[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J46XT1KA1HSEZYRM8HDSVT":3,"skill-same:01M6J46XT1KA1HSEZYRM8HDSVT":54},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":21,"publishedAt":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M6J46XT1KA1HSEZYRM8HDSVT","research-digest",null,"MiroShark\u002Fmiroshark-aeon","MiroShark","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F304594232?v=4","01M6J466B8NNAZ4H6NNK3N3TT5","01M6J466FXNNWH622S3B9PC496",20,"MIT","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fdocs\u002Fexamples\u002Fskill-templates\u002Fresearch-digest\u002FSKILL.md",[16],{"categoryNo":17,"categoryName":18,"taxonomyType":19,"taxonomyTypeDesc":20},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[22,23,24],"research","research digest","digest","2026-11-10 10:12:30",false,"---\nname: [REPLACE: SKILL_NAME]\ndescription: Digest of the most interesting new posts on [REPLACE: TOPIC] from RSS feeds and the open web\nmetadata:\n  category: productivity\n  var: \"\"\n  tags:\n    - research\n---\n\n> **${var}** — Optional. Pass a different topic to override the default. If empty, digests [REPLACE: TOPIC].\n\nToday is ${today}. Build a digest of the [REPLACE: MAX_ITEMS] most interesting new posts on **[REPLACE: TOPIC]**.\n\n## Steps\n\n1. **Read sources** — pull the last 24h of entries from each feed:\n\n   ```text\n   [REPLACE: FEED_URLS]\n   ```\n\n   (Comma- or newline-separated list of RSS\u002FAtom URLs.)\n\n   Use **WebFetch** to retrieve each feed and parse the entries. If a feed 404s or returns malformed XML, log a single warning line and skip that feed for this run.\n\n2. **Augment with web search** — run a `WebSearch` for `[REPLACE: TOPIC] latest` and pick up to 5 fresh links published in the last 24h that aren't already in the feed results.\n\n3. **Score and rank** — for each candidate, score on:\n   - **Recency** — within the last 24h gets full marks.\n   - **Source weight** — feeds in the configured list outrank generic search results.\n   - **Specificity** — items mentioning concrete numbers, code, or named systems beat opinion pieces.\n\n   Drop anything obviously off-topic (the `${var}` or `[REPLACE: TOPIC]` keyword should appear somewhere in title or summary).\n\n4. **Pick the top [REPLACE: MAX_ITEMS]** — write `output\u002Farticles\u002F[REPLACE: SKILL_NAME]-${today}.md` with one entry each:\n   ```markdown\n   ### [Title](url)\n   *[Source · published date]*\n   2-3 sentences distilling the takeaway. No filler.\n   ```\n\n5. **Notify** via `.\u002Fnotify` with:\n   ```\n   *[REPLACE: TOPIC] digest — ${today}*\n\n   [N] picks. Top item: [shortened title].\n\n   Full digest: https:\u002F\u002Fgithub.com\u002F${GITHUB_REPOSITORY}\u002Fblob\u002Fmain\u002Foutput\u002Farticles\u002F[REPLACE: SKILL_NAME]-${today}.md\n   ```\n\n6. **Log** — append to `memory\u002Flogs\u002F${today}.md`:\n   ```\n   ## [REPLACE: SKILL_NAME]\n   - **Sources scanned**: N feeds + 1 web search\n   - **Items picked**: N (of M candidates)\n   - **Top source**: domain\n   - **Status**: DIGEST_OK | DIGEST_QUIET (no items) | DIGEST_DEGRADED (some feeds failed)\n   ```\n\n## Network note\n\n`WebFetch` and `WebSearch` are built-in Claude tools. There is no network sandbox — `curl` works too; use `WebFetch` as the fallback for a flaky public GET. For this research skill the reads are unauthenticated, so `WebSearch` + `WebFetch` are the simplest path.\n\n## Constraints\n\n- **Never repeat**. Track which item URLs went out via `memory\u002Ftopics\u002F[REPLACE: SKILL_NAME]-seen.txt` (append-only). Skip anything that's already in there.\n- **No filler**. If fewer than `[REPLACE: MAX_ITEMS]` items meet the bar, send fewer items — never pad with low-signal content.\n- **Quote, don't paraphrase the news**. Say \"Anthropic released X\" not \"AI labs are releasing things.\" Specificity beats hand-waving.\n","> **${var}** — Optional. Pass a different topic to override the default. If empty, digests [REPLACE: TOPIC].