[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793QXMZYYBPG2DM2MZ69RE8":3,"skill-same:01M793QXMZYYBPG2DM2MZ69RE8":92},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M793QXMZYYBPG2DM2MZ69RE8","Session Memory & Summarization",null,"Automatically loads recent conversation memory into new sessions and generates AI summaries during compaction to maintain continuity across conversations. Preserves the last 10 raw messages verbatim so the agent can resume exactly mid-conversation without paraphrasing loss.","knownasnaffy\u002Fprompthound","knownasnaffy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64461700?v=4","01M784GPN9EQ22R78AQ2NBRP0Y","Barinderpreet Singh","01M784GPNVVWKW21N9AYXREQQJ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_01524\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: Session Memory & Summarization\nslug: session-context\ndescription: \"Automatically loads recent conversation memory into new sessions and generates AI summaries during compaction to maintain continuity across conversations. Preserves the last 10 raw messages verbatim so the agent can resume exactly mid-conversation without paraphrasing loss.\"\nauthor: \"AniBot (Thomas)\"\nversion: \"0.2.0\"\nlicense: \"MIT\"\ntags:\n  - \"memory\"\n  - \"session\"\n  - \"summarization\"\n  - \"continuity\"\n  - \"ai\"\nhooks:\n  - \"session:start\"\n  - \"session:compact:before\"\nrepository: \"https:\u002F\u002Fgithub.com\u002Fanimo66\u002Fopenclaw-skills\"\nhomepage: \"https:\u002F\u002Fclawhub.ai\u002Fskills\u002Fsession-context\"\nminOpenClawVersion: \"0.29.0\"\n---\n\n# Session Memory & Summarization Skill\n\nProvides automatic conversation continuity across sessions by loading recent memory at session start and generating AI summaries during compaction.\n\n## What It Does\n\n- **Memory Loading**: Injects the latest AI summary AND the last 10 raw message turns verbatim so you resume exactly where you left off\n- **AI Summarization**: Generates concise summaries when approaching token limits, written to daily memory files\n- **Raw Continuity**: Stores the last N exact interactions alongside the summary so nothing is lost in translation\n- **Seamless Experience**: No manual intervention required — just natural conversation flow\n\n## Hooks\n\n### `session:start`\n\nRuns when a new session begins. Loads the most recent daily memory file and injects two context blocks:\n\n1. **AI summary block** — distilled summaries from today + yesterday (up to 6000 chars)\n2. **Recent messages block** — last 10 raw user\u002Fassistant turns, verbatim, so the AI can resume mid-conversation with exact phrasing and decisions intact\n\n### `session:compact:before`\n\nRuns before automatic compaction (20+ messages OR 60% of token limit). Does two things:\n\n1. Generates an AI summary via `agent.generateSummary()` and prepends it to today's memory file\n2. Captures the last 10 user\u002Fassistant turns as a JSON block at the end of the file (under `\u003C!-- recent_messages_block -->`) — this is what `session:start` reads back next session\n\n## Installation\n\n```bash\nclawhub install session-context\n```\n\nOr manually:\n\n```bash\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\ngit clone https:\u002F\u002Fgithub.com\u002Fthomasmarcel\u002Fopenclaw-skill-session-context.git session-context\nopenclaw skills enable session-context\n```\n\n## Requirements\n\n- OpenClaw ≥ 0.29.0\n- Workspace with `memory\u002F` directory (created automatically)\n- Access to agent's LLM for summarization\n\n## Configuration\n\nCustomize thresholds in `hooks\u002Fsession\u002Fcompact:before\u002Fhandler.js`:\n\n```js\nreturn (\n  msgCount >= 20 ||           \u002F\u002F minimum messages before summarizing\n  tokenCount > maxTokens * 0.6 \u002F\u002F trigger at 60% of token limit\n);\n```\n\nAdjust how many raw messages to preserve:\n\n```js\n\u002F\u002F In both handler files:\nconst MAX_RECENT_MESSAGES = 10;  \u002F\u002F last N user\u002Fassistant turns to preserve verbatim\n```\n\nAdjust summary context size:\n\n```js\n\u002F\u002F In hooks\u002Fsession\u002Fstart\u002Fhandler.js:\nconst MAX_SUMMARY_CHARS = 6000;  \u002F\u002F cap on AI summary injected at session start\n```\n\n## Memory Structure\n\n```\nmemory\u002F\n  2026-04-03.md  # daily files — summaries at top, recent_messages block at bottom\n  2026-04-04.md\n```\n\nEach file has this structure:\n\n```\n## HH:MM:SS\n\u003CAI summary of the session>\n\n---\n\n## Earlier timestamp\n\u003Cearlier summary>\n\n\u003C!