deepgram-webhooks-events

Implement Deepgram callback and webhook handling for async transcription. Use when implementing callback URLs, processing async transcription results, or handling Deepgram event notifications. Trigger: "deepgram callback", "deepgram webhook", "async transcription", "deepgram events", "deepgram notifications", "deepgram async".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

A highly actionable, well-sequenced skill body with strong workflow checkpoints, undermined by weak progressive disclosure and redundancy: the bundled reference file is unlinked and duplicates code already inlined in SKILL.md. Tightening the body and offloading detail to the reference would lift the weaker dimensions.

Suggestions

Replace the inlined callback-server, client-SDK, and ngrok-testing code blocks with concise overviews that link to references/implementation.md, then keep SKILL.md to the unique flow (submit, verify, track, dedup) to remove the duplication.

Add explicit, clearly signaled references (e.g., '**Full callback server**: See [implementation.md](references/implementation.md)') so the reference is discoverable rather than orphaned.

Drop the 'Output' section, which only restates the steps above, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable code with little concept fluff, but it is very long, inlines six full implementations, duplicates much of references/implementation.md, and ends with a redundant 'Output' recap that restates the steps.	2 / 3
Actionability	Each step provides complete, copy-paste-ready TypeScript plus working curl examples (e.g., the submit, callback server, Redis tracker, and client SDK blocks), with specific configuration values like model 'nova-3' and a 50mb body limit.	3 / 3
Workflow Clarity	Steps 1–6 form a clear sequence with explicit validation checkpoints (HMAC signature verification returning 401, idempotency dedup, 500-to-trigger-retry) and an error-handling table for recovery, matching the 'clear sequence with explicit validation' anchor.	3 / 3
Progressive Disclosure	Sections are well organized, but references/implementation.md is never linked or signaled from the body and largely duplicates inline content (callback server, client SDK, ngrok testing), so detail that should live one level deep is instead repeated inline.	2 / 3
	Total	10 / 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.

A strong, third-person description with explicit 'Use when' guidance and natural trigger terms. Its only gap is specificity — it states the domain and a couple of actions rather than enumerating the concrete capabilities the skill provides.

Dimension	Reasoning	Score
Specificity	It names the domain and a couple of actions ("Implement Deepgram callback and webhook handling for async transcription") but does not list a comprehensive set of concrete actions like signature verification, job tracking, or idempotent processing, so it stops at 'names domain and some actions'.	2 / 3
Completeness	It explicitly answers both 'what' (implement callback/webhook handling for async transcription) and 'when' ("Use when implementing callback URLs, processing async transcription results, or handling Deepgram event notifications") with explicit triggers.	3 / 3
Trigger Term Quality	Trigger terms ("deepgram callback", "deepgram webhook", "async transcription", "deepgram events", "deepgram notifications", "deepgram async") are natural phrases a user would say and cover the common variations well.	3 / 3
Distinctiveness Conflict Risk	The Deepgram-specific scope and distinct webhook/callback triggers make it a clear niche unlikely to conflict with other 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: 4 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.