Iblai api agent create

Skill iblai/api/skills/iblai-api-agent-create

Agent skills + a chat MCP server to operate the ibl.ai platform via its REST API. Install: npx skills add iblai/api

Install

npx -y skills add iblai/api --skill iblai-api-agent-create

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

15 stars15 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Create a new ibl.ai agent from a template via the platform API — set name, display name, description, system prompt, and LLM provider; returns the new agent's unique id. Use when creating an agent from scratch, then configure it with the other /iblai-api-agent-* skills.

SKILL.md

3.8 KB, as published. Nobody here has run it

iblai-api-agent-create

Create a brand-new agent from a template. This is the step before configuring an agent: it mints a new agent and returns its unique_id, which you then hand to the /iblai-api-agent-* skills (settings, llm, prompts, datasets, …) to configure further. To duplicate an existing agent instead of starting from a template, use /iblai-api-agent-setting (fork).

Auth & conventions

Base URL: https://api.iblai.app
Header: Authorization: Api-Token $IBLAI_API_KEY on every request.
Path vars: {org} = $IBLAI_ORG, {username} = $IBLAI_USERNAME.
Not connected yet? Run /iblai-api-login first to populate IBLAI_ORG, IBLAI_USERNAME, and IBLAI_API_KEY.

Reads

GET https://api.iblai.app/dm/api/search/orgs/{org}/users/{username}/mentors/ — list existing agents in the org (useful to pick a fork source or confirm names are free).
GET https://api.iblai.app/dm/api/ai-mentor/orgs/{org}/users/{username}/mentor/categories/ — category options (to assign after creation via /iblai-api-agent-setting).

Writes

POST https://api.iblai.app/dm/api/ai-mentor/orgs/{org}/users/{username}/mentor-with-settings/ — create a new agent from a template (returns the created agent with its unique_id):

{
  "template_name": "string (required, e.g. ai-mentor)",
  "new_mentor_name": "string (required)",
  "display_name": "string",
  "description": "string",
  "system_prompt": "string",
  "llm_provider": "string"
}

Example

Create a data-science agent from the default ai-mentor template, then capture its unique_id for follow-up configuration:

curl -X POST \
  "https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/mentor-with-settings/" \
  -H "Authorization: Api-Token $IBLAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "template_name": "ai-mentor",
    "new_mentor_name": "Data Science Tutor",
    "description": "Helps users with statistics and Python."
  }'
# → response includes "unique_id"; use it as {mentor} in the other skills

Notes

template_name defaults to ai-mentor on most orgs; the create call accepts any template the org exposes.
Creation is intentionally minimal — set only name + a couple of fields here, then drive the rest with the focused skills: /iblai-api-agent-setting, /iblai-api-agent-llm, /iblai-api-agent-prompt, /iblai-api-agent-dataset, /iblai-api-agent-tool, etc., using the returned unique_id as {mentor}.
To copy an existing agent rather than start from a template, use the fork endpoint in /iblai-api-agent-setting.
End-to-end example: the iblai/quickstarts Python client wraps these calls — create an agent, open a session, and chat with it from a script (see also /iblai-api-agent-session for the chat transport).

Reference material

Doc-sourced material preserved from the developer docs:

references/quickstart.md — the iblai/quickstarts Python client outlined: env vars and the create-agent → open-session → chat-over-WebSocket flow, with the runnable client (quickstart.py + api.py) preserved in assets/.
references/agent-file-format.md — the .iblai Markdown agent-file format (iblai/standard pointer).