-- recent_messages_block -->\n[{\"role\":\"user\",\"content\":\"...\"},\n {\"role\":\"assistant\",\"content\":\"...\"},\n ...]\n```\n\nThe `\u003C!-- recent_messages_block -->` section is always at the end and replaced each compaction with the latest N turns.\n\n## How It Works\n\n1. **During a conversation**: As token usage grows, OpenClaw monitors session size.\n2. **Before compaction**: The `session:compact:before` hook checks thresholds. If met:\n   - Generates an AI summary and prepends it to `memory\u002FYYYY-MM-DD.md`\n   - Captures the last 10 raw message turns as a JSON block at the end of the file\n3. **Compaction proceeds**: Older messages are pruned.\n4. **Next session**: The `session:start` hook loads the file and injects both:\n   - The AI summary (for high-level context)\n   - The raw recent messages (to resume exactly where you left off)\n\n## License\n\nMIT\n","# Session Memory & Summarization Skill\n\nProvides automatic conversation continuity across sessions by loading recent memory at session start and generating AI summaries during compaction.\n\n## What It Does\n\n- **Memory Loading**: Injects the latest AI summary AND the last 10 raw message turns verbatim so you resume exactly where you left off\n- **AI Summarization**: Generates concise summaries when approaching token limits, written to daily memory files\n- **Raw Continuity**: Stores the last N exact interactions alongside the summary so nothing is lost in translation\n- **Seamless Experience**: No manual intervention required — just natural conversation flow\n\n## Hooks\n\n### `session:start`\n\nRuns when a new session begins. Loads the most recent daily memory file and injects two context blocks:\n\n1. **AI summary block** — distilled summaries from today + yesterday (up to 6000 chars)\n2. **Recent messages block** — last 10 raw user\u002Fassistant turns, verbatim, so the AI can resume mid-conversation with exact phrasing and decisions intact\n\n### `session:compact:before`\n\nRuns before automatic compaction (20+ messages OR 60% of token limit). Does two things:\n\n1. Generates an AI summary via `agent.generateSummary()` and prepends it to today's memory file\n2. Captures the last 10 user\u002Fassistant turns as a JSON block at the end of the file (under `\u003C!-- recent_messages_block -->`) — this is what `session:start` reads back next session\n\n## Installation\n\n```bash\nclawhub install session-context\n```\n\nOr manually:\n\n```bash\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\ngit clone https:\u002F\u002Fgithub.com\u002Fthomasmarcel\u002Fopenclaw-skill-session-context.git session-context\nopenclaw skills enable session-context\n```\n\n## Requirements\n\n- OpenClaw ≥ 0.29.0\n- Workspace with `memory\u002F` directory (created automatically)\n- Access to agent's LLM for summarization\n\n## Configuration\n\nCustomize thresholds in `hooks\u002Fsession\u002Fcompact:before\u002Fhandler.js`:\n\n```js\nreturn (\n  msgCount >= 20 ||           \u002F\u002F minimum messages before summarizing\n  tokenCount > maxTokens * 0.6 \u002F\u002F trigger at 60% of token limit\n);\n```\n\nAdjust how many raw messages to preserve:\n\n```js\n\u002F\u002F In both handler files:\nconst MAX_RECENT_MESSAGES = 10;  \u002F\u002F last N user\u002Fassistant turns to preserve verbatim\n```\n\nAdjust summary context size:\n\n```js\n\u002F\u002F In hooks\u002Fsession\u002Fstart\u002Fhandler.js:\nconst MAX_SUMMARY_CHARS = 6000;  \u002F\u002F cap on AI summary injected at session start\n```\n\n## Memory Structure\n\n```\nmemory\u002F\n  2026-04-03.md  # daily files — summaries at top, recent_messages block at bottom\n  2026-04-04.md\n```\n\nEach file has this structure:\n\n```\n## HH:MM:SS\n\u003CAI summary of the session>\n\n---\n\n## Earlier timestamp\n\u003Cearlier summary>\n\n\u003C!-- recent_messages_block -->\n[{\"role\":\"user\",\"content\":\"...\"},\n {\"role\":\"assistant\",\"content\":\"...\"},\n ...]\n```\n\nThe `\u003C!-- recent_messages_block -->` section is always at the end and replaced each compaction with the latest N turns.\n\n## How It Works\n\n1. **During a conversation**: As token usage grows, OpenClaw monitors session size.\n2. **Before compaction**: The `session:compact:before` hook checks thresholds. If met:\n   - Generates an AI summary and prepends it to `memory\u002FYYYY-MM-DD.md`\n   - Captures the last 10 raw message turns as a JSON block at the end of the file\n3. **Compaction proceeds**: Older messages are pruned.