[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71VC1BSQ5VAB2G42HTZQRWM":3,"skill-same:01M71VC1BSQ5VAB2G42HTZQRWM":53},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":13,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":52},"01M71VC1BSQ5VAB2G42HTZQRWM","memory",null,"Two-layer memory system with Dream-managed knowledge files.","midakaID\u002FNanobot","midakaID","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F274763386?v=4","01M71VBRKPKH8X05SDN8FNFMC5","01M71VBRMP9NXWW793AZCCSKDZ",0,"MIT","https:\u002F\u002Fgithub.com\u002FmidakaID\u002FNanobot\u002Fblob\u002Fmain\u002Fnanobot\u002Fskills\u002Fmemory\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26,27],"dream","knowledge","system","files","memory system","with","true","layer","managed","two","2026-11-10 13:02:02",false,"---\nname: memory\ndescription: Two-layer memory system with Dream-managed knowledge files.\nalways: true\n---\n\n# Memory\n\n## Structure\n\n- `SOUL.md` — Bot personality and communication style. **Managed by Dream.** Do NOT edit.\n- `USER.md` — User profile and preferences. **Managed by Dream.** Do NOT edit.\n- `memory\u002FMEMORY.md` — Long-term facts (project context, important events). **Managed by Dream.** Do NOT edit.\n- `memory\u002Fhistory.jsonl` — append-only JSONL, not loaded into context. Prefer the built-in `grep` tool to search it.\n\n## Search Past Events\n\n`memory\u002Fhistory.jsonl` is JSONL format — each line is a JSON object with `cursor`, `timestamp`, `content`.\n\n- For broad searches, start with `grep(..., path=\"memory\", glob=\"*.jsonl\", output_mode=\"count\")` or the default `files_with_matches` mode before expanding to full content\n- Use `output_mode=\"content\"` plus `context_before` \u002F `context_after` when you need the exact matching lines\n- Use `fixed_strings=true` for literal timestamps or JSON fragments\n- Use `head_limit` \u002F `offset` to page through long histories\n- Use `exec` only as a last-resort fallback when the built-in search cannot express what you need\n\nExamples (replace `keyword`):\n- `grep(pattern=\"keyword\", path=\"memory\u002Fhistory.jsonl\", case_insensitive=true)`\n- `grep(pattern=\"2026-04-02 10:00\", path=\"memory\u002Fhistory.jsonl\", fixed_strings=true)`\n- `grep(pattern=\"keyword\", path=\"memory\", glob=\"*.jsonl\", output_mode=\"count\", case_insensitive=true)`\n- `grep(pattern=\"oauth|token\", path=\"memory\", glob=\"*.jsonl\", output_mode=\"content\", case_insensitive=true)`\n\n## Important\n\n- **Do NOT edit SOUL.md, USER.md, or MEMORY.md.** They are automatically managed by Dream.\n- If you notice outdated information, it will be corrected when Dream runs next.\n- Users can view Dream's activity with the `\u002Fdream-log` command.\n","# Memory\n\n## Structure\n\n- `SOUL.md` — Bot personality and communication style. **Managed by Dream.** Do NOT edit.\n- `USER.md` — User profile and preferences. **Managed by Dream.** Do NOT edit.\n- `memory\u002FMEMORY.md` — Long-term facts (project context, important events). **Managed by Dream.** Do NOT edit.\n- `memory\u002Fhistory.jsonl` — append-only JSONL, not loaded into context. Prefer the built-in `grep` tool to search it.\n\n## Search Past Events\n\n`memory\u002Fhistory.jsonl` is JSONL format — each line is a JSON object with `cursor`, `timestamp`, `content`.\n\n- For broad searches, start with `grep(..., path=\"memory\", glob=\"*.jsonl\", output_mode=\"count\")` or the default `files_with_matches` mode before expanding to full content\n- Use `output_mode=\"content\"` plus `context_before` \u002F `context_after` when you need the exact matching lines\n- Use `fixed_strings=true` for literal timestamps or JSON fragments\n- Use `head_limit` \u002F `offset` to page through long histories\n- Use `exec` only as a last-resort fallback when the built-in search cannot express what you need\n\nExamples (replace `keyword`):\n- `grep(pattern=\"keyword\", path=\"memory\u002Fhistory.jsonl\", case_insensitive=true)`\n- `grep(pattern=\"2026-04-02 10:00\", path=\"memory\u002Fhistory.jsonl\", fixed_strings=true)`\n- `grep(pattern=\"keyword\", path=\"memory\", glob=\"*.jsonl\", output_mode=\"count\", case_insensitive=true)`\n- `grep(pattern=\"oauth|token\", path=\"memory\", glob=\"*.jsonl\", output_mode=\"content\", case_insensitive=true)`\n\n## Important\n\n- **Do NOT edit SOUL.md, USER.md, or MEMORY.md.