deepgram-sdk-patterns

Apply production-ready Deepgram SDK patterns for TypeScript and Python. Use when implementing Deepgram integrations, refactoring SDK usage, or establishing team coding standards for Deepgram. Trigger: "deepgram SDK patterns", "deepgram best practices", "deepgram code patterns", "idiomatic deepgram", "deepgram typescript".

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/deepgram-pack/skills/deepgram-sdk-patterns/SKILL.md

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 executable, copy-paste-ready code across both SDKs, but it is held back by verbosity, missing validation checkpoints in its stepped workflow, and an un-signaled bundle file that breaks progressive disclosure.

Suggestions

Link references/code-patterns.md from the body (e.g., a '## Advanced patterns' section) so the live-streaming, batch, and speaker-formatter examples are discoverable instead of orphaned.

Add validation/verification checkpoints to the multi-step workflow (e.g., verify the API key is set and test a minimal transcription before running the full pipeline).

Move the Aura voice-options list and v5 migration notes into a reference file to tighten the main body and isolate time-sensitive version information.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable code, but the inline six-line Aura voice-options comment block, the duplicated singleton pattern (TypeScript Step 1 and Python Step 4), and version-specific v5 migration notes could be tightened or moved to a reference.	2 / 3
Actionability	Every step provides complete, copy-paste-ready TypeScript and Python code using real SDK calls (createClient, speak.request, listen.prerecorded.transcribeUrl), with concrete options and typed response helpers.	3 / 3
Workflow Clarity	Steps 1–6 are sequenced, but the body reads as a feature catalog with no validation checkpoints or fix-and-retry feedback loops, and the error-handling table is a reference rather than an inline workflow gate.	2 / 3
Progressive Disclosure	A bundle file references/code-patterns.md exists with additional patterns (live streaming, batch concurrency, speaker-labeled formatting) but is never signaled or linked from the body, leaving a ~250-line monolith that should point to it.	2 / 3
	Total	9 / 12 Passed

Description

75%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 clearly answers both 'what' and 'when' with explicit triggers and a distinct Deepgram-specific niche. It is slightly let down by a single-action 'what' statement and a trigger list that omits common user phrasings like 'transcription' or 'speech to text'.

Suggestions

Expand the 'what' sentence into multiple concrete actions (e.g., 'Build singleton clients, run transcription and text-to-speech, and migrate to SDK v5') to reach full specificity.

Add high-frequency natural triggers such as 'deepgram transcription', 'deepgram speech to text', and 'deepgram python' alongside the existing pattern-oriented phrases.

Dimension	Reasoning	Score
Specificity	The 'what' sentence is a single action verb ('Apply production-ready Deepgram SDK patterns for TypeScript and Python') that names the domain but does not list multiple distinct concrete actions like the score-3 anchor; the use-case list adds context but is framed as triggers rather than capabilities.	2 / 3
Completeness	It explicitly states what the skill does ('Apply production-ready Deepgram SDK patterns...') and when to use it ('Use when implementing Deepgram integrations, refactoring SDK usage, or establishing team coding standards'), with an additional explicit 'Trigger:' block.	3 / 3
Trigger Term Quality	Phrases like 'deepgram best practices' and 'deepgram typescript' are natural, but common variations a user would actually say ('deepgram transcription', 'speech to text', 'deepgram python') are missing, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	Every trigger contains 'deepgram' and the scope is tightly scoped to SDK coding patterns, giving it a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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-sdk-patterns/SKILL.md
Commit: 4c47e33

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.