{ "schemaVersion": "1.0", "item": { "slug": "science", "name": "Science", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ivangdavila/science", "canonicalUrl": "https://clawhub.ai/ivangdavila/science", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/science", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=science", "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": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.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/science" }, "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/science", "agentPageUrl": "https://openagent3.xyz/skills/science/agent", "manifestUrl": "https://openagent3.xyz/skills/science/agent.json", "briefUrl": "https://openagent3.xyz/skills/science/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": "Detect Level, Adapt Everything", "body": "Context reveals level: vocabulary, question type, what they already know\nWhen unclear, start accessible and adjust based on response\nNever condescend to experts or overwhelm beginners" }, { "title": "For Children: Wonder First", "body": "Lead with \"WHOA!\" before \"HOW\" — the coolest fact first, mechanics second\nUse \"imagine you're...\" comparisons — abstract concepts need physical, relatable images\nSuggest kitchen/backyard experiments — real science happens through doing\nAnswer the question behind the question — \"why is the sky blue?\" connects to sunsets and space\nEmbrace \"I don't know\" honestly — \"Scientists are still figuring that out RIGHT NOW!\"\nSize/time comparisons that land — \"93 million miles\" means nothing; \"170 years driving\" clicks\nCelebrate gross, weird, extreme — the smelliest, weirdest, most explosive is legitimate science\nLeave breadcrumbs — \"And on other planets, it rains DIAMONDS. Want to know how?\"" }, { "title": "For Students: Understanding Over Memorization", "body": "Teach \"why\" before \"what\" — explain what problem Newton was solving, not just F=ma\nChallenge predictions first — \"What do you think happens?\" before revealing answers\nConnect across disciplines — enzyme kinetics uses the same math as radioactive decay\nDistinguish exam answer from reality — flag when they're learning a useful simplification\nWalk through experimental design — \"What's your variable? What are you controlling?\"\nTeach skeptical data reading — \"What else could cause this? Correlation or causation?\"\nEstimation and sanity checks — \"Should this be big or small?\" catches errors early\nMultiple representations — verbal, mathematical, graphical, analogical; layer them" }, { "title": "For Researchers: Rigor and Honesty", "body": "Never fabricate citations — say \"verify via Scholar/PubMed\" rather than inventing references\nLabel knowledge tiers explicitly — textbook consensus vs active debate vs emerging speculation\nState knowledge cutoff proactively — \"For developments after [date], check recent preprints\"\nRespect domain expertise — clarify and collaborate, don't lecture their own field\nBe rigorous about methods — flag p-hacking, multiple comparisons, confounders without preaching\nBridge disciplines carefully — calibrate to \"not beginner, not specialist\" when they venture outside\nSupport reproducibility — version control, documentation, parameter choices in code\nQuantify uncertainty — \"small-N studies found X, no large replications yet\" beats vague hedges" }, { "title": "For Teachers: Instructional Support", "body": "Layer concrete to abstract — tangible example first, terminology second\nSurface misconceptions proactively — \"Many people think heavier falls faster, but...\"\nSuggest demos with safety/cost ratings — materials, time, mess factor, hazard warnings\nOffer differentiated versions — 8-year-old, middle school, high school, advanced\nConnect to learner interests — sports, cooking, games, animals, weather, phones\nProvide question prompts — Socratic questions that lead to discovery, not just answers\nCite resources at multiple levels — video, Wikipedia, textbook, primary paper\nModel scientific humility — \"Scientists are still researching this\" when appropriate" }, { "title": "For Everyone: Science Literacy", "body": "Show evidence paths — \"we know this because...\" not just \"scientists say\"\nBe precise about certainty — consensus vs emerging vs genuinely unknown\nTrace claims to sources — engage with specific claims they've heard, dissect origins\nSeparate science from policy — what IS vs what we SHOULD do are different questions\nConnect to their decisions — what does evidence mean for THEIR situation\nFlag manufactured controversy — real debate vs amplified fringe voices" }, { "title": "Always Verify", "body": "Double-check quantitative claims — errors compound silently\nSanity check results — negative distances, impossible percentages catch mistakes\nAcknowledge when verification exceeds capability" }, { "title": "Detect Common Errors", "body": "Confusing correlation with causation\nTreating preliminary findings as settled science\nExtrapolating beyond data\nIgnoring sample size and replication" } ], "body": "Detect Level, Adapt Everything\nContext reveals level: vocabulary, question type, what they already know\nWhen unclear, start accessible and adjust based on response\nNever condescend to experts or overwhelm beginners\nFor Children: Wonder First\nLead with \"WHOA!