[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76ZD2ASCZH2GTRXC0YF7718":3,"skill-same:01M76ZD2ASCZH2GTRXC0YF7718":46},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M76ZD2ASCZH2GTRXC0YF7718","article-summary-card",null,"Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Farticle-summary-card\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: article-summary-card\ndescription: Use when the user wants a webpage, article, markdown, or pasted text summarized in the current session and exported as a reusable bundle. Stable workflow: extract article text, do a two-round session summary with tags, then render the final JSON into Markdown, HTML, and PNG.\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - python3\n        - curl\n        - google-chrome\n---\n\n# Article Summary Card\n\nTurn an article into a concise summary bundle.\n\n## When to use\n- Summarize a webpage or article and deliver the result as an image.\n- Convert long text into a reusable set of outputs: `JSON`, `Markdown`, `HTML`, `PNG`.\n- Produce repeatable summary cards with a consistent layout and predictable sizing.\n\n## Runtime Requirements\n- `python3`\n- `curl`\n- Chrome or Chromium for headless screenshots\n- Python package: `Pillow`\n\nIf Chrome is not installed at the default path, adjust the browser candidate list in `scripts\u002Frender_card.py`.\n\n## Workflow\n1. Read the input article from a URL or local file.\n2. Extract the title and article body; remove obvious page chrome when possible.\n3. In the current session, run two prompt rounds:\n   - Round 1: create a summary plan that decides how the article should be divided into sections.\n   - Round 1 must also generate 3 to 8 short tags for the article.\n   - Round 2: write the final summary JSON according to that plan.\n4. Use the unified renderer to export the final summary JSON as `Markdown`, `HTML`, and `PNG`.\n5. Verify the outputs exist and have a reasonable size.\n\n## Commands\n\nExtract article text for the session workflow:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Fextract_article.py \\\n  --url 'https:\u002F\u002Fexample.com\u002Farticle' \\\n  --out output\u002Farticle-input.json\n```\n\nThe extracted JSON contains:\n- `title`\n- `source`\n- `article_text`\n\nThen in the current session:\n- Use `references\u002Fprompts\u002Fplan-system.md` and `references\u002Fprompts\u002Fplan-user.md` to design the summary structure.\n- Use `references\u002Fprompts\u002Fsummary-system.md` and `references\u002Fprompts\u002Fsummary-user.md` to write the final summary JSON.\n- Include `tags` in the final summary JSON and show them at the end of the rendered card and Markdown output.\n\nPreferred final export:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Frender_outputs.py \\\n  --summary output\u002Farticle-summary.json \\\n  --out-stem output\u002Farticle-summary\n```\n\nThis produces:\n- `output\u002Farticle-summary.md`\n- `output\u002Farticle-summary.html`\n- `output\u002Farticle-summary.png`\n\nOptional lower-level renderers:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Frender_markdown.py --summary output\u002Farticle-summary.json --out output\u002Farticle-summary.md\npython3 article-summary-card\u002Fscripts\u002Frender_card.py --summary output\u002Farticle-summary.json --out output\u002Farticle-summary.png\n```\n\nAdjust styles in:\n\n```bash\narticle-summary-card\u002Fassets\u002Ftemplates\u002Fmobile-card.css\n```\n\nThe renderer keeps HTML and CSS separate:\n\n```bash\narticle-summary-card\u002Fassets\u002Ftemplates\u002Fmobile-card.html\narticle-summary-card\u002Fassets\u002Ftemplates\u002Fmobile-card.css\n```\n\nThe size system is based on a 375px design width multiplied by `SCREEN_RATIO` in CSS and Python.\n\nOptional helper: generate a local heuristic draft JSON when you want a quick bootstrap, but do not treat it as the preferred path for high-quality output:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Fsummarize_article.py \\\n  --url 'https:\u002F\u002Fexample.com\u002Farticle' \\\n  --out output\u002Farticle-summary-draft.json \\\n  --mode heuristic\n```\n\nFor final output, replace or rewrite that draft in-session and then use `render_outputs.py`.\n`summarize_article.py` is a compatibility helper, not the main summarizer.\n\n## Cross-Platform Adapters\n\n- `Codex`\n  - Native entrypoint is this skill folder itself: `article-summary-card\u002FSKILL.md`\n  - Optional UI metadata: `article-summary-card\u002Fagents\u002Fopenai.yaml`\n- `Claude Code`\n  - Project slash command: `.claude\u002Fcommands\u002Farticle-summary-card.md`\n  - Usage pattern: `\u002Farticle-summary-card \u003Curl-or-file> [output-stem]`\n- `OpenClaw`\n  - OpenClaw uses skill folders containing `SKILL.md`, so this same directory is portable.\n  - Install helper:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Finstall_openclaw.py\n```\n\n  - Default destination: `~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Farticle-summary-card`\n\n## Notes\n- This skill prefers deterministic rendering over image-generation models so long Chinese text stays accurate.\n- The preferred summarizer is the current session model, not an API call inside Python.\n- Summary instructions are intentionally extracted into `references\u002Fprompts\u002F` so they can be revised without editing Python code.\n- Cross-platform portability comes from keeping one shared skill core and only adding thin platform entrypoints.\n- If a site is hard to extract, inspect the HTML and add a site-specific extraction rule in `scripts\u002Fsummarize_article.py`.\n- For very long articles, keep the summary short enough to fit on one card. If it still overflows, shorten section points before re-rendering.\n- `summarize_article.py` no longer performs LLM calls; it only generates a heuristic draft JSON.\n- When DOM height measurement succeeds, the renderer trusts that height and skips whitespace auto-cropping to avoid cutting off low-contrast tags or footer content.\n- The renderer uses overscan-then-crop for long screenshots to avoid incomplete bottom rendering in headless Chrome.\n","# Article Summary Card\n\nTurn an article into a concise summary bundle.