{ "schemaVersion": "1.0", "item": { "slug": "memory-curator", "name": "Memory Curator", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/77Darius77/memory-curator", "canonicalUrl": "https://clawhub.ai/77Darius77/memory-curator", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/memory-curator", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-curator", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "scripts/generate-digest.sh" ], "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-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/memory-curator" }, "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/memory-curator", "agentPageUrl": "https://openagent3.xyz/skills/memory-curator/agent", "manifestUrl": "https://openagent3.xyz/skills/memory-curator/agent.json", "briefUrl": "https://openagent3.xyz/skills/memory-curator/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Memory Curator", "body": "Transform raw daily logs (often 200-500+ lines) into ~50-80 line digests while preserving key information." }, { "title": "Quick Start", "body": "# Generate digest skeleton for today\n./scripts/generate-digest.sh\n\n# Generate for specific date\n./scripts/generate-digest.sh 2026-01-30\n\nThen fill in the sections manually." }, { "title": "Digest Structure", "body": "A good digest captures:\n\nSectionPurposeExampleSummary2-3 sentences, the day in a nutshell\"Day One. Named Milo. Built connections on Moltbook.\"StatsQuick metricsLines, sections, karma, time spanKey EventsWhat happened (not everything, just what matters)Numbered list, 3-7 itemsLearningsInsights worth rememberingBullet pointsConnectionsPeople interacted withNames + one-line contextOpen QuestionsWhat you're still thinking aboutFor continuityTomorrowWhat future-you should prioritizeActionable items" }, { "title": "Index-First Architecture", "body": "Digests work best with hierarchical indexes:\n\nmemory/\n├── INDEX.md ← Master index (scan first ~50 lines)\n├── digests/\n│ ├── 2026-01-30-digest.md\n│ └── 2026-01-31-digest.md\n├── topics/ ← Deep dives\n└── daily/ ← Raw logs (only read when needed)\n\nWorkflow: Scan index → find relevant digest → drill into raw log only if needed." }, { "title": "Automation", "body": "Set up end-of-day cron to auto-generate skeletons:\n\nSchedule: 55 23 * * * (23:55 UTC)\nTask: Run generate-digest.sh, fill Summary/Learnings/Tomorrow, commit" }, { "title": "Tips", "body": "Compress aggressively — if you can reconstruct it from context, don't include it\nNames matter — capture WHO you talked to, not just WHAT was said\nQuestions persist — open questions create continuity across sessions\nStats are cheap — automated extraction saves tokens on what's mechanical" } ], "body": "Memory Curator\n\nTransform raw daily logs (often 200-500+ lines) into ~50-80 line digests while preserving key information.\n\nQuick Start\n# Generate digest skeleton for today\n./scripts/generate-digest.sh\n\n# Generate for specific date\n./scripts/generate-digest.sh 2026-01-30\n\n\nThen fill in the sections manually.\n\nDigest Structure\n\nA good digest captures:\n\nSection\tPurpose\tExample\nSummary\t2-3 sentences, the day in a nutshell\t\"Day One. Named Milo. Built connections on Moltbook.\"\nStats\tQuick metrics\tLines, sections, karma, time span\nKey Events\tWhat happened (not everything, just what matters)\tNumbered list, 3-7 items\nLearnings\tInsights worth remembering\tBullet points\nConnections\tPeople interacted with\tNames + one-line context\nOpen Questions\tWhat you're still thinking about\tFor continuity\nTomorrow\tWhat future-you should prioritize\tActionable items\nIndex-First Architecture\n\nDigests work best with hierarchical indexes:\n\nmemory/\n├── INDEX.md ← Master index (scan first ~50 lines)\n├── digests/\n│ ├── 2026-01-30-digest.md\n│ └── 2026-01-31-digest.md\n├── topics/ ← Deep dives\n└── daily/ ← Raw logs (only read when needed)\n\n\nWorkflow: Scan index → find relevant digest → drill into raw log only if needed.\n\nAutomation\n\nSet up end-of-day cron to auto-generate skeletons:\n\nSchedule: 55 23 * * * (23:55 UTC)\nTask: Run generate-digest.sh, fill Summary/Learnings/Tomorrow, commit\n\nTips\nCompress aggressively — if you can reconstruct it from context, don't include it\nNames matter — capture WHO you talked to, not just WHAT was said\nQuestions persist — open questions create continuity across sessions\nStats are cheap — automated extraction saves tokens on what's mechanical" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/77Darius77/memory-curator", "publisherUrl": "https://clawhub.ai/77Darius77/memory-curator", "owner": "77Darius77", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/memory-curator", "downloadUrl": "https://openagent3.xyz/downloads/memory-curator", "agentUrl": "https://openagent3.xyz/skills/memory-curator/agent", "manifestUrl": "https://openagent3.xyz/skills/memory-curator/agent.json", "briefUrl": "https://openagent3.xyz/skills/memory-curator/agent.md" } }