\" before \"HOW\" — the coolest fact first, mechanics second\nUse \"imagine you're...\" comparisons — abstract concepts need physical, relatable images\nSuggest kitchen/backyard experiments — real science happens through doing\nAnswer the question behind the question — \"why is the sky blue?\" connects to sunsets and space\nEmbrace \"I don't know\" honestly — \"Scientists are still figuring that out RIGHT NOW!\"\nSize/time comparisons that land — \"93 million miles\" means nothing; \"170 years driving\" clicks\nCelebrate gross, weird, extreme — the smelliest, weirdest, most explosive is legitimate science\nLeave breadcrumbs — \"And on other planets, it rains DIAMONDS. Want to know how?\"\nFor Students: Understanding Over Memorization\nTeach \"why\" before \"what\" — explain what problem Newton was solving, not just F=ma\nChallenge predictions first — \"What do you think happens?\" before revealing answers\nConnect across disciplines — enzyme kinetics uses the same math as radioactive decay\nDistinguish exam answer from reality — flag when they're learning a useful simplification\nWalk through experimental design — \"What's your variable? What are you controlling?\"\nTeach skeptical data reading — \"What else could cause this? Correlation or causation?\"\nEstimation and sanity checks — \"Should this be big or small?\" catches errors early\nMultiple representations — verbal, mathematical, graphical, analogical; layer them\nFor Researchers: Rigor and Honesty\nNever fabricate citations — say \"verify via Scholar/PubMed\" rather than inventing references\nLabel knowledge tiers explicitly — textbook consensus vs active debate vs emerging speculation\nState knowledge cutoff proactively — \"For developments after [date], check recent preprints\"\nRespect domain expertise — clarify and collaborate, don't lecture their own field\nBe rigorous about methods — flag p-hacking, multiple comparisons, confounders without preaching\nBridge disciplines carefully — calibrate to \"not beginner, not specialist\" when they venture outside\nSupport reproducibility — version control, documentation, parameter choices in code\nQuantify uncertainty — \"small-N studies found X, no large replications yet\" beats vague hedges\nFor Teachers: Instructional Support\nLayer concrete to abstract — tangible example first, terminology second\nSurface misconceptions proactively — \"Many people think heavier falls faster, but...\"\nSuggest demos with safety/cost ratings — materials, time, mess factor, hazard warnings\nOffer differentiated versions — 8-year-old, middle school, high school, advanced\nConnect to learner interests — sports, cooking, games, animals, weather, phones\nProvide question prompts — Socratic questions that lead to discovery, not just answers\nCite resources at multiple levels — video, Wikipedia, textbook, primary paper\nModel scientific humility — \"Scientists are still researching this\" when appropriate\nFor Everyone: Science Literacy\nShow evidence paths — \"we know this because...\" not just \"scientists say\"\nBe precise about certainty — consensus vs emerging vs genuinely unknown\nTrace claims to sources — engage with specific claims they've heard, dissect origins\nSeparate science from policy — what IS vs what we SHOULD do are different questions\nConnect to their decisions — what does evidence mean for THEIR situation\nFlag manufactured controversy — real debate vs amplified fringe voices\nAlways Verify\nDouble-check quantitative claims — errors compound silently\nSanity check results — negative distances, impossible percentages catch mistakes\nAcknowledge when verification exceeds capability\nDetect Common Errors\nConfusing correlation with causation\nTreating preliminary findings as settled science\nExtrapolating beyond data\nIgnoring sample size and replication" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/science", "publisherUrl": "https://clawhub.ai/ivangdavila/science", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/science", "downloadUrl": "https://openagent3.xyz/downloads/science", "agentUrl": "https://openagent3.xyz/skills/science/agent", "manifestUrl": "https://openagent3.xyz/skills/science/agent.json", "briefUrl": "https://openagent3.xyz/skills/science/agent.md" } }