How do I install the The Loop skill?

Run npx skillmds@latest add oxbshw/the-loop in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is The Loop safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with The Loop?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is The Loop free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published The Loop?

oxbshw (@oxbshw) published this skill. Their other Agent Skills are listed on their SkillMD profile.

The Loop by oxbshw — Agent Skill

Name: The Loop
Author: oxbshw

The Loop

The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does the animation glitch". Use this to record the running thing, critique the recording against plain-language pass criteria, and iterate until it passes with before/after proof.

oxbshw df1e9b0 2.4 KB Updated Sep 17, 2026

File contents

THE LOOP

A screenshot shows a moment; it cannot show a flow. THE LOOP records the actual running target, watches the recording, and judges it against pass criteria you state in plain language. The loop only observes — YOU apply the fixes, then iterate. On pass it renders a before/after MP4 + GIF as proof.

UI / web page / desktop window

watch-skill loop start "<url | screen: | window:<title> | file>" "<pass criteria>" [--script '<json steps>']
# ...apply the suggested fixes to the code...
watch-skill loop iterate <loop_id>

Pass criteria are ordinary sentences: "the checkout completes, no error toast ever appears, the total is never NaN". Negative claims ("never X") and exemplars ("a real price (like $29.00)") are both understood and enforced deterministically.
--script replays the same clicks/fills every iteration, so the comparison is honest.
Only call iterate after you actually changed something. It diffs against the previous iteration: fixed / unchanged / new.

Generated video (Manim, Remotion, ffmpeg, AI-gen)

watch-skill loop video-gen "<what the video must show>" "<render command>" --output <file>

Re-runs the generator each iteration and judges the fresh render against the spec.

Game / simulation

watch-skill loop game "<canvas-url | window:<title> | screen:>" "<pass criteria>" [--run "<launch cmd>"]

Catches the failures screenshots miss: a NaN score counter, black flicker frames, sprites that vanish mid-motion.

Watch for a condition (monitoring)

watch-skill loop monitor "<folder | url | screen: | window:<title>>" "<condition>" [--interval 10] [--max-checks 10]

Bounded — it always terminates. Events land in events.jsonl under the loop directory as structured records.

Record without judging

watch-skill capture "<target>" [--duration 10]

Capture alone never critiques; it just records, analyzes, and indexes. Use loop start when there are pass criteria.

---name: the-loopdescription: The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does the animation glitch". Use this to record the running thing, critique the recording against plain-language pass criteria, and iterate until it passes with before/after proof.license: MIT---# THE LOOPA screenshot shows a moment; it cannot show a flow. THE LOOP records theactual running target, watches the recording, and judges it against passcriteria you state in plain language. The loop only observes — YOU applythe fixes, then iterate. On pass it renders a before/after MP4 + GIF asproof.## UI / web page / desktop window```bashwatch-skill loop start "<url | screen: | window:<title> | file>" "<pass criteria>" [--script '<json steps>']# ...apply the suggested fixes to the code...watch-skill loop iterate <loop_id>```- Pass criteria are ordinary sentences: "the checkout completes, no error toast ever appears, the total is never NaN". Negative claims ("never X") and exemplars ("a real price (like $29.00)") are both understood and enforced deterministically.- `--script` replays the same clicks/fills every iteration, so the comparison is honest.- Only call `iterate` after you actually changed something. It diffs against the previous iteration: fixed / unchanged / new.## Generated video (Manim, Remotion, ffmpeg, AI-gen)```bashwatch-skill loop video-gen "<what the video must show>" "<render command>" --output <file>```Re-runs the generator each iteration and judges the fresh render againstthe spec.## Game / simulation```bashwatch-skill loop game "<canvas-url | window:<title> | screen:>" "<pass criteria>" [--run "<launch cmd>"]```Catches the failures screenshots miss: a NaN score counter, blackflicker frames, sprites that vanish mid-motion.## Watch for a condition (monitoring)```bashwatch-skill loop monitor "<folder | url | screen: | window:<title>>" "<condition>" [--interval 10] [--max-checks 10]```Bounded — it always terminates. Events land in `events.jsonl` under theloop directory as structured records.## Record without judging```bashwatch-skill capture "<target>" [--duration 10]```Capture alone never critiques; it just records, analyzes, and indexes.Use `loop start` when there are pass criteria.

Frequently asked questions