菜单
Domain expertise for downloading a YouTube video locally at a resolution suitable for later frame OCR. Sub-skill of `youtube-extraction`. Use when the parent skill needs to acquire the source video file before any frame, transcript, or content analysis.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Automated project implementation orchestrator that drives feature-driven development from a single initial prompt through to completed code. Use this skill when the user invokes /init-project, /init-features, /add-feature, /continue-tasks, /continue-new-session, /iterate-tasks, /review-tasks, /update-tasks, /analyze-features, or /reinit. Also trigger proactively when docs/INITIAL_PROMPT.md exists and the user says anything like "move forward", "keep building", "what's next", "continue the implementation", or "start working on the project", AND when the user says "set up project management", "bootstrap a new project", "initialize the project workflow", or "make sure agents follow the project plan". This skill manages the full lifecycle: scaffolding a new project with enforcement artifacts, extracting feature specs via interview, generating phased implementation plans, spawning typed agents to execute tasks, monitoring completion sentinels, recovering from failures, and archiving finished work — all driven by m
Generate a copy-ready prompt that a fresh session (Claude Code, Codex, or Gemini) can paste in to immediately begin work on the next recommended action that was identified in this session's most recent recap. Reference-style — names file paths with short excerpts, no large inline content.
Self-perpetuating, subagent-driven iteration of the project pipeline. One invocation: (1) merges any pending PR left by the previous turn, (2) dispatches the recap-recommended next action as a fresh subagent so each unit of work gets a clean context, then (3) emits a copy-ready prompt for the action that comes AFTER the one just completed. Designed to pair with /loop for unattended runs and to minimize parent-context growth.
Run the full project orchestration loop with approved-spec gating, dependency ordering, verified completion, and deterministic failure/blocked handling
Use when starting a new project from scratch or retrofitting the project-manager workflow onto an existing repo. Scaffolds the docs/ tree, copies canonical templates, installs agent-enforcement artifacts (AGENTS.md, CLAUDE.md fragment, pre-commit guard, Claude Code hook, PR template, ROADMAP), and seeds INITIAL_PROMPT.md. Idempotent: re-running only fills gaps.
Dry-run project status report. Produces a read-only snapshot of feature specs, dependency blockers, plans, active tasks, stale work, verification backlog, and open issues without spawning agents or modifying files.
| name | video-acquisition |
| description | Domain expertise for downloading a YouTube video locally at a resolution suitable for later frame OCR. Sub-skill of `youtube-extraction`. Use when the parent skill needs to acquire the source video file before any frame, transcript, or content analysis. |
Sub-skill of youtube-extraction. The parent skill calls this when it needs the
source video on disk. You receive url and <basename> from the caller.
Place the video at:
docs/youtube-extraction/<basename>/video.<ext>
…at a resolution high enough for OCR of code and IDE chrome. Aim for 1080p when available; accept 720p when the upload caps there.
Frame OCR quality scales with pixel density. A 480p frame loses character
distinctions that are critical for code (l vs 1, O vs 0, : vs ;). If
you accept a low-res download here, every downstream sub-skill pays for it.
yt-dlp -f "bv*[height<=1080]+ba/b[height<=1080]" `
--merge-output-format mp4 `
-o "docs/youtube-extraction/<basename>/video.%(ext)s" `
"<url>"
The format selector picks the best video stream up to 1080p plus the best audio, falling back to a single 1080p-or-lower combined stream when separate streams are unavailable. Merging into mp4 is friendlier to ffmpeg downstream.
yt-dlp --skip-download --write-info-json --write-description `
-o "docs/youtube-extraction/<basename>/info.%(ext)s" `
"<url>"
Move-Item -Force docs/youtube-extraction/<basename>/info.info.json `
docs/youtube-extraction/<basename>/metadata.json
Move-Item -Force docs/youtube-extraction/<basename>/info.description `
docs/youtube-extraction/<basename>/description.txt
metadata.json carries the title, channel, duration, publish date, view count,
and tags — every later sub-skill leans on these. description.txt often holds
the canonical repo URL and file paths the speaker references.
| Symptom | Fallback |
|---|---|
Sign in to confirm you're not a bot | Pass --cookies-from-browser chrome (or whichever browser the user is signed into YouTube on). |
| Live stream / premiere | Skip — extraction needs a finalised VOD. Surface a clear error. |
| Members-only / private | Authenticated cookies as above. If still blocked, surface to the user. |
| Age-restricted | --cookies-from-browser again. |
| 1080p unavailable | Drop to bv*[height<=720]+ba/b[height<=720]. Note the resolution drop in EXTRACTION.md later. |
| Multiple parts (chapters) | Single download — chapters are timestamps within one file. |
video.<ext> exists and is non-empty.metadata.json parses as JSON and has a duration field.If video.<ext> already exists with non-zero size for the same <basename>, do
not re-download. Re-fetch metadata and description anyway, since channels can
edit those after upload.