deepgram-migration-deep-dive

Deep dive into migrating to Deepgram from other transcription providers. Use when migrating from AWS Transcribe, Google Cloud STT, Azure Speech, OpenAI Whisper, AssemblyAI, or Rev.ai to Deepgram. Trigger: "deepgram migration", "switch to deepgram", "migrate transcription", "deepgram from AWS", "deepgram from Google", "replace whisper with deepgram".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

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

The body is highly actionable, well sequenced, and includes built-in validation and rollback for a risky migration. Its main weakness is progressive disclosure: full implementations are inline while the bundled reference file is orphaned and undisc discoverable.

Suggestions

Move the full adapter/router implementations into references/implementation.md and link to it from a concise overview in the body, keeping only the interface and a quick-start snippet inline.

Add a clearly signaled reference link (e.g. 'See [implementation.md](references/implementation.md) for full adapter code') so the existing bundle is discoverable.

Reconcile the body's nova-3 model recommendation with implementation.md's nova-2 to avoid inconsistent guidance across files.

Dimension	Reasoning	Score
Conciseness	The body is dense executable TypeScript plus feature-mapping tables with minimal prose, and it does not explain concepts Claude already knows; nearly every section earns its place.	3 / 3
Actionability	Provides complete, copy-paste-ready code for the adapter interface, Deepgram/AWS adapters, migration router, and Jaccard validation, alongside concrete per-provider feature mappings.	3 / 3
Workflow Clarity	Six clearly sequenced steps with explicit validation checkpoints (Jaccard similarity threshold, pass/fail reporting) and rollback guidance (setDeepgramPercent(0)) for this risky batch migration.	3 / 3
Progressive Disclosure	The body is well sectioned but monolithic, with full implementations inline; a references/implementation.md bundle exists yet is never linked or signaled from the body, so content that should be separate is inline.	2 / 3
	Total	11 / 12 Passed

Description

90%

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 defines a clear niche and supplies explicit 'Use when' triggers with natural, well-covered phrasing. Its only weakness is the vague 'deep dive' framing in place of concrete capability verbs.

Suggestions

Replace 'Deep dive into migrating' with concrete actions, e.g. 'Migrate transcription pipelines to Deepgram using an adapter pattern, parallel-run validation, and percentage-based traffic shifting with rollback.'

Dimension	Reasoning	Score
Specificity	Names the transcription domain and a concrete list of source providers plus the 'migrating' action, but 'Deep dive into migrating' is vague and only one action verb is given rather than multiple concrete capabilities.	2 / 3
Completeness	Explicitly answers both what (migrate to Deepgram from other transcription providers) and when ('Use when migrating from AWS Transcribe, Google Cloud STT, Azure Speech, OpenAI Whisper, AssemblyAI, or Rev.ai') plus an explicit Trigger list.	3 / 3
Trigger Term Quality	Includes natural phrases a user would actually say ('deepgram migration', 'switch to deepgram', 'replace whisper with deepgram') with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Narrowly scoped to Deepgram migration from named providers with provider-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: 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.