deepgram-webhooks

Receive and verify Deepgram webhooks (callbacks). Use when setting up Deepgram webhook handlers, processing transcription callbacks, or handling asynchronous transcription results.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

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

A largely actionable, well-organized skill body with concrete executable examples and sensible reference splitting. The main gaps are a redundant dg-token example, a broken 'examples/' reference, and workflow guidance expressed through code rather than explicit sequenced steps.

Suggestions

Remove the duplicate dg-token verification block (keep it in one place, e.g. the Authentication Methods section) to tighten conciseness.

Fix or remove the 'examples/' reference on line 156, since that directory does not exist in the bundle — either add the directory or drop the line.

Add a short explicit numbered workflow (set up endpoint → verify dg-token → parse payload → process → respond 200-299) so the validated sequence is called out as steps rather than only implied by the code.

Dimension	Reasoning	Score
Conciseness	The body is code-forward and mostly tight, but the dg-token verification logic appears twice (basic handler and Authentication Methods) and the opening paragraph restates callback mechanics, placing it just above the 'mostly efficient' anchor rather than fully lean.	4 / 5
Actionability	It provides copy-paste-ready executable code (Express handler, auth middleware), a complete curl request, concrete environment variables, and a runnable Hookdeck CLI command covering the common cases.	5 / 5
Workflow Clarity	The handler code embeds a clear validated sequence — check dg-token (401/403 on failure) → parse → process → return 200 — and operational notes (retry up to 10 times, allowed ports) supply checkpoints, though the flow is shown in code rather than as an explicitly numbered sequence.	4 / 5
Progressive Disclosure	References to overview.md, setup.md, and verification.md are well-signaled, one level deep, and the files exist; however the 'examples/' link (line 156) points to a directory that does not exist, a minor organization gap that keeps it below the top anchor.	4 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

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, well-structured description that concisely states what the skill does and gives explicit, concrete 'Use when' triggers tied to a specific provider niche. Trigger coverage and action specificity are solid, with only minor room for additional synonyms.

Dimension	Reasoning	Score
Specificity	The description names the Deepgram webhook domain and lists several concrete actions — 'Receive and verify Deepgram webhooks', 'setting up Deepgram webhook handlers', 'processing transcription callbacks', 'handling asynchronous transcription results' — with only minor breadth gaps, matching the 'several specific actions' anchor rather than the fully comprehensive anchor 5.	4 / 5
Completeness	It explicitly answers both 'what' ('Receive and verify Deepgram webhooks (callbacks)') and 'when' ('Use when setting up Deepgram webhook handlers, processing transcription callbacks, or handling asynchronous transcription results') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	It includes natural terms a user would say — 'Deepgram webhooks', '(callbacks)', 'webhook handlers', 'transcription callbacks', 'asynchronous transcription results' — giving good keyword coverage with the synonym 'callbacks', though a few natural variants (e.g. 'speech-to-text', 'transcription') are absent.	4 / 5
Distinctiveness Conflict Risk	The Deepgram-specific niche with provider-scoped triggers ('Deepgram webhooks', 'transcription callbacks') makes it clearly distinguishable from other webhook skills with minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: hookdeck/webhook-skills
Path: skills/deepgram-webhooks/SKILL.md
Commit: daaf3db

Reviewed: 3 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.