\n\nToday is ${today}. Build a digest of the [REPLACE: MAX_ITEMS] most interesting new posts on **[REPLACE: TOPIC]**.\n\n## Steps\n\n1. **Read sources** — pull the last 24h of entries from each feed:\n\n   ```text\n   [REPLACE: FEED_URLS]\n   ```\n\n   (Comma- or newline-separated list of RSS\u002FAtom URLs.)\n\n   Use **WebFetch** to retrieve each feed and parse the entries. If a feed 404s or returns malformed XML, log a single warning line and skip that feed for this run.\n\n2. **Augment with web search** — run a `WebSearch` for `[REPLACE: TOPIC] latest` and pick up to 5 fresh links published in the last 24h that aren't already in the feed results.\n\n3. **Score and rank** — for each candidate, score on:\n   - **Recency** — within the last 24h gets full marks.\n   - **Source weight** — feeds in the configured list outrank generic search results.\n   - **Specificity** — items mentioning concrete numbers, code, or named systems beat opinion pieces.\n\n   Drop anything obviously off-topic (the `${var}` or `[REPLACE: TOPIC]` keyword should appear somewhere in title or summary).\n\n4. **Pick the top [REPLACE: MAX_ITEMS]** — write `output\u002Farticles\u002F[REPLACE: SKILL_NAME]-${today}.md` with one entry each:\n   ```markdown\n   ### [Title](url)\n   *[Source · published date]*\n   2-3 sentences distilling the takeaway. No filler.\n   ```\n\n5. **Notify** via `.\u002Fnotify` with:\n   ```\n   *[REPLACE: TOPIC] digest — ${today}*\n\n   [N] picks. Top item: [shortened title].\n\n   Full digest: https:\u002F\u002Fgithub.com\u002F${GITHUB_REPOSITORY}\u002Fblob\u002Fmain\u002Foutput\u002Farticles\u002F[REPLACE: SKILL_NAME]-${today}.md\n   ```\n\n6. **Log** — append to `memory\u002Flogs\u002F${today}.md`:\n   ```\n   ## [REPLACE: SKILL_NAME]\n   - **Sources scanned**: N feeds + 1 web search\n   - **Items picked**: N (of M candidates)\n   - **Top source**: domain\n   - **Status**: DIGEST_OK | DIGEST_QUIET (no items) | DIGEST_DEGRADED (some feeds failed)\n   ```\n\n## Network note\n\n`WebFetch` and `WebSearch` are built-in Claude tools. There is no network sandbox — `curl` works too; use `WebFetch` as the fallback for a flaky public GET. For this research skill the reads are unauthenticated, so `WebSearch` + `WebFetch` are the simplest path.\n\n## Constraints\n\n- **Never repeat**. Track which item URLs went out via `memory\u002Ftopics\u002F[REPLACE: SKILL_NAME]-seen.txt` (append-only). Skip anything that's already in there.\n- **No filler**. If fewer than `[REPLACE: MAX_ITEMS]` items meet the bar, send fewer items — never pad with low-signal content.\n- **Quote, don't paraphrase the news**. Say \"Anthropic released X\" not \"AI labs are releasing things.\" Specificity beats hand-waving.\n",{},"main","b582c38fd13a043dca7ed24605354715d7a6e3f2","docs\u002Fexamples\u002Fskill-templates\u002Fresearch-digest",2,"https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon","https:\u002F\u002Ft.me\u002Fmiroshark_aeon","https:\u002F\u002Fgithub.com\u002FMiroShark","https:\u002F\u002Fwww.miroshark.xyz\u002F","Simulate anything, for $1 & less than 10 min.","2026-11-12 02:45:59",{"source":7,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add MiroShark\u002Fmiroshark-aeon --skill research-digest",{"tool":46,"command":47},"bunx","bunx skills add MiroShark\u002Fmiroshark-aeon --skill research-digest",{"tool":49,"command":50},"pnpm","pnpm dlx skills add MiroShark\u002Fmiroshark-aeon --skill research-digest","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fdocs\u002Fexamples\u002Fskill-templates\u002Fresearch-digest\u002FSKILL.md",true,[],[55,90,113,141,166,189],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":69,"publishedAt":25},"01M6J4P8XKB8RJ7PCYMZPZ0F6S","you-web-search","Web search using You.com Search API with high-quality, cited results — runs keyless out of the box; YDC_API_KEY unlocks higher limits and real-time web crawling","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fyou-web-search\u002FSKILL.md",[61,64],{"categoryNo":62,"categoryName":63,"taxonomyType":19,"taxonomyTypeDesc":20},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":65,"categoryName":66,"taxonomyType":67,"taxonomyTypeDesc":68},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,22,85,86,87,88,89],"web search","search","you","you web search","web","time","only","api","web crawling","read","read-only","real-time","basics","keyless","with","results","high","quality","box","limits",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":25},"01M6J4P4H35WQG6RHGTTACSMVW","write-tweet","Multi-format tweet studio - standalone drafts (10 across 5 size tiers), a 5-10 tweet thread, or 10 remixes of past tweets, selected via ${var}","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-tweet\u002FSKILL.md",[],[97,98,99,100,101,77,102,103,104,105,82,106,107,108,109,110,111,112],"write","write tweet","standalone","social","studio","across","xai","past","drafts","twitter","thread","multi","size","via","format","content",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":122,"publishedAt":25},"01M6J4P11K7ZJ2PJDHDTTFZ1HY","weekly-aeoncard","Build a weekly token-consumption recap image from memory\u002Ftoken-usage.csv - this week + all-time totals, top skills, rendered as a shareable SVG card.","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fweekly-aeoncard\u002FSKILL.md",[119],{"categoryNo":120,"categoryName":121,"taxonomyType":19,"taxonomyTypeDesc":20},"01JBSEEDCAT000000000000016","图像与多媒体",[123,124,125,126,127,128,129,75,130,131,132,133,134,135,136,137,138,97,139,140],"weekly","weekly aeoncard","as","usage","SVG","memory","card","Meta","image","recap","csv","monitoring","notifications","productivity","top","build","token","aeon",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":25},"01M6J4NVJYQP5DNKSGXAXQW06B","vuln-tracker","One lifecycle poll over everything vuln-scanner produces - PR and advisory status, PVR triage transitions, and pending-disclosure aging, with a stars-secured impact headline and one action queue.","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-tracker\u002FSKILL.md",[],[148,149,130,150,151,97,139,152,153,154,155,156,157,158,159,160,161,84,162,163,164,165],"tracker","vuln tracker","impact","scanner","status","action","security","pr","stars","lifecycle","dev","gh","aging","advisory","github","transitions","triage","global",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":175,"publishedAt":25},"01M6J4NNQCHTKNGENAPJQ8KYHR","vuln-scanner","Audit trending repos for real security vulnerabilities and disclose responsibly - scan and route findings (PVR \u002F dependency PR), re-submit queued advisories, and send armed email disclosures","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-scanner\u002FSKILL.md",[172],{"categoryNo":173,"categoryName":174,"taxonomyType":19,"taxonomyTypeDesc":20},"01JBSEEDCAT000000000000005","邮件与沟通",[151,176,177,178,179,130,180,154,181,182,183,158,162,184,165,185,77,186,187,188],"vuln scanner","resend","re","trending","repos","email","for","scan","vulnerabilities","submit","route","audit","send",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":196,"publishedAt":25},"01M6J4NFBXTGG0R4M484T0KNYW","video-script","Turn a repo, product page, or update into a recording-ready video script in a receipts-first format - verifies every claim against live sources, then writes timestamped VO + on-screen direction with a plain-language glossary, assets checklist, anti-tells, and a verify-before-recording list","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-script\u002FSKILL.md",[195],{"categoryNo":120,"categoryName":121,"taxonomyType":19,"taxonomyTypeDesc":20},[197,198,199,200,201,202,203,204,205,82,206,207,208,84,209,210,211,212,213,111,214,215,216],"Video","video script","script","recording","sources","ready","direction","page","repo","claim","plain-language","glossary","first","verify","product","screen","update","list","live","receipts"]