openai-webhooks

Receive and verify OpenAI webhooks. Use when setting up OpenAI webhook handlers for fine-tuning jobs, batch completions, or async events like fine_tuning.job.completed, batch.completed, or realtime.call.incoming.

Quality

82%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

64%

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

This skill provides highly actionable, executable webhook handler code for OpenAI in two languages with proper security practices (timing-safe comparison, replay attack prevention, raw body parsing). Its main weaknesses are verbosity—two full implementations inline plus duplicated event information and a long related skills list—and a lack of an explicit end-to-end setup workflow with verification checkpoints.

Suggestions

Add an explicit numbered setup workflow: register webhook in OpenAI dashboard → set environment variables → start server → test with local tunnel → verify signature works, with a checkpoint to confirm events are received.

Move one of the two full implementations (Express or FastAPI) to a referenced example file to reduce inline token usage, keeping only the primary implementation and a brief pointer to the alternative.

Trim the 'Related Skills' section to 2-3 most relevant skills or move it to a separate references file to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The core code examples are useful but the skill is quite long. The extensive 'Related Skills' section listing 10 other skills and the 'Recommended' section with external GitHub links add significant token overhead. The switch statement with many similar cases could be condensed. The event types table partially duplicates what's already in the switch statement.	2 / 3
Actionability	Provides fully executable, copy-paste ready code in both JavaScript (Express) and Python (FastAPI) with complete signature verification implementations, proper header extraction, timing-safe comparison, and event handling. Environment variables and local development commands are concrete and specific.	3 / 3
Workflow Clarity	The code itself follows a clear verify-then-parse-then-handle sequence, and includes timestamp validation and replay attack prevention. However, there's no explicit step-by-step setup workflow (e.g., 1. Register webhook in dashboard, 2. Set env vars, 3. Start server, 4. Test with tunnel). The local development section is a single command with no verification step to confirm the webhook is working.	2 / 3
Progressive Disclosure	References to examples/ directories and references/ files are well-signaled, but no bundle files were provided, so we can't verify they exist. The main SKILL.md inlines two complete implementations (~150 lines of code) that could arguably be in separate example files, with just the verification function or a shorter snippet in the overview. The 'Related Skills' and 'Recommended' sections add bulk that could be in a separate file.	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.

This is a strong skill description that clearly communicates its purpose, provides explicit trigger guidance with a 'Use when...' clause, and includes highly specific event names that serve as excellent trigger terms. The description is concise, uses third person voice correctly, and carves out a distinct niche that would be easy for Claude to match against user requests.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Receive and verify OpenAI webhooks' and names specific use cases like 'fine-tuning jobs, batch completions, async events' with concrete event names like 'fine_tuning.job.completed', 'batch.completed', 'realtime.call.incoming'.	3 / 3
Completeness	Clearly answers both what ('Receive and verify OpenAI webhooks') and when ('Use when setting up OpenAI webhook handlers for fine-tuning jobs, batch completions, or async events...') with explicit trigger guidance and specific event examples.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'OpenAI webhooks', 'webhook handlers', 'fine-tuning jobs', 'batch completions', 'async events', plus specific event names like 'fine_tuning.job.completed', 'batch.completed', 'realtime.call.incoming' that users might reference directly.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — the combination of 'OpenAI' + 'webhooks' + specific event types like 'fine_tuning.job.completed' creates a very clear niche that is unlikely to conflict with other skills. The specificity to OpenAI's webhook API differentiates it from general webhook or general OpenAI skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: hookdeck/webhook-skills
Commit: da37fc7

Reviewed: 18 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.