deepgram-reference-architecture

Implement Deepgram reference architecture for scalable transcription systems. Use when designing transcription pipelines, building production architectures, or planning Deepgram integration at scale. Trigger: "deepgram architecture", "transcription pipeline", "deepgram system design", "deepgram at scale", "enterprise deepgram", "deepgram queue".

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.

Strong actionability and conciseness with executable TypeScript for all four architectures, but workflow clarity is capped by missing validation checkpoints on batch operations, and progressive disclosure is undermined by an unreferenced, duplicative bundle file.

Suggestions

Add explicit validation/verification checkpoints to the async queue and callback workflows (e.g., verify job completion, retry-on-failure feedback loops) to lift workflow clarity above 2.

Reference references/implementation.md from the body (e.g., a '## Implementation details' section linking to it) and de-duplicate the shared patterns so the inline content points one level deep rather than repeating the bundle.

Replace the Step 4 hybrid router's 'auto' selection with an explicit validation step that confirms the estimated duration before routing, giving the multi-step process a clear checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean — minimal prose, no explanation of concepts Claude already knows, and every code block is actionable rather than padded context — matching the 'every token earns its place' anchor.	3 / 3
Actionability	Four complete, executable TypeScript implementations (Sync REST, BullMQ queue, WebSocket proxy, hybrid router) that are copy-paste ready with real imports and configuration.	3 / 3
Workflow Clarity	Steps are labeled (Step 1–5) but the async queue and callback paths are batch operations with no validation or validate→fix→retry checkpoints, which caps workflow clarity at 2 per the rubric guideline.	2 / 3
Progressive Disclosure	A references/implementation.md bundle exists but is never referenced from the body and largely duplicates the inline patterns; the inline patterns that could live one level deep are not clearly signaled out.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 well-crafted description: concrete actions, explicit 'Use when' guidance, natural trigger terms, and a clearly distinct Deepgram niche. No first/second-person voice or vague fluff is present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'designing transcription pipelines, building production architectures, or planning Deepgram integration at scale' — matching the multi-action anchor rather than the single-domain score 2.	3 / 3
Completeness	Explicitly answers both what ('Implement Deepgram reference architecture for scalable transcription systems') and when ('Use when designing...') with an explicit trigger list, so it is not capped at 2.	3 / 3
Trigger Term Quality	Provides good coverage of natural trigger phrases a user would say ('deepgram architecture', 'transcription pipeline', 'enterprise deepgram', 'deepgram queue'), matching the broad-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Deepgram-specific niche with distinct triggers ('deepgram architecture', 'deepgram at scale') makes it unlikely to fire for an unrelated skill.	3 / 3
	Total	12 / 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: 4 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.