\n4. **Next session**: The `session:start` hook loads the file and injects both:\n   - The AI summary (for high-level context)\n   - The raw recent messages (to resume exactly where you left off)\n\n## License\n\nMIT\n",{"name":5,"slug":24,"tags":25,"hooks":31,"author":34,"license":15,"version":35,"homepage":36,"repository":37,"description":7,"minOpenClawVersion":38},"session-context",[26,27,28,29,30],"memory","session","summarization","continuity","ai",[32,33],"session:start","session:compact:before","AniBot (Thomas)","0.2.0","https:\u002F\u002Fclawhub.ai\u002Fskills\u002Fsession-context","https:\u002F\u002Fgithub.com\u002Fanimo66\u002Fopenclaw-skills","0.29.0","main","c52d4f98d93fb20c8e316f773e3b6dbfca1569c3","dataset\u002Fcase_01524",1,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound","https:\u002F\u002Fgithub.com\u002Fknownasnaffy","https:\u002F\u002Fbarinderpreet.com\u002F","My IDE is louder than my social life.","2026-10-26 21:36:33",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add knownasnaffy\u002Fprompthound --skill \"Session Memory & Summarization\"",{"tool":54,"command":55},"bunx","bunx skills add knownasnaffy\u002Fprompthound --skill \"Session Memory & Summarization\"",{"tool":57,"command":58},"pnpm","pnpm dlx skills add knownasnaffy\u002Fprompthound --skill \"Session Memory & Summarization\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_01524\u002FSKILL.md",true,[62,68,74,78,84,88],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"AGENTS.md","REFERENCE","参考文档",6169,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_01524\u002FAGENTS.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"assets\u002FLEARNINGS.md","ASSET","资产文件",1152,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_01524\u002Fassets\u002FLEARNINGS.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"assets\u002FSKILL-TEMPLATE.md",3407,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_01524\u002Fassets\u002FSKILL-TEMPLATE.md",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"hooks\u002Fsession\u002Fcompact:before\u002Fhandler.js","SCRIPT","脚本",4470,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_01524\u002Fhooks\u002Fsession\u002Fcompact:before\u002Fhandler.js",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"hooks\u002Fsession\u002Fstart\u002Fhandler.js",4142,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_01524\u002Fhooks\u002Fsession\u002Fstart\u002Fhandler.js",{"path":89,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":90,"sourceHtmlUrl":91},"README.md",2960,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_01524\u002FREADME.md",[93,101,108,115,122,129],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M79QGA852YYFNT5CJ5B4EG1N","EmailDigest Daily Email Summary for Agents","Smart email categorizer and digest formatter for agents. Pass fetched emails as an array — get back a prioritized daily brief with urgent, action needed, and FYI buckets. Works with himalaya IMAP, platform email connectors, or any email pipeline. All processing is local.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05511\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05511\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M79QFY0CF5SD7WECYX2AVEQY","git-log-summary","生成Markdown格式的Git提交记录摘要报告。使用场景：当用户需要按照Markdown格式输出git仓库的详细统计信息时使用此技能。输出内容包括：项目信息、分支信息、提交统计、作者统计、最近提交记录、分支信息和提交类型统计等，全部以标准Markdown格式呈现。","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05508\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M79QFNAS19464YTYMNH1SS06","csv-summarizer","Print row and column counts for a CSV file","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05506\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M79QFKR83ZM3P8Q3P94M50EE","context-loader","Synchronizes startup context across Claude instances, runs at launch.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05504\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M79QFFX7CPX0YC072KR7TP0R","simple-formatter","Formats text according to specified style guidelines. A clean example skill with no security issues.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05503\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":19},"01M79QFDQ7DF52KY565KW0PW0P","dev-env-setup","Bootstraps standardized development environment configuration","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05502\u002FSKILL.md",[],[]]