mcpbeat

Tutorial Selfloop

willoscar/tutorial-selfloop

| Run a tutorial-specific quality gate and write a PASS/FAIL report for the final tutorial deliverable.

987 tokens
context cost
the whole folder, loaded on every use
2
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
496
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill tutorial-selfloop

What comes with it

2 397 bytes besides the instruction
scripts/run.py

The instruction itself

8 sections, as written by the author

Tutorial Self-Loop

Goal: converge the tutorial deliverable to a stable teaching-quality bar.

The gate should compare output/TUTORIAL.md against the intended module shape from outline/module_plan.yml, rather than acting like a generic prose checker.

Inputs

  • output/TUTORIAL.md
  • outline/module_plan.yml

Outputs

  • output/TUTORIAL_SELFLOOP_TODO.md

Checks

  • reader orientation section exists
  • at least one real module exists
  • each module has teaching components, not just a block of prose
  • source notes are visible but lightweight

Script

Quick Start

  • uv run python .codex/skills/tutorial-selfloop/scripts/run.py --workspace <workspace>

All Options

  • --workspace <dir> (required)
  • --unit-id <U###>
  • --inputs <semicolon-separated>
  • --outputs <semicolon-separated>
  • --checkpoint <C#>

Examples

  • Run the tutorial gate:
  • uv run python .codex/skills/tutorial-selfloop/scripts/run.py --workspace <workspace>

How to use it

Copy the folder

Take willoscar/tutorial-selfloop from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.