Volnyn API
Wires the account to other systems with webhooks, schedules and automations.
Engineering · produces a Automation · built in, ready to run
What you give it
Whatever the job is about — a block of text, a URL, a name. It arrives below the instructions, fenced and labelled as data, so nothing inside it can rewrite the procedure.
Tools it uses
Restricted to these, and nothing else:
webhook_postwebhook_list_targetswebhook_add_targetcreate_automationcreate_scheduled_tasklist_integrations
Fewer tools means fewer ways to do the job, which is what makes the result the same next week. If one of these needs an app you have not connected, the skill says so rather than failing quietly.
What it reads
This skill carries material of its own. None of it is loaded up front — the assistant opens a file when the job calls for it, and leaves the rest alone.
| File | What it holds |
|---|---|
docs/agents.md |
Agents |
docs/automations.md |
Automations and runs |
docs/brain.md |
Brain — the account's own knowledge |
docs/conventions.md |
Conventions — envelopes, errors, polling |
docs/sessions.md |
Sessions — a conversation over HTTP |
docs/skills.md |
Skills |
docs/workflows.md |
Workflows |
The procedure it follows
This is the skill, in full. Add it to your own skills to change any of it.
Everything is under /api/v1 on this host, authenticated with a personal key sent as "Authorization: Bearer vln_…" or an X-Api-Key header, rate-limited to 60 requests per key per minute. Confirm the key with GET /api/v1/whoami before anything else. A one-shot job is POST /agents/{id}/run; anything the user replies to is a session. Runs are asynchronous — poll the run endpoint with a backoff rather than holding the request open, and never retry a 4xx. Every run spends the owner's credits. Never invent an endpoint, and never put a key in a URL or an example.
How to run it
| Where | How |
|---|---|
| Chat | "Run my Volnyn API skill", or pick it from the + menu |
| Skills page | Find Volnyn API under Library and press Add & Use |
| Automations | Invoke it on every trigger |
| API | POST /v1/skills/{id}/run — add it to your own skills first, then take the id from GET /v1/skills |
In chat, on the Skills page and in automations you do not have to add it first — a library skill runs as it is. Adding it makes an editable copy under your own skills, which is what you need to change the wording, and what the API works against.
New to skills? Start with what a skill is.