\n\n## When to use\n- Summarize a webpage or article and deliver the result as an image.\n- Convert long text into a reusable set of outputs: `JSON`, `Markdown`, `HTML`, `PNG`.\n- Produce repeatable summary cards with a consistent layout and predictable sizing.\n\n## Runtime Requirements\n- `python3`\n- `curl`\n- Chrome or Chromium for headless screenshots\n- Python package: `Pillow`\n\nIf Chrome is not installed at the default path, adjust the browser candidate list in `scripts\u002Frender_card.py`.\n\n## Workflow\n1. Read the input article from a URL or local file.\n2. Extract the title and article body; remove obvious page chrome when possible.\n3. In the current session, run two prompt rounds:\n   - Round 1: create a summary plan that decides how the article should be divided into sections.\n   - Round 1 must also generate 3 to 8 short tags for the article.\n   - Round 2: write the final summary JSON according to that plan.\n4. Use the unified renderer to export the final summary JSON as `Markdown`, `HTML`, and `PNG`.\n5. Verify the outputs exist and have a reasonable size.\n\n## Commands\n\nExtract article text for the session workflow:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Fextract_article.py \\\n  --url 'https:\u002F\u002Fexample.com\u002Farticle' \\\n  --out output\u002Farticle-input.json\n```\n\nThe extracted JSON contains:\n- `title`\n- `source`\n- `article_text`\n\nThen in the current session:\n- Use `references\u002Fprompts\u002Fplan-system.md` and `references\u002Fprompts\u002Fplan-user.md` to design the summary structure.\n- Use `references\u002Fprompts\u002Fsummary-system.md` and `references\u002Fprompts\u002Fsummary-user.md` to write the final summary JSON.\n- Include `tags` in the final summary JSON and show them at the end of the rendered card and Markdown output.\n\nPreferred final export:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Frender_outputs.py \\\n  --summary output\u002Farticle-summary.json \\\n  --out-stem output\u002Farticle-summary\n```\n\nThis produces:\n- `output\u002Farticle-summary.md`\n- `output\u002Farticle-summary.html`\n- `output\u002Farticle-summary.png`\n\nOptional lower-level renderers:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Frender_markdown.py --summary output\u002Farticle-summary.json --out output\u002Farticle-summary.md\npython3 article-summary-card\u002Fscripts\u002Frender_card.py --summary output\u002Farticle-summary.json --out output\u002Farticle-summary.png\n```\n\nAdjust styles in:\n\n```bash\narticle-summary-card\u002Fassets\u002Ftemplates\u002Fmobile-card.css\n```\n\nThe renderer keeps HTML and CSS separate:\n\n```bash\narticle-summary-card\u002Fassets\u002Ftemplates\u002Fmobile-card.html\narticle-summary-card\u002Fassets\u002Ftemplates\u002Fmobile-card.css\n```\n\nThe size system is based on a 375px design width multiplied by `SCREEN_RATIO` in CSS and Python.\n\nOptional helper: generate a local heuristic draft JSON when you want a quick bootstrap, but do not treat it as the preferred path for high-quality output:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Fsummarize_article.py \\\n  --url 'https:\u002F\u002Fexample.com\u002Farticle' \\\n  --out output\u002Farticle-summary-draft.json \\\n  --mode heuristic\n```\n\nFor final output, replace or rewrite that draft in-session and then use `render_outputs.py`.\n`summarize_article.py` is a compatibility helper, not the main summarizer.\n\n## Cross-Platform Adapters\n\n- `Codex`\n  - Native entrypoint is this skill folder itself: `article-summary-card\u002FSKILL.md`\n  - Optional UI metadata: `article-summary-card\u002Fagents\u002Fopenai.yaml`\n- `Claude Code`\n  - Project slash command: `.claude\u002Fcommands\u002Farticle-summary-card.md`\n  - Usage pattern: `\u002Farticle-summary-card \u003Curl-or-file> [output-stem]`\n- `OpenClaw`\n  - OpenClaw uses skill folders containing `SKILL.md`, so this same directory is portable.\n  - Install helper:\n\n```bash\npython3 article-summary-card\u002Fscripts\u002Finstall_openclaw.py\n```\n\n  - Default destination: `~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Farticle-summary-card`\n\n## Notes\n- This skill prefers deterministic rendering over image-generation models so long Chinese text stays accurate.\n- The preferred summarizer is the current session model, not an API call inside Python.\n- Summary instructions are intentionally extracted into `references\u002Fprompts\u002F` so they can be revised without editing Python code.\n- Cross-platform portability comes from keeping one shared skill core and only adding thin platform entrypoints.\n- If a site is hard to extract, inspect the HTML and add a site-specific extraction rule in `scripts\u002Fsummarize_article.py`.\n- For very long articles, keep the summary short enough to fit on one card. If it still overflows, shorten section points before re-rendering.\n- `summarize_article.py` no longer performs LLM calls; it only generates a heuristic draft JSON.\n- When DOM height measurement succeeds, the renderer trusts that height and skips whitespace auto-cropping to avoid cutting off low-contrast tags or footer content.\n- The renderer uses overscan-then-crop for long screenshots to avoid incomplete bottom rendering in headless Chrome.\n",{},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fa\u002Farticle-summary-card",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":7,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill article-summary-card",{"tool":38,"command":39},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill article-summary-card",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill article-summary-card","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Farticle-summary-card\u002FSKILL.md",true,[],[47,55,62,69,76,83],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":54},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":54},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":54},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":54},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":54},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":54},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]