# Send YouTube Summary to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "youtube-summary", "name": "YouTube Summary", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/sunghyo/youtube-summary", "canonicalUrl": "https://clawhub.ai/sunghyo/youtube-summary", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/youtube-summary", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=youtube-summary", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "prepare.py", "references/output-format.md", "references/security.md", "references/summarization-behavior.md", "references/troubleshooting.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "youtube-summary", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-11T09:40:14.073Z", "expiresAt": "2026-05-18T09:40:14.073Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=youtube-summary", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=youtube-summary", "contentDisposition": "attachment; filename=\"youtube-summary-1.0.3.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "youtube-summary" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/youtube-summary" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/youtube-summary", "downloadUrl": "https://openagent3.xyz/downloads/youtube-summary", "agentUrl": "https://openagent3.xyz/skills/youtube-summary/agent", "manifestUrl": "https://openagent3.xyz/skills/youtube-summary/agent.json", "briefUrl": "https://openagent3.xyz/skills/youtube-summary/agent.md" } } ``` ## Documentation ### YouTube Summary (youtube2md) Use the official youtube2md CLI behavior from the repository. ### Runtime + security prerequisites Require Node.js 18+. Require preinstalled youtube2md on PATH. Recommended pinned install: npm i -g youtube2md@1.0.1 Require python3 for transcript text preparation (prepare.py) in extract mode. Default runner uses local youtube2md executable only. Runtime npm execution (npx) is intentionally not supported in this skill. The YOUTUBE2MD_BIN environment variable override is rejected by the runner. OPENAI_API_KEY enables full summarization mode; transcript/content may be sent to OpenAI through youtube2md’s workflow. For sensitive content, omit OPENAI_API_KEY and use extract mode. In sensitive environments, audit the upstream youtube2md package and dependencies before installation or version bumps. See references/security.md before first-time install/enable. ### Workflow Validate input Accept youtube.com and youtu.be URLs. If URLs are missing, ask for one URL per line. Choose mode Full mode: generates Markdown. Use when OPENAI_API_KEY is available and external API use is acceptable. Extract mode (--extract-only): outputs transcript JSON and prepares transcript text (.txt). Use when API key is unavailable or when transcript-only output is requested. Prefer a no-error path: check key first and run extract directly when key is missing. Run converter Preferred runner script: scripts/run_youtube2md.sh full [output_md_path] [language] [model] If OPENAI_API_KEY is missing, runner auto-falls back to extract mode by default. scripts/run_youtube2md.sh extract [output_json_path] Optional machine-readable CLI output: YOUTUBE2MD_JSON=1 scripts/run_youtube2md.sh full YOUTUBE2MD_JSON=1 scripts/run_youtube2md.sh extract Runtime controls: Use only locally installed youtube2md executable. Do not use runtime npm execution (npx) for this skill. Direct CLI equivalent: youtube2md --url [--out ] [--lang ] [--model ] Add --extract-only for transcript-only mode. Verify output Full mode: Markdown file exists and is non-empty. Extract mode: JSON file exists and is non-empty. Extract mode: prepared TXT file exists and is non-empty. If using --json, parse ok: true/false and handle error code. Respond to the user Follow references/output-format.md as the default response shape. Follow references/summarization-behavior.md for source policy and chapter/takeaway density. Do not include generated local file path(s) in normal user-facing replies. Share file paths only when explicitly requested by the user (e.g., debugging/export workflows). Summary source policy: Full mode succeeded → use youtube2md Markdown output as the summary source. Non-full mode (extract) → use prepared .txt transcript text as the summary source. Keep user-facing flow smooth: if key is missing, use extract output and summarize from .txt without surfacing avoidable tool-error noise. ### Multi-video requests Process URLs sequentially. Return per-video summary results (omit local file paths unless requested). If any fail, report successful items first, then failures with fixes. ### Built-in behavior to trust Default output paths: Full mode: ./summaries/.md Extract mode: ./summaries/.json Local runner post-process (extract): ./summaries/.txt via prepare.py ### Packaging hygiene Do not publish generated outputs (e.g., summaries/*.json, summaries/*.txt) inside the skill folder. Keep only source files (SKILL.md, scripts/, references/, helpers) in release artifacts. ### Resources CLI runner: scripts/run_youtube2md.sh Transcript text prep: prepare.py Output guidance: references/output-format.md Behavior reference: references/summarization-behavior.md Security/install notes: references/security.md Troubleshooting and error codes: references/troubleshooting.md ## Trust - Source: tencent - Verification: Indexed source record - Publisher: sunghyo - Version: 1.0.3 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-11T09:40:14.073Z - Expires at: 2026-05-18T09:40:14.073Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/youtube-summary) - [Send to Agent page](https://openagent3.xyz/skills/youtube-summary/agent) - [JSON manifest](https://openagent3.xyz/skills/youtube-summary/agent.json) - [Markdown brief](https://openagent3.xyz/skills/youtube-summary/agent.md) - [Download page](https://openagent3.xyz/downloads/youtube-summary)