Comprehensive guide to the Hookdeck Event Gateway for receiving, routing, and delivering webhooks and events. Covers setup, connections, authentication, local development, monitoring, and API automation. Use when receiving webhooks, setting up webhook endpoints, testing webhooks locally, configuring webhook relay or event queue, event routing, webhook retry, webhook monitoring, third-party routing, asynchronous APIs, or local webhook development. For provider webhooks (Stripe, Shopify, Chargebee, GitHub, etc.), use together with the matching skill from hookdeck/webhook-skills; do not only parse JSON — use provider SDK verification and event construction (e.g. Stripe constructEvent).
63
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/event-gateway/SKILL.mdQuality
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 a strong, well-crafted skill description that covers specific capabilities, includes an explicit and comprehensive 'Use when...' clause with many natural trigger terms, and clearly distinguishes itself from related provider-specific webhook skills. The cross-referencing guidance for provider webhooks is a particularly thoughtful addition that reduces ambiguity in multi-skill environments.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: receiving, routing, delivering webhooks; covers setup, connections, authentication, local development, monitoring, and API automation. Also mentions provider SDK verification and event construction. | 3 / 3 |
Completeness | Clearly answers both 'what' (comprehensive guide to Hookdeck Event Gateway for receiving, routing, and delivering webhooks) and 'when' (explicit 'Use when...' clause with extensive trigger scenarios). Also includes guidance on when to combine with other skills. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'webhooks', 'webhook endpoints', 'testing webhooks locally', 'webhook relay', 'event queue', 'event routing', 'webhook retry', 'webhook monitoring', 'local webhook development', plus specific provider names like Stripe, Shopify, GitHub. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Hookdeck Event Gateway and webhook/event management, which is a distinct niche. Explicitly delineates boundaries with provider-specific webhook skills, reducing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill demonstrates strong workflow clarity with well-sequenced stages and validation checkpoints, and has a thoughtful reference architecture. However, it suffers significantly from verbosity and redundancy—the provider webhooks guidance is repeated 3+ times, the CLI/API/Dashboard decision tree is overly detailed for inline content, and context verification instructions appear twice. The skill would benefit greatly from moving detailed decision frameworks to reference files and eliminating repeated content.
Suggestions
Move the entire 'How agents choose: CLI, API, or Dashboard' section to a reference file (e.g., references/cli-api-dashboard-guide.md) and replace with a 2-line summary and link—this section alone is ~40 lines of guidance Claude can largely infer.
Consolidate the provider webhooks guidance into a single concise section instead of repeating it in 'Provider webhooks: use two skills together', 'Signature Verification', and 'Workflow Stages'—currently the same install command and verification pattern appears 3 times.
Remove the duplicate context verification instructions—the same whoami/confirm flow appears both in the 'Workflow Stages' blockquote and the dedicated 'Context verification' section.
Trim explanatory prose that restates what the referenced files already cover (e.g., the Production paragraph could be reduced to a few bullet points with a link to the receive-webhooks quickstart).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~200+ lines with significant redundancy. The provider webhooks section repeats the same guidance (try installing, use provider SDK, verify Hookdeck first) at least 3 times across different sections. The CLI vs API vs Dashboard decision tree is excessively detailed for a skill file, explaining concepts Claude already understands (what CI is, what credentials are). The context verification instructions are repeated twice verbatim. | 1 / 3 |
Actionability | The quick start section provides concrete, executable commands (`hookdeck listen 3000 <source_name> --path /webhooks`), and there are specific CLI commands throughout. However, most actionable content is deferred to reference files rather than provided inline, and much of the body is procedural guidance and decision frameworks rather than executable instructions. The actual verification code and handler patterns are all in referenced files. | 2 / 3 |
Workflow Clarity | The workflow stages (01-setup through 04-iterate) are clearly sequenced with explicit ordering. The context verification workflow has clear validation steps (run whoami, show output, confirm with user, switch if wrong, re-verify). The provider webhooks checklist is a prerequisite gate before scaffolding. The production deployment section includes a checklist of configuration steps (rate limiting, retries, notifications). | 3 / 3 |
Progressive Disclosure | The skill uses extensive references to supporting files (references/verification-code.md, references/cli-workflows.md, etc.) with clear tables organizing when to use each. However, too much content that should be in reference files is inlined (the entire CLI vs API vs Dashboard decision framework, repeated provider webhook guidance), making the main SKILL.md bloated. The reference structure itself is well-organized but the body doesn't stay at overview level. | 2 / 3 |
Total | 8 / 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.
efe0b2d
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.