CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-upgrade-migration

Plan and execute Deepgram SDK upgrades and model migrations. Use when upgrading SDK versions (v3 to v4 to v5), migrating models (Nova-2 to Nova-3), or planning API version transitions. Trigger: "upgrade deepgram", "deepgram migration", "update deepgram SDK", "deepgram version upgrade", "nova-3 migration".

67

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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 with concrete, executable migration code, but it is held back by an orphaned bundle reference (implementation.md is never linked), a validation suite that tests the old rather than the new API, missing explicit validation feedback loops, and some explanatory filler. It is a solid, mostly-efficient guide that needs tighter structure and a corrected validation step.

Suggestions

Link references/implementation.md from the body (e.g., a "## Implementation details" section pointing to it) so the bundle reference is discoverable rather than orphaned, and consider moving the full A/B test and validation suites into that reference to slim the SKILL.md overview.

Rewrite the Step 4 A/B test and Step 5 validation suite to use the v5 API (new DeepgramClient / listen.v1.media / speak.v1.audio.generate) so the validation actually exercises the migrated code rather than the pre-migration createClient path.

Add an explicit validate→fix→retry feedback loop with a gating checkpoint (e.g., "Only proceed to rollback-or-release when the validation suite passes") between the migration and rollback steps, and remove the marketing-style Nova-3 improvements bullet list to tighten conciseness.

DimensionReasoningScore

Conciseness

Mostly efficient executable code, but includes unnecessary explanatory filler (the "Nova-3 improvements over Nova-2" bullet list on accuracy/accents/pricing) and the SDK Version History table overlaps the Step 2 migration map, so it could be tightened.

2 / 3

Actionability

Dense, copy-paste-ready guidance throughout: side-by-side v3/v4 vs v5 migration code, a complete A/B test function, a full vitest validation suite, and concrete npm/curl rollback commands — matching the fully-executable anchor.

3 / 3

Workflow Clarity

Steps 1–6 are sequenced and a validation suite exists, but there is no explicit validate→fix→retry feedback loop or "only proceed when valid" checkpoint, and the validation/A-B-test code uses the pre-migration createClient API instead of v5, so it does not actually validate the migrated result.

2 / 3

Progressive Disclosure

Sections are well-organized, but the bundle file references/implementation.md is never linked or signaled from the body, and large detailed code blocks (A/B test, validation suite) that could live in references are kept inline — matching the "references present but not clearly signaled; content that should be separate is inline" anchor.

2 / 3

Total

9

/

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.

The description is well-crafted: it states concrete Deepgram-specific actions, provides explicit "Use when" triggers plus a enumerated trigger-term list, uses third person, and occupies a distinctive niche unlikely to conflict. It meets the top anchor on every dimension with no over-claims or fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete action types in a specific domain: "upgrading SDK versions (v3 to v4 to v5), migrating models (Nova-2 to Nova-3), or planning API version transitions" — matching the anchor that enumerates several specific concrete actions rather than vague verbs.

3 / 3

Completeness

Explicitly answers both what ("Plan and execute Deepgram SDK upgrades and model migrations") and when ("Use when upgrading SDK versions... migrating models... or planning API version transitions") with an explicit Trigger clause, satisfying the top anchor.

3 / 3

Trigger Term Quality

Explicit natural trigger phrases a user would actually say: "upgrade deepgram", "deepgram migration", "update deepgram SDK", "deepgram version upgrade", "nova-3 migration" — strong coverage matching the top anchor.

3 / 3

Distinctiveness Conflict Risk

A narrow Deepgram-only niche with version- and model-specific triggers (v3->v5, Nova-2->Nova-3) that are unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

12

/

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.