outpost
Sets up and configures Hookdeck Outpost for outbound event delivery to customer endpoints. Use when sending webhooks to customers, building webhook delivery infrastructure, managing tenants and destinations with supported types (webhooks, Hookdeck Event Gateway, AWS SQS/Kinesis/S3, Azure Service Bus, GCP Pub/Sub, RabbitMQ, Kafka), or aligning topics and publishes. EventBridge support is tracked in GitHub issues.
70
85%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Failed to scan
The risk profile of this skill
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 a strong skill description that clearly identifies the tool (Hookdeck Outpost), lists specific capabilities and supported integrations, and includes an explicit 'Use when' clause with natural trigger terms. The description is comprehensive yet focused, making it easy for Claude to select this skill when appropriate. The only minor note is the somewhat tangential mention of EventBridge support being tracked in GitHub issues, which is more of a limitation note than a capability description.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple specific concrete actions: setting up Hookdeck Outpost, configuring outbound event delivery, managing tenants and destinations, aligning topics and publishes. It also enumerates specific supported destination types (webhooks, AWS SQS/Kinesis/S3, Azure Service Bus, GCP Pub/Sub, RabbitMQ, Kafka). | 3 / 3 |
Completeness | Clearly answers both 'what' (sets up and configures Hookdeck Outpost for outbound event delivery, manages tenants and destinations) and 'when' (explicit 'Use when' clause covering sending webhooks to customers, building webhook delivery infrastructure, managing tenants and destinations with specific types). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'webhooks', 'webhook delivery', 'sending webhooks to customers', 'tenants', 'destinations', plus specific service names like 'AWS SQS', 'Kafka', 'RabbitMQ', 'GCP Pub/Sub', 'Hookdeck Outpost', 'Event Gateway'. These are terms a developer would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Hookdeck Outpost for outbound webhook delivery. The specific product name, the enumeration of supported destination types, and the focus on outbound event delivery make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured navigation and workflow skill that excels at progressive disclosure and agent workflow clarity, directing Claude through a clear decision tree from simplest to most complex paths. Its main weakness is that it contains no executable code or concrete commands—it's entirely a routing layer to external documentation and reference files. The conciseness is good but not optimal, with some redundancy across sections.
Suggestions
Add at least one minimal executable example (e.g., a curl command to publish an event or create a tenant) so the skill provides immediate actionability without requiring external fetches.
Consolidate the 'Supported destination types' and 'Deployment and API pointers' sections into the documentation index to reduce redundancy and tighten the file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and avoids explaining basic concepts Claude would know, but there's some redundancy—destination types are listed in the description, the supported destinations section, and linked docs. Some sections like 'Test webhook destination URLs' and 'Future skills' add marginal value. The file could be tightened by ~20%. | 2 / 3 |
Actionability | The skill provides clear links and a structured agent workflow path, but contains no executable code, commands, or concrete examples. Everything is delegated to external docs and reference files. An agent following this skill must fetch external resources before it can do anything concrete. | 2 / 3 |
Workflow Clarity | The 'Fast path for agents' section provides a clear 5-step sequence with decision points (scope ambiguous → default to smallest), escalation logic (open full-stack only when clearly needed), and a verification step via outpost-verify.md. The scope/verify references act as validation checkpoints. | 3 / 3 |
Progressive Disclosure | Excellent layered structure: quick overview → documentation index → quickstarts → agent fast path → scope/verify references → full-stack examples (gated with 'use only when'). References are one level deep and clearly signaled with descriptive labels. Navigation between sections is intuitive. | 3 / 3 |
Total | 10 / 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.
- Repository
- hookdeck/agent-skills
- Commit
efe0b2d
- 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.