use when implementing Deepgram integrations, refactoring SDK usage, or establishing team coding standards for Deepgram. Trigger: "deepgram SDK patterns", "deepgram best practices", "deepgram code patterns", "idiomatic deepgram", "deepgram typescript".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

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

The content is lean and highly actionable with executable code in both languages and a useful error table, but it presents independent patterns as a pseudo-workflow without validation checkpoints and fails to surface its own reference bundle.

Suggestions

Relabel 'Step 1–6' as topical sections (e.g. 'Singleton Client', 'Text-to-Speech') rather than sequential steps, since they are independent patterns, not an ordered workflow.

Add explicit validation/feedback guidance where operations can fail or be destructive — e.g. check the TTS stream is non-empty before writing, and verify transcription results before parsing channels/alternatives.

Link references/code-patterns.md from the body (e.g. under a 'More patterns' section) so the live-streaming, batch-concurrency, and speaker-formatter examples it contains are discoverable rather than stranded.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable code with brief section headers and no explanation of concepts Claude already knows; every block is a distinct, earning pattern rather than padding.	3 / 3
Actionability	It provides complete, copy-paste-ready TypeScript and Python implementations plus a concrete error/cause/solution table, fully executable rather than pseudocode.	3 / 3
Workflow Clarity	The 'Step 1–Step 6' headings present independent patterns rather than a true sequenced process, and there are no validation checkpoints or feedback loops for the operations shown.	2 / 3
Progressive Disclosure	The skill is fairly monolithic — six full code patterns live inline in SKILL.md — and the existing references/code-patterns.md bundle file is never signaled or linked from the body, so content that should be split out stays inline.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 answers both what and when with explicit, distinctive Deepgram-scoped triggers, but its capability verbs are more abstract than concrete and its trigger set is narrow and pattern-focused rather than task-focused.

Suggestions

Replace abstract verbs with concrete actions, e.g. 'transcribe audio, generate speech with Aura, run sentiment/intent analysis, migrate to SDK v5' instead of 'implementing integrations, refactoring usage, establishing standards'.

Add task-oriented trigger terms users would naturally say, such as 'deepgram transcription', 'deepgram text to speech', 'deepgram TTS', and 'deepgram speech to text', alongside the existing pattern-focused ones.

Drop the 'production-ready' qualifier to reduce buzzword padding while keeping the same meaning.

Dimension	Reasoning	Score
Specificity	It names the domain and several actions ('implementing Deepgram integrations, refactoring SDK usage, or establishing team coding standards'), but these are higher-level and more abstract than the concrete level-3 actions like 'extract text, fill forms, merge documents'; 'production-ready' also leans on buzzword framing.	2 / 3
Completeness	It explicitly states what it does ('Apply production-ready Deepgram SDK patterns for TypeScript and Python') and when to use it ('Use when implementing Deepgram integrations...'), plus an explicit Trigger clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Triggers like 'deepgram best practices' and 'deepgram SDK patterns' are plausible, but the set is narrow and somewhat jargon-y ('idiomatic deepgram', 'deepgram code patterns') and misses common task-oriented variations users would say such as 'deepgram transcription', 'deepgram TTS', or 'deepgram speech to text'.	2 / 3
Distinctiveness Conflict Risk	It occupies a clear Deepgram-specific niche with triggers all carrying the 'deepgram' qualifier, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 02d6341

Reviewed: about 16 hours 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.