** They are automatically managed by Dream.\n- If you notice outdated information, it will be corrected when Dream runs next.\n- Users can view Dream's activity with the `\u002Fdream-log` command.\n",{"name":5,"always":33,"description":7},true,"main","0cf90a8ad637cdb4cd42e8b8aa3b21c8c538fad7","nanobot\u002Fskills\u002Fmemory","https:\u002F\u002Fgithub.com\u002FmidakaID\u002FNanobot","https:\u002F\u002Fgithub.com\u002FmidakaID","2026-05-05 10:38:19",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":33},[42,45,48],{"tool":43,"command":44},"npx","npx skills add midakaID\u002FNanobot --skill memory",{"tool":46,"command":47},"bunx","bunx skills add midakaID\u002FNanobot --skill memory",{"tool":49,"command":50},"pnpm","pnpm dlx skills add midakaID\u002FNanobot --skill memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FmidakaID\u002FNanobot\u002Fblob\u002Fmain\u002Fnanobot\u002Fskills\u002Fmemory\u002FSKILL.md",[],[54,66,75,92,116,137],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":28},"01M71VCC94JY1AN5Q0VMY5V66D","weather","Get current weather and forecasts (no API key required).","https:\u002F\u002Fgithub.com\u002FmidakaID\u002FNanobot\u002Fblob\u002Fmain\u002Fnanobot\u002Fskills\u002Fweather\u002FSKILL.md",[],[56,61,62,63,64,65],"curl","get","help","api","https",{"skillNo":67,"name":68,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":28},"01M71VCB49R04140THDCNVE30D","update-setup","https:\u002F\u002Fgithub.com\u002FmidakaID\u002FNanobot\u002Fblob\u002Fmain\u002Fnanobot\u002Fskills\u002Fupdate-setup\u002FSKILL.md",[],[72,73,74],"update","setup","update setup",{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":28},"01M71VC9H72ZQA3HNRR00EAMY0","tmux","Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.","https:\u002F\u002Fgithub.com\u002FmidakaID\u002FNanobot\u002Fblob\u002Fmain\u002Fnanobot\u002Fskills\u002Ftmux\u002FSKILL.md",[],[77,82,83,84,85,86,87,88,89,90,91],"scraping","remote-control","for","darwin","linux","sessions","remote","interactive","output","control",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":103,"publishedAt":28},"01M71VC7SE11KHNPPE8W1W6Y64","summarize","Summarize or extract text\u002Ftranscripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube\u002Fvideo”).","https:\u002F\u002Fgithub.com\u002FmidakaID\u002FNanobot\u002Fblob\u002Fmain\u002Fnanobot\u002Fskills\u002Fsummarize\u002FSKILL.md",[98],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[94,21,104,105,106,107,65,108,109,110,111,112,84,113,114,115],"fallback","extract","transcripts","install","youtube","text","tap","local","transcribe","brew","local files","Video",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":125,"publishedAt":28},"01M71VC59TDJQFTAXA648H0J2G","skill-creator","Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.","https:\u002F\u002Fgithub.com\u002FmidakaID\u002FNanobot\u002Fblob\u002Fmain\u002Fnanobot\u002Fskills\u002Fskill-creator\u002FSKILL.md",[122],{"categoryNo":123,"categoryName":124,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000023","Skill与智能体开发",[126,127,128,129,130,23,131,132,133,72,134,135,136],"creator","skill creator","packaging","use","when","with scripts","create","references","scripts","assets","agentskills",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":28},"01M71VC2ESZ959XFF4FXVEGZS3","my","Check and set the agent's own runtime state (model, iterations, context window, token usage, web config). Use when diagnosing why something doesn't work (\"why can't you search the web?\", \"why did you stop?\"), checking resource limits before complex tasks, adapting configuration for long or simple tasks, or remembering user preferences across turns. Also use when the user asks what model you are running, how many tokens you've used, or what your settings are.","https:\u002F\u002Fgithub.com\u002FmidakaID\u002FNanobot\u002Fblob\u002Fmain\u002Fnanobot\u002Fskills\u002Fmy\u002FSKILL.md",[],[139,144,145,146,147,148,84,149,150,151,152,24,153,129,130,154,155,156,157,158],"can","SET","running","usage","model","runtime","search","tokens","long","preferences","you","tasks","across","check","state"]