Learn from a single YouTube or public video through The Homie's native video-learning engine. Use when the user asks Claude Code to watch, digest, study, summarize, extract strategy from, remember, compare, or apply lessons from one video URL.
Scanned 9/11/2026
Install to Claude Code
Skills Directorynpx -y skills add TheSmokeDev/taskchad-os --skill watch --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Watch?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/thesmokedev-watch)More formats (shields.io, HTML) on the badges page.
---
name: watch
description: Learn from a single YouTube or public video through The Homie's native video-learning engine. Use when the user asks Claude Code to watch, digest, study, summarize, extract strategy from, remember, compare, or apply lessons from one video URL.
---
# Watch
Delegate to the shared Homie engine. Do not implement a separate Claude-only extractor.
```powershell
uv run --project .claude/scripts thehomie chat -q "/watch <video-url> <optional question> --detail smart" -Q
```
- `smart`: transcript first; read bounded frames only when visual cues matter.
- `transcript`: captions/audio only.
- `deep`: bounded visual-frame inspection as well as transcript analysis.
- `--no-save`: skip the sourced vault note only when explicitly requested.
The engine analyzes one video, compares it with current/recalled context, keeps raw artifacts out of the vault, and saves a paraphrased dossier in `research/videos/` by default.
Application is two-step and default-deny: `/watch apply <job_id>` produces a local proposal without edits; `/watch approve <job_id> <exact-token>` applies only that exact local proposal. External actions remain separately gated.
Use `/watch status [job_id]`, `/watch retry <job_id>`, and `/watch cancel <job_id>` for operations.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling
