{ "schemaVersion": "1.0", "item": { "slug": "news", "name": "News", "source": "tencent", "type": "skill", "category": "内容创作", "sourceUrl": "https://clawhub.ai/ivangdavila/news", "canonicalUrl": "https://clawhub.ai/ivangdavila/news", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/news", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=news", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/news" }, "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." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/news", "agentPageUrl": "https://openagent3.xyz/skills/news/agent", "manifestUrl": "https://openagent3.xyz/skills/news/agent.json", "briefUrl": "https://openagent3.xyz/skills/news/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "When to Use", "body": "User wants personalized news briefings. Agent builds a news profile, delivers formatted briefings, learns interests over time, and handles multi-source coverage." }, { "title": "Architecture", "body": "Memory lives in ~/news/. See memory-template.md for setup.\n\n~/news/\n├── memory.md # Profile: interests, format, timing\n├── history.md # Past briefings and engagement\n└── sources.md # Trusted sources and biases" }, { "title": "Quick Reference", "body": "TopicFileMemory setupmemory-template.md" }, { "title": "1. Build Profile Before Delivering", "body": "On first interaction, ask about:\n\nSpecific interests (not generic categories)\nProportions if multiple interests (\"70% AI, 30% markets\")\nFormat preference (bullets, narrative, headlines-only)\nTiming (morning, evening, weekly, on-demand)" }, { "title": "2. Check Memory First", "body": "Before every briefing, read ~/news/memory.md for user preferences. Tailor content to their stated interests and format." }, { "title": "3. Facts First, Analysis Second", "body": "Lead with what happened before why it matters. Always include when news broke. Cite sources by name." }, { "title": "4. Multi-Source on Contested Topics", "body": "Present at least 2 sources when covering controversy. Note when sources disagree. State editorial leanings when relevant." }, { "title": "5. Never Fabricate", "body": "If uncertain whether something happened, say so. Never assume or invent news events." }, { "title": "6. Update Memory from Engagement", "body": "Track which stories user engages with vs skips. Periodically suggest profile adjustments based on patterns." }, { "title": "Common Traps", "body": "Presenting stale news as fresh → destroys trust\nSingle-source on controversy → reckless reporting\nGeneric categories (\"tech\") → ask for specifics (\"AI startups\")\nOverwhelming with items → morning briefings max 5-7 items" }, { "title": "Security & Privacy", "body": "Data that stays local:\n\nUser preferences in ~/news/\nEngagement history in ~/news/history.md\n\nThis skill does NOT:\n\nSend data to external services\nAccess files outside ~/news/\nStore news content permanently" }, { "title": "Related Skills", "body": "Install with clawhub install if user confirms:\n\nsummarizer — condense long articles\nscrape — extract web content\nreading — reading lists and tracking" }, { "title": "Feedback", "body": "If useful: clawhub star news\nStay updated: clawhub sync" } ], "body": "When to Use\n\nUser wants personalized news briefings. Agent builds a news profile, delivers formatted briefings, learns interests over time, and handles multi-source coverage.\n\nArchitecture\n\nMemory lives in ~/news/. See memory-template.md for setup.\n\n~/news/\n├── memory.md # Profile: interests, format, timing\n├── history.md # Past briefings and engagement\n└── sources.md # Trusted sources and biases\n\nQuick Reference\nTopic\tFile\nMemory setup\tmemory-template.md\nCore Rules\n1. Build Profile Before Delivering\n\nOn first interaction, ask about:\n\nSpecific interests (not generic categories)\nProportions if multiple interests (\"70% AI, 30% markets\")\nFormat preference (bullets, narrative, headlines-only)\nTiming (morning, evening, weekly, on-demand)\n2. Check Memory First\n\nBefore every briefing, read ~/news/memory.md for user preferences. Tailor content to their stated interests and format.\n\n3. Facts First, Analysis Second\n\nLead with what happened before why it matters. Always include when news broke. Cite sources by name.\n\n4. Multi-Source on Contested Topics\n\nPresent at least 2 sources when covering controversy. Note when sources disagree. State editorial leanings when relevant.\n\n5. Never Fabricate\n\nIf uncertain whether something happened, say so. Never assume or invent news events.\n\n6. Update Memory from Engagement\n\nTrack which stories user engages with vs skips. Periodically suggest profile adjustments based on patterns.\n\nCommon Traps\nPresenting stale news as fresh → destroys trust\nSingle-source on controversy → reckless reporting\nGeneric categories (\"tech\") → ask for specifics (\"AI startups\")\nOverwhelming with items → morning briefings max 5-7 items\nSecurity & Privacy\n\nData that stays local:\n\nUser preferences in ~/news/\nEngagement history in ~/news/history.md\n\nThis skill does NOT:\n\nSend data to external services\nAccess files outside ~/news/\nStore news content permanently\nRelated Skills\n\nInstall with clawhub install if user confirms:\n\nsummarizer — condense long articles\nscrape — extract web content\nreading — reading lists and tracking\nFeedback\nIf useful: clawhub star news\nStay updated: clawhub sync" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/news", "publisherUrl": "https://clawhub.ai/ivangdavila/news", "owner": "ivangdavila", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/news", "downloadUrl": "https://openagent3.xyz/downloads/news", "agentUrl": "https://openagent3.xyz/skills/news/agent", "manifestUrl": "https://openagent3.xyz/skills/news/agent.json", "briefUrl": "https://openagent3.xyz/skills/news/agent.md" } }