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

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

65%Weight 40%Scale 1-3

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 complete, executable code for four architecture patterns, but it is monolithic — a bundle file exists yet is never referenced, and batch operations lack explicit validation feedback loops. Tightening the overview and offloading detail to the existing reference would lift both conciseness and progressive disclosure.

Suggestions

Add explicit validate->fix->retry checkpoints around the async queue worker (e.g., verify job output and re-enqueue on partial failure) to reach workflow clarity 3 for batch operations.

Replace inline full implementations of the less-common patterns (callback, hybrid router) with concise overviews that link to references/implementation.md, moving SKILL.md toward a lean overview with one-level-deep references.

Signal the existing reference explicitly in the body — e.g., "Full implementation details: [implementation.md](references/implementation.md)" — so the bundle file is discoverable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes competence, but four full TypeScript implementations plus a large ASCII diagram are inline; some prose and full code blocks could be tightened or offloaded to keep the overview lean.	2 / 3
Actionability	Four complete, executable TypeScript patterns (sync REST, BullMQ queue, WebSocket proxy, hybrid router) are copy-paste ready with real imports, options, and error handling, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Steps 1-5 present patterns as parallel alternatives rather than a sequenced process, and the batch/queue operations lack explicit validate->fix->retry feedback loops, which caps workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	A references/implementation.md bundle file exists but the body never links to or signals it; all detailed implementations are inline in a monolithic SKILL.md rather than split into one-level-deep references.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that states concrete capabilities, an explicit Use-when clause, and natural trigger terms scoped tightly to Deepgram architecture. No fluff or over-claims; every element earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Implement Deepgram reference architecture for scalable transcription systems", "designing transcription pipelines, building production architectures, or planning Deepgram integration at scale" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers both what (implement Deepgram reference architecture for scalable transcription) and when ("Use when designing transcription pipelines, building production architectures, or planning Deepgram integration at scale") with an explicit trigger block.	3 / 3
Trigger Term Quality	Explicit trigger list ("deepgram architecture", "transcription pipeline", "deepgram system design", "deepgram at scale", "enterprise deepgram", "deepgram queue") gives good coverage of natural terms a user would say.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to Deepgram transcription architecture with Deepgram-specific triggers, making it clearly distinguishable and unlikely to fire for unrelated skills.	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
Path: plugins/saas-packs/deepgram-pack/skills/deepgram-reference-architecture/SKILL.md
Commit: 0540a62

Reviewed: about 18 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.