---
title: "What has been learned that helps with a task"
method: GET
path: "/v1/skills"
---

# What has been learned that helps with a task

`GET /v1/skills`

## Request

- Base URL: `https://api.doubleoh.ai`
- URL: `https://api.doubleoh.ai/v1/skills`
- Auth: one of:
  - API key in header `x-api-key`
  - HTTP bearer

Call BEFORE your agent attempts something it has failed at before. Put a returned skill's `instructions` in the agent's context.

## Query parameters

- `task` string, required
- `url` string

## Response `200`

Your learned skills that match, best first.

- object
  - `skills` object[]
    - `systemHint` string: The skill as one block of context for a model: boundary first, then the steps, then how to report. Paste it verbatim.
    - `authority` object, nullable
      - `requiresHuman` string[]
      - `never` string[]
    - `name` string
    - `description` string
    - `instructions` string: The steps, as prose. Put this in your agent's context.
    - `timesWorked` integer: Raw counts, not a rate: 5 for 5 is worth following, 1 for 1 is a guess that worked once.
    - `timesFailed` integer

---

[API](https://skmtc.dev/doubleoh/apis/doubleoh-api.md) · [All operations](https://skmtc.dev/doubleoh/apis/doubleoh-api/llms.txt) · [OpenAPI document](https://skmtc.dev/doubleoh/apis/doubleoh-api/revisions/398fb6ef5068?raw)