CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/deepgram-pack/skills/deepgram-migration-deep-dive/SKILL.md
SKILL.md
Quality
Evals
Security

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 and a sensible migration sequence, but it is let down by weak progressive disclosure (an unreferenced duplicate bundle file) and a rollout that lacks an automated validation gate before increasing traffic. It is also somewhat padded with marketing claims.

Suggestions

Link to references/implementation.md from the body and move the duplicated adapter/router/similarity code there, keeping SKILL.md as an overview plus the unique feature-mapping tables and checklist.

Add an explicit rollout gate in the router (e.g. only auto-advance deepgramPercent when validateMigration passes a threshold) so the feedback loop is in code, not prose.

Trim editorial padding such as "10-100x faster" and "Deepgram advantage" notes that do not advance the task.

DimensionReasoningScore

Conciseness

The body is information-dense and mostly avoids explaining concepts Claude already knows, but it carries padding such as "10-100x faster" and "Deepgram advantage" notes, and it duplicates much of references/implementation.md inline rather than deferring to that file, fitting the level-2 anchor.

2 / 3

Actionability

It provides fully executable TypeScript for the adapter interface, Deepgram adapter, AWS adapter, migration router, and Jaccard validation harness — concrete and copy-paste ready, matching the level-3 anchor; minor gaps (Google/Azure adapters only mapped, AWS.transcribeFile throws) do not reduce it below 3.

3 / 3

Workflow Clarity

Steps 1–6 are clearly sequenced and a validation harness with a similarity threshold exists, but the production rollout progression is governed by prose ("Increase if no issues") rather than an automated gating checkpoint, so for this risky batch/traffic-shifting operation the feedback loop is only implicit per the level-2 anchor.

2 / 3

Progressive Disclosure

A references/implementation.md bundle exists but is never linked or signaled from the SKILL.md body, and the body itself inlines ~350 lines of code that largely duplicate that file, fitting the level-2 anchor of references present but not clearly signaled with content that should be separate kept inline.

2 / 3

Total

9

/

12

Passed

Description

90%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.

The description is strong: it states a clear niche, explicit "Use when" guidance, and natural trigger phrases. Its only weakness is specificity — it relies on the single verb "migrating" rather than enumerating concrete migration actions.

Suggestions

Replace the generic verb "migrating" with concrete actions, e.g. "Map provider features, build adapter interfaces, run parallel validation, and shift traffic to Deepgram".

Consider tightening the trigger list slightly; six quoted phrases plus a 'Trigger:' label is more verbose than the concise style the good examples use.

DimensionReasoningScore

Specificity

The description names the domain and target providers ("migrating to Deepgram from other transcription providers" plus AWS, Google, Azure, Whisper, AssemblyAI, Rev.ai) but the only concrete action stated is "migrating" — there is no list of specific concrete actions as in the level-3 anchor.

2 / 3

Completeness

It explicitly answers both what ("migrating 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 to Deepgram"), satisfying the level-3 anchor.

3 / 3

Trigger Term Quality

It supplies six natural trigger phrases a user would actually say ("deepgram migration", "switch to deepgram", "migrate transcription", "deepgram from AWS", "deepgram from Google", "replace whisper with deepgram"), matching the level-3 anchor's good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

The niche is narrow and provider-specific with distinct triggers, making it unlikely to fire for unrelated transcription or general SaaS skills, matching the level-3 anchor.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.