Skip to content

mnvsk97/eyeroll / plugins/eyeroll/skills/video-to-skill

video-to-skill

Verified

Watch a tutorial or demo video and generate a Claude Code skill from it. Activated when user says "create a skill from this video" or similar.

FileKindSize
SKILL.mdskill md1.8 KB
---
name: video-to-skill
description: >
  Watch a tutorial or demo video and generate a Claude Code skill from it.
  Activated when user says "create a skill from this video" or similar.
user-invocable: true
---

# Video to Skill

Watch a tutorial or demo video and generate a Claude Code skill from it.

## When To Use

- User says "create a skill from this", "make this into a skill", "turn this into a command"
- User shares a tutorial video and wants to automate the workflow shown

## Workflow

1. Run `/eyeroll:watch <source> --context "create a skill from this"`
2. Check the report metadata before generating anything:
   - Continue when `intent` is tutorial/how-to, feature demo, or a workflow walkthrough
   - Pause and summarize instead when the video is a bug report, question, docs lookup, or general notes
3. From the report, identify:
   - What workflow/process is demonstrated
   - What commands/tools are used
   - What inputs and outputs
   - Trigger phrases (when should this skill activate)
4. Check if `skills/` directory exists, read existing skills for patterns
5. Generate SKILL.md using the template below
6. Ask the user to review before finalizing

## SKILL.md Template

```markdown
---
name: {skill-name}
description: >
  {What this skill does and when to use it.}
---

# {Skill Name}

{One-liner description.}

## When To Use This Skill

{Bullet list of trigger conditions.}

## Workflow

{Numbered steps the agent should follow.}

## Example Interactions

{2-3 realistic examples.}

## Rules

{Guardrails and constraints.}
```

## Rules

- Always run `/eyeroll:watch` first — don't generate a skill without understanding the video
- Do not force every video into a skill; use the report intent and handoff recommendation to decide
- Keep SKILL.md under 500 lines
- The generated skill should be self-contained
- Ask the user to review before finalizing
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: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated 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: 323kUpdated Claude CodeCodexVerifiedInstall