Skip to content

axel-pm/watch-n-learn / skills/watch-and-learn

watch-and-learn

Verified

Watch a how-to / tutorial / demo video and turn the procedure it teaches into one or more working Claude Code skills. Use when the user wants to "turn this video into a skill", "watch this tutorial and make a skill", "learn how to do X from this video", "build a skill from this screencast/demo/talk", or capture a repeatable workflow shown in a video. Sends an agent to watch the video (local file or URL) with a local, free, no-API toolchain, breaks the procedure down, authors the skill(s), and verifies they actually work.

references/procedure-spec-template.md

View on GitHub
# procedure-spec-template.md

The structured breakdown to produce from a watched how-to video, before authoring any skill.
Fill every section; write "N/A" where the video genuinely doesn't cover it (and note the gap).

```md
# Procedure: <the capability the video teaches, as a verb phrase>

## Goal
One or two sentences: what someone can DO after this that they couldn't before.

## Prerequisites
- Tools / accounts / files that must exist first (versions if shown).
- Assumed starting state.

## Inputs → Outputs
- Input(s): what you start with.
- Output(s): what you end with (files created, state changed, artifact produced).

## Steps
Ordered, imperative, each independently checkable. For each step capture:
1. **<action>** — what to do.
   - exact command / UI action / keystroke shown  (quote it verbatim; cite frame @ T.Ts)
   - expected result / how you know it worked
   - evidence: frame #N @ T.Ts  and/or transcript [start–end]

## Decision points
Where the procedure branches ("if X then …"). State the condition and each path.

## Gotchas
Mistakes the video warns about, easy-to-miss details, ordering that matters, things that
look optional but aren't.

## Uncertain / inferred
Anything you concluded rather than saw stated — flag it so the skill author can verify.
```

## Reading tips
- **Exact syntax** (commands, filenames, flags) → read the **frame**, not the transcript (Whisper mangles code).
- **Intent / rationale** → the **transcript**.
- If a step's evidence is only narration with no supporting frame, mark it inferred.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall