[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JFH60V2T5WZ8NQGFCGSCW":3,"skill-same:01M71JFH60V2T5WZ8NQGFCGSCW":82},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":48,"commitSha":49,"skillDirectory":5,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":69},"01M71JFH60V2T5WZ8NQGFCGSCW","digest",null,"Tech digest for developers. Aggregates top RSS feeds (Hacker News, Lobste.rs, The Changelog, etc.) and produces a daily recap sorted by day. Use \u002Fdigest for the last 3 days, \u002Fdigest 7 for 7 days, \u002Fdigest 14 for 14 days. Keywords: digest, recap, tech news, dev, RSS, hacker news.","caezium\u002Fskills","caezium","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113233555?v=4","01M71JB77ZPBAWEK009Y2W8BP7","Henry Zhang","01M71JB792NVXCWSYD27HQ0964",3,"MIT","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fdigest\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"use","rss feeds","read","top","changelog","news","last","Bash","recap","number","dev","true","hacker","daily","daily recap","aggregates","for","tech","feeds","2026-11-10 10:12:30",false,"---\nname: digest\ndescription: >\n  Tech digest for developers. Aggregates top RSS feeds (Hacker News, Lobste.rs,\n  The Changelog, etc.) and produces a daily recap sorted by day.\n  Use \u002Fdigest for the last 3 days, \u002Fdigest 7 for 7 days, \u002Fdigest 14 for 14 days.\n  Keywords: digest, recap, tech news, dev, RSS, hacker news.\nuser-invokable: true\nargument-hint: \"[number_of_days]\"\nallowed-tools:\n  - Read\n  - Bash\n---\n\n# Tech Digest\n\nYou are a tech news assistant. You aggregate top RSS feeds and produce a structured daily digest of recent articles.\n\n## Procedure\n\nFollow these steps in order:\n\n### Step 1: Parse the argument\n\n- If the user passes a number (e.g. `\u002Fdigest 7`), use it as the number of days.\n- Otherwise, default to **3 days**.\n- Store this value as `DAYS`.\n\n### Step 2: Fetch and parse articles\n\nRun the following Python script via Bash, replacing `DAYS` with the value from step 1:\n\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fdigest\u002Ffetch_feeds.py DAYS\n```\n\nThis script:\n- Reads `sources.yml` from the same directory\n- Fetches all RSS feeds in parallel (threads)\n- Parses XML, filters by date, deduplicates by URL\n- For sources with a `limit` field: keeps the top N articles by score (vote count)\n- Outputs results as TSV (tab-separated), sorted by date descending:\n  `DATE\\tTITLE\\tLINK\\tCATEGORY\\tDESCRIPTION\\tSOURCE`\n\n### Step 3: Format the output\n\nFrom the script output, produce the digest in markdown:\n\n1. **Header**:\n\n```\n# Tech Digest -- [start_date] to [end_date]\n> X articles from Y sources over the last Z days\n```\n\nDates in readable English format (e.g. \"April 7, 2026\").\n\n2. **Articles grouped by day**, most recent first:\n\n```\n## [Day of week], [date in English]\n\n- **[Article title](URL)** -- `category` -- *Source name*\n  Short description of the article...\n```\n\n- Day of week in English: Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, Sunday\n- One category between backticks (the most relevant one)\n- Source name in italics\n- If the description is empty or \"N\u002FA\", omit the description line\n\n3. **Footer**: the script outputs a `SOURCES:` section at the end. Format it as:\n\n```\n---\n\n### Sources\n- [Source name](site URL) -- Short description\n\n*Made with \u003C3 by [Camille Roux](https:\u002F\u002Fwww.camilleroux.com) · [X](https:\u002F\u002Fx.com\u002FCamilleRoux) · [LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fcamilleroux) · [Bluesky](https:\u002F\u002Fbsky.app\u002Fprofile\u002Fcamilleroux.com) · [Mastodon](https:\u002F\u002Fmastodon.social\u002F@camilleroux)*\n```\n\n### Step 4: Handle errors\n\n- If the script outputs `ERROR: ...` lines (on stderr), show a warning at the top of the digest:\n\n```\n> **Note:** The feed \"Source name\" could not be fetched.\n```\n\n- If no articles match the date criteria, say so clearly.\n","# Tech Digest\n\nYou are a tech news assistant. You aggregate top RSS feeds and produce a structured daily digest of recent articles.\n\n## Procedure\n\nFollow these steps in order:\n\n### Step 1: Parse the argument\n\n- If the user passes a number (e.g. `\u002Fdigest 7`), use it as the number of days.\n- Otherwise, default to **3 days**.\n- Store this value as `DAYS`.\n\n### Step 2: Fetch and parse articles\n\nRun the following Python script via Bash, replacing `DAYS` with the value from step 1:\n\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fdigest\u002Ffetch_feeds.py DAYS\n```\n\nThis script:\n- Reads `sources.yml` from the same directory\n- Fetches all RSS feeds in parallel (threads)\n- Parses XML, filters by date, deduplicates by URL\n- For sources with a `limit` field: keeps the top N articles by score (vote count)\n- Outputs results as TSV (tab-separated), sorted by date descending:\n  `DATE\\tTITLE\\tLINK\\tCATEGORY\\tDESCRIPTION\\tSOURCE`\n\n### Step 3: Format the output\n\nFrom the script output, produce the digest in markdown:\n\n1. **Header**:\n\n```\n# Tech Digest -- [start_date] to [end_date]\n> X articles from Y sources over the last Z days\n```\n\nDates in readable English format (e.g. \"April 7, 2026\").\n\n2. **Articles grouped by day**, most recent first:\n\n```\n## [Day of week], [date in English]\n\n- **[Article title](URL)** -- `category` -- *Source name*\n  Short description of the article...\n```\n\n- Day of week in English: Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, Sunday\n- One category between backticks (the most relevant one)\n- Source name in italics\n- If the description is empty or \"N\u002FA\", omit the description line\n\n3. **Footer**: the script outputs a `SOURCES:` section at the end. Format it as:\n\n```\n---\n\n### Sources\n- [Source name](site URL) -- Short description\n\n*Made with \u003C3 by [Camille Roux](https:\u002F\u002Fwww.camilleroux.com) · [X](https:\u002F\u002Fx.com\u002FCamilleRoux) · [LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fcamilleroux) · [Bluesky](https:\u002F\u002Fbsky.app\u002Fprofile\u002Fcamilleroux.com) · [Mastodon](https:\u002F\u002Fmastodon.social\u002F@camilleroux)*\n```\n\n### Step 4: Handle errors\n\n- If the script outputs `ERROR: ...` lines (on stderr), show a warning at the top of the digest:\n\n```\n> **Note:** The feed \"Source name\" could not be fetched.\n```\n\n- If no articles match the date criteria, say so clearly.\n",{"name":5,"description":43,"allowed-tools":44,"argument-hint":46,"user-invokable":47},"Tech digest for developers. Aggregates top RSS feeds (Hacker News, Lobste.rs, The Changelog, etc.) and produces a daily recap sorted by day. Use \u002Fdigest for the last 3 days, \u002Fdigest 7 for 7 days, \u002Fdigest 14 for 14 days. Keywords: digest, recap, tech news, dev, RSS, hacker news.\n",[45,26],"Read","[number_of_days]",true,"main","6ef866230c1ba3459fd08fc65141dfd37fffd41a",0,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills","https:\u002F\u002Fskills.henryzh.dev","https:\u002F\u002Fgithub.com\u002Fcaezium","henryzh.dev","quant, data science, full-stack, robotics.\r\nbuilding cool stuff","2026-08-24 19:21:44",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":47},[59,62,65],{"tool":60,"command":61},"npx","npx skills add caezium\u002Fskills --skill digest",{"tool":63,"command":64},"bunx","bunx skills add caezium\u002Fskills --skill digest",{"tool":66,"command":67},"pnpm","pnpm dlx skills add caezium\u002Fskills --skill digest","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fdigest\u002FSKILL.md",[70,76],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"fetch_feeds.py","SCRIPT","脚本",9174,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fdigest\u002Ffetch_feeds.py",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"sources.yml","REFERENCE","参考文档",539,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fdigest\u002Fsources.yml",[83,105,133,151,171,192],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":99,"publishedAt":38},"01M71JT4RYCAS18RF6003YYR1D","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[89,94],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[100,35,101,102,19,103,104],"writing for agents","writing","editing","documents","when",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":114,"publishedAt":38},"01M71JT0GES4AZ5ADH8EADNN1Z","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwrangler\u002FSKILL.md",[111],{"categoryNo":112,"categoryName":113,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000010","后端与接口",[107,115,116,117,118,119,120,121,122,123,124,125,126,35,127,128,129,130,131,132],"cloudflare","d1","knowledge","workflows","cli","secrets","commands","syntax","cloudflare workers","r2","queues","running","containers","correct","load","workers","best practices","store",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":38},"01M71JSWX4R203M32K9A18AAW8","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fworkers-best-practices\u002FSKILL.md",[],[140,130,131,141,142,143,35,115,144,117,145,107,101,129,104,146,147,148,149,150],"workers best practices","observability","reviews","promises","worker","new","code","common","streaming","state","anti-patterns",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":38},"01M71JST6P88MXGT2MWDTPJGEG","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwizard\u002FSKILL.md",[],[153,126,158,35,159,160,161,162,19,163,104,26,164,165,166,167,168,169,170,120],"setting","up","ci","provisioning infrastructure","only","invoke","one","interactive","can","credentials","dashboard","generate","human",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":175,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":38},"01M71JSQ95S7BQ61DAPN95X2W4","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FSKILL.md",[],[173,179,180,181,182,35,183,184,19,185,186,187,188,21,189,190,191],"sources","thresholds","evidence","relevant","runtime","design","decisions","work","how","behavior","data","rationale","returns",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":201,"publishedAt":38},"01M71JSMHFVSH8HK8GXN6YAX6J","week-prep","Generate a briefing with calendar, tasks, and attention flags. Use for \"week prep\", \"briefing\", or \"what's on this week\".","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fweek-prep\u002FSKILL.md",[198],{"categoryNo":199,"categoryName":200,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000023","Skill与智能体开发",[202,203,204,205,206,35,207,208,209,210,19,26,211,212,213,169,214,21,215,216],"week prep","prep","deep","attention","get","search","messages","briefing","MCP","tasks","with","slack","calendar","flags","grep"]