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.
95
92%
Does it follow best practices?
Impact
100%
2.04xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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 an excellent skill description that follows best practices. It uses third person voice, provides specific capabilities, includes a clear 'Use when...' clause, and lists concrete event types that serve as natural trigger terms. The description is concise yet comprehensive, making it easy for Claude to select this skill when appropriate.
| 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 types. | 3 / 3 |
Completeness | Clearly answers both what ('Receive and verify OpenAI webhooks') AND when ('Use when setting up OpenAI webhook handlers for...') with explicit triggers and specific event types. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'OpenAI webhooks', 'webhook handlers', 'fine-tuning jobs', 'batch completions', and specific event names like 'fine_tuning.job.completed', 'batch.completed', 'realtime.call.incoming'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche - specifically targets OpenAI webhooks with named event types, unlikely to conflict with generic webhook skills or other API integrations. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with complete, executable webhook handler implementations for multiple frameworks. The verification logic is thorough with proper security considerations (timing-safe comparison, timestamp validation). Minor verbosity in the related skills section and some redundancy between language implementations slightly reduce token efficiency.
Suggestions
Consider consolidating the related skills section to just 2-3 most relevant links, or move to a separate reference file
The Express and FastAPI examples share identical verification logic explanations - consider a brief 'verification algorithm' section referenced by both instead of inline comments in each
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill provides useful code but includes some redundancy - both Express and FastAPI implementations are nearly identical in structure, and the extensive related skills list at the bottom adds bulk without essential value. The code comments are helpful but some explanatory text could be trimmed. | 2 / 3 |
Actionability | Excellent executable code examples for both Express and FastAPI with complete signature verification implementations. The code is copy-paste ready with proper imports, error handling, and event type switching. Environment variables and local development commands are concrete and specific. | 3 / 3 |
Workflow Clarity | The verification flow is explicit with clear validation steps: check signature format, validate timestamp within 5 minutes, extract version, create signed content, compare signatures. The code includes proper error handling and the handler sequence (verify -> parse -> handle) is clear. | 3 / 3 |
Progressive Disclosure | Well-structured with quick reference code upfront, then links to detailed examples in separate directories (examples/express/, examples/nextjs/, examples/fastapi/). Reference materials are clearly signaled with one-level-deep links. The event types table provides quick lookup without overwhelming detail. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%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.
f8a4801
Table of Contents
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.