agentsclimarketplace

Iblai api course create

Skill iblai/api/skills/iblai-api-course-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-course-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

Programmatically generate, edit, and publish courses via the ibl.ai Course Creation API — create a task, generate an AI outline, run the full creation pipeline, then read the course outline, full structure, and draft unit content. Use to author courses from the API.

SKILL.md

3.4 KB, 871 tokens by cl100k_base, as published. Nobody here has run it

iblai-api-course-create

Generate, edit, and publish courses through the ibl.ai Course Creation API: spin up a task, let AI generate a course outline, run the full creation pipeline, then read the resulting outline, full structure, and draft unit content. Host root for every endpoint below is …/dm/api/ai-mentor/orgs/{org}/users/{username}/course-creation/.

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, {task_id} = a course-creation task's id, {course_id} = a created course's id.
  • Host root: …/dm/api/ai-mentor/orgs/{org}/users/{username}/course-creation/.
  • Not connected yet? Run /iblai-api-login first to populate IBLAI_ORG, IBLAI_USERNAME, and IBLAI_API_KEY.

Reads

Tasks

  • GET …/course-creation/tasks/ — list tasks.
  • GET …/course-creation/tasks/{task_id}/ — task detail / status (status flows Pending → Scheduled).
  • GET …/course-creation/tasks/{task_id}/start/ — start the full creation pipeline.
  • GET …/course-creation/tasks/{task_id}/cancel/ — cancel the pipeline.

Courses

  • GET …/course-creation/course/ — list courses (filter by task with ?task={task_id}).
  • GET …/course-creation/course/{course_id}/ — course detail.
  • GET …/course-creation/course/{course_id}/outline/ — outline (no component content).
  • GET …/course-creation/course/{course_id}/full-structure/ — full structure (add ?include_content=true for HTML).
  • GET …/course-creation/course/{course_id}/draft-content-for-all-units/ — draft content for all units.

Writes

Tasks

  • POST …/course-creation/tasks/ — create a task.
  • DELETE …/course-creation/tasks/{task_id}/ — delete a task. Destructive — confirm with the user first.
  • POST …/course-creation/tasks/{task_id}/create-course/ — create the course on the LMS.
  • POST …/course-creation/tasks/{task_id}/create-course-outline/ — generate the outline with AI.

Courses

  • DELETE …/course-creation/course/{course_id}/ — delete the course record. Destructive — confirm with the user first.
  • POST …/course-creation/course/{course_id}/draft-content-for-unit/ — draft content for one unit.

Example

Generate the AI outline for an existing task:

curl -X POST \
  "https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/course-creation/tasks/$TASK_ID/create-course-outline/" \
  -H "Authorization: Api-Token $IBLAI_API_KEY"

Notes

  • Typical flow: create task → generate outline (AI) → start pipeline → read full-structure/ / draft content.
  • Task status flows Pending → Scheduled; poll …/tasks/{task_id}/ to track progress, and …/tasks/{task_id}/cancel/ to stop a running pipeline.
  • full-structure/ returns the structure without HTML by default — add ?include_content=true to include rendered component content.
  • List courses for a given task with …/course/?task={task_id}.

Gives 0 of the 12 instructions most learn study skills give in 871 tokens

Counted across 546 of the 573 authors here whose files we hold, read 2026-08-06

  • produce self-contained HTML lessonsin 24 of 546, across 8 files
  • record user preferences in a notes filein 23 of 546, across 5 files
  • calculate the zone of proximal development before teachingin 23 of 546, across 6 files
  • maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
  • make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
  • create reusable components for lessonsin 19 of 546, across 5 files
  • create compressed reference documents for quick lookupin 19 of 546, across 3 files
  • find high-quality resources before writing lessonsin 18 of 546, across 4 files
  • update the mission file and records upon mission changesin 16 of 546, across 2 files
  • set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
  • populate the mission file before teachingin 15 of 546, across 1 file
  • include interactive feedback loops in lessonsin 15 of 546, across 1 file

Said here and by no other author read

  • include an authorization header on every request
  • run login first if credentials are missing
  • create a task before generating an outline
  • generate the course outline using ai
  • start the creation pipeline after generating the outline
  • poll task status to track progress

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.