Agent Skills
Install the open-source Webhook Relay Agent Skills so Claude and other agents can forward, transform, debug, tunnel and schedule webhooks with the CLI.
Overview
Agent Skills are small, self-contained instruction packs that teach Claude (and other skill-aware agents) how to perform a specific task. Webhook Relay publishes an open-source set of Skills that show agents how to drive the platform with the relay CLI and API — forwarding webhooks, transforming them, debugging incoming requests, exposing services over tunnels, scheduling recurring webhooks, and receiving, parsing and transforming inbound email.
The Skills are maintained on GitHub:
Use that repository to browse the source, open issues, or contribute new skills.
Quick start
Install every skill with the skills.sh CLI:
npx skills add webhookrelay/skills
That drops the skills into your agent's skills directory. From then on you can ask your agent in plain language — it picks the right skill and runs the relay commands for you:
| Ask your agent | Skill it uses |
|---|---|
| "Test this webhook through the real pipeline, wait for delivery and debug the transform logs" | agentic-webhook-testing |
| "Give me a webhook URL to test my Stripe integration" | webhook-debug |
| "Forward my GitHub webhooks to localhost:3000" | webhook-forwarding-internal |
| "Relay this webhook to Slack without running anything locally" | webhook-forwarding-public |
| "Reshape this payload into a Slack message before delivering it" | webhook-transformations |
| "Expose my local dev server on a public HTTPS URL" | relay-tunnels |
| "Send a health-check webhook every 5 minutes" | recurring-webhooks |
| "Give me a throwaway email address and read what it receives" | temporary-email |
| "Turn incoming emails into JSON and POST them to my API" | transform-email-to-api-call |
See all the ways to install — single skill, Claude Code plugin, ClawHub, or manual — below.
Skills vs. MCP
Skills and the MCP server solve related but different problems, and they work well together:
- Skills are instructions. They teach an agent how to use the
relayCLI/API correctly — the right commands, payload shapes, and workflows. They run wherever your agent has a shell. - MCP is a live connection. It gives an agent typed tools to manage buckets, inspect webhook logs, and work with transform functions directly against your account.
Install the Skills for guided, command-line workflows; connect MCP when you want the agent to call Webhook Relay tools directly.
Available skills
| Skill | What it does |
|---|---|
agentic-webhook-testing | Test and debug a webhook integration through the real pipeline with MCP: send a representative request, wait for delivery, inspect the forwarded request and destination response, follow function execution IDs into persisted console logs, fix and retest, and replay existing events only when authorized. |
webhook-debug | Capture and inspect webhooks with a free, no-signup bin at bin.webhookrelay.com — a public URL that records any HTTP request so you can see the exact method, headers, query and body a provider sends, stream requests live, mock the response, and verify HMAC signatures. No CLI or account required. |
webhook-forwarding-internal | Receive webhooks from providers (Stripe, GitHub, Shopify, CI, etc.) and forward them to a destination with no public IP — localhost, a private LAN host, or a Kubernetes service. The relay agent performs the final hop, so no inbound firewall ports are needed. Best for local development. |
webhook-forwarding-public | Forward webhooks server-side from a public Webhook Relay endpoint to another internet-reachable URL — no local agent required. Relay between cloud services, put a stable URL in front of an API, fan one webhook out to many destinations, or transform payloads in transit. |
webhook-transformations | Write, test, and attach JavaScript (or Lua) functions that modify webhooks in flight — reshape the JSON body, rename fields, add/remove headers, change the method or path, set the response, drop requests conditionally, or call other HTTP APIs. |
relay-tunnels | Expose a local or internal HTTP/TCP service on a stable public hostname (an ngrok-style reverse proxy) without opening firewall ports — share a dev server, demo a local app, expose an internal API, or tunnel TCP (SSH, databases). |
recurring-webhooks | Schedule cron-driven webhooks that fire automatically — send a recurring HTTP request (method, body, headers) to one or more destinations on an interval or at specific times. Use for health checks, heartbeats, scheduled reports, or triggering a function on a timer. |
temporary-email | Create a disposable / temporary inbound email address from the terminal and read the mail it receives as JSON — no mailbox, SMTP server, or per-address signup. Grab a throwaway inbox for a signup / OTP / confirmation link, receive one-off mail in a script, or watch an address for incoming messages. |
email-parsing-api | Turn inbound email into structured JSON — create an inbound address and every message is parsed into a stable payload (from, to/cc, subject, text, html, headers, spf/dkim/dmarc, attachments), delivered to your endpoint or pulled from the events API. An "email → JSON" API with no SMTP/IMAP server. |
transform-email-to-api-call | Turn inbound emails into calls to your own API — a bucket with an email address, a public output pointing at your API, and a JavaScript function that reshapes the parsed email into the exact request your endpoint expects. Email-driven automation, e.g. create a ticket/lead/record from an email. |
Installation
The fastest way to install is with the skills.sh CLI:
npx skills add webhookrelay/skills
Add -g to install globally for all your agents:
npx skills add webhookrelay/skills -g
Install a single skill
Pass --skill <name> to install just one:
npx skills add webhookrelay/skills --skill webhook-debug
Claude Code plugin marketplace
The repository doubles as a Claude Code plugin marketplace. Add it, then install the plugin:
/plugin marketplace add webhookrelay/skills
/plugin install webhookrelay-skills
ClawHub
The skills are also published on ClawHub, the open registry for AI agent skills. Install the bundled Webhook Relay skill with the openclaw CLI:
openclaw skills install webhook-relay
See Webhook Relay on ClawHub for what the registry does and how the skill fits.
Manual install
You can also copy any skills/<name>/ folder from the repository into your agent's skills directory.
Prerequisites
The webhook-debug skill works against the public bin API with nothing but curl — no account or key needed. agentic-webhook-testing prefers a connected Webhook Relay MCP server so the agent can use the typed send, wait, delivery-log and function-log tools.
For CLI fallback and skills that operate a local runtime, install and authenticate the relay CLI:
- Install it — see CLI installation.
- Log in:
relay login(or set theRELAY_KEY/RELAY_SECRETenvironment variables). - Verify:
relay bucket ls.
Concepts at a glance
- Bucket — groups inputs and outputs.
- Input — a public HTTPS endpoint that receives webhooks.
- Output — a destination requests are relayed to;
internal(delivered by a running agent, e.g. localhost) orpublic(delivered server-side). - Function — server-side JavaScript/Lua that transforms requests/responses.
- Tunnel — a public hostname that proxies inbound HTTP/TCP to a local or internal service.
- Cron — a scheduled, recurring webhook.
See Getting Started for the full model.
Issues and contributions
The Skills are open source. To report a problem, request a new skill, or read the code, use the GitHub repository:
- github.com/webhookrelay/skills — browse the code and open an issue.
Links
- Webhook Relay Skills on GitHub
- skills.sh CLI — what it is and how to install with it
- Webhook Relay on ClawHub
- MCP server
- Functions reference
- CLI installation
- Dashboard
- LLM-friendly docs index — append
.mdto any docs URL for plain markdown, or see llms.txt