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".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with excellent trigger term coverage and completeness, clearly specifying both what the skill does and when to use it. Its main weakness is that the capability description could be more specific about the concrete actions performed (e.g., parsing payloads, setting up endpoints, verifying webhook signatures) rather than using general terms like 'implement' and 'handling'.
Suggestions
Add more specific concrete actions such as 'parse webhook payloads', 'set up callback endpoints', 'verify webhook signatures', or 'handle transcription completion events' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Deepgram callback/webhook handling) and mentions async transcription, but doesn't list multiple concrete actions beyond 'implement' and 'handle'. It could specify actions like 'parse webhook payloads', 'verify signatures', 'set up callback endpoints', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (implement Deepgram callback and webhook handling for async transcription) and 'when' (explicit 'Use when' clause with trigger scenarios, plus an explicit 'Trigger:' list). | 3 / 3 |
Trigger Term Quality | Includes a comprehensive set of natural trigger terms: 'deepgram callback', 'deepgram webhook', 'async transcription', 'deepgram events', 'deepgram notifications', 'deepgram async'. These cover the variations a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Deepgram's callback/webhook/async transcription niche. The combination of 'Deepgram' + 'callback/webhook' + 'async transcription' creates a very distinct trigger profile unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable skill with excellent executable code examples and a clear multi-step workflow for implementing Deepgram async transcription callbacks. Its main weakness is length — the inline Redis tracker, full client SDK, and idempotency patterns make it quite long when some of these could be split into separate reference files. The error handling table and callback flow diagram are strong additions.
Suggestions
Move Steps 3-4 (Redis job tracking and Client SDK) into a separate reference file (e.g., ADVANCED_PATTERNS.md) and link to it from the main skill to improve progressive disclosure and reduce token usage.
Trim Step 6 (idempotent processing) to just the Redis-based production pattern rather than showing both in-memory Set and Redis approaches.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes more code than necessary — the Redis job tracker, client SDK with poll/wait, and idempotent processing sections add significant length. Some of this could be referenced rather than inlined. However, it doesn't waste tokens explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript/bash with real imports, proper error handling, and copy-paste ready patterns. The curl examples, ngrok setup, and SDK usage examples are concrete and specific. | 3 / 3 |
Workflow Clarity | The 6-step sequence is clearly ordered from submission through callback handling, job tracking, client SDK, local testing, and idempotency. The callback flow diagram at the top establishes the mental model. Validation is present via signature verification, error handling table, and explicit retry behavior documentation. | 3 / 3 |
Progressive Disclosure | All content is inlined in a single file — the Redis tracker, client SDK, and idempotent processing sections could be split into referenced files. The Resources section links to external docs, but the skill itself is monolithic at ~200+ lines of code. The structure with numbered steps helps, but the volume of inline code hurts discoverability. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
70e9fa4
- 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.