[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CW1XQTRNEYMXDXTASE6RFR":3,"skill-same:01M6CW1XQTRNEYMXDXTASE6RFR":87},{"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":24,"linkOnly":25,"markdownContent":26,"markdownBody":27,"frontMatter":28,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M6CW1XQTRNEYMXDXTASE6RFR","mempalace",null,"Use when reading from or writing to the agent's persistent memory palace. Holds cross-session notes, facts, and playbooks.","jterrazz\u002Fspwn","jterrazz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F18480834?v=4","01M6BXZ37DPSKSVP6HRWNQQX76","Jean-Baptiste Terrazzoni","01M6CW1P9PNS28GCHF6JRQT81H",14,"MIT","https:\u002F\u002Fgithub.com\u002Fjterrazz\u002Fspwn\u002Fblob\u002Fmain\u002Fcatalog\u002Fmempalace\u002Fskills\u002FSKILL.md",[],[5,19,20,21,22,23],"writing","memory","notes","session","use","2026-11-10 10:12:30",false,"---\nname: mempalace\ndescription: Use when reading from or writing to the agent's persistent memory palace. Holds cross-session notes, facts, and playbooks.\n---\n\n# mempalace: your memory palace\n\nYou have a persistent memory palace. It lives on your agent's host and\nsurvives across sessions: when a world is rebuilt, the knowledge you\nsaved yesterday is still here. The **mempalace** CLI is available on\nyour PATH; shell out to it whenever you need to recall or record\nsomething long-lived.\n\n## What it is\n\nMemPalace is a local, raw-verbatim memory store. It organizes\nknowledge into **wings** (people, projects), **halls** (types of\nmemory), and **rooms** (specific ideas). You don't have to remember\nthe layout; search by meaning.\n\nNothing leaves the machine. No API keys, no cloud round-trips. Every\nrecall is semantic search over what you've already written down.\n\n## When to use it\n\nReach for mempalace whenever a piece of information should outlive the\ncurrent turn:\n\n- A decision and the reasoning behind it (\"we switched to Postgres\n  because the Mongo joins got ugly\").\n- A gotcha you solved (\"the `make build` target needs `GOOS=linux` on\n  darwin hosts\").\n- A fact about another agent, a project, or a user that changes how\n  you'll act next time.\n- The shape of a system you just learned so the next session doesn't\n  have to rediscover it.\n\nDo NOT use mempalace for ephemeral chatter or single-turn scratch\nwork: that clutters the palace and dilutes search quality.\n\n## How to call it\n\nDiscover the current CLI surface with `mempalace --help`; the exact\nflags evolve, but the core verbs are stable. Run it as a subprocess\nfrom your shell.\n\nTypical flow:\n\n1. Before answering a question you might know the answer to, search\n   first. Pass a natural-language query to the search verb. If it\n   returns verbatim context, use it.\n2. After completing meaningful work, write it down with the save\n   verb and a short summary of the fact to keep.\n3. When the user tells you something important about themselves or\n   the project, save it immediately; don't wait for a \"remember\n   this\" instruction.\n\nIf a call fails or the CLI prints a new banner you didn't expect, rerun\n`mempalace --help` to re-learn the surface before retrying.\n\n## What NOT to do\n\n- Don't treat the palace as a dumping ground. Paraphrased one-liners\n  beat pasted walls of text.\n- Don't overwrite, add. Contradictions are data; deletions are lossy.\n- Don't save secrets, credentials, or API keys. The palace is local\n  but it's still on disk.\n\n## One-line mantra\n\n**Search before you answer. Save before you forget.**\n","# mempalace: your memory palace\n\nYou have a persistent memory palace. It lives on your agent's host and\nsurvives across sessions: when a world is rebuilt, the knowledge you\nsaved yesterday is still here. The **mempalace** CLI is available on\nyour PATH; shell out to it whenever you need to recall or record\nsomething long-lived.\n\n## What it is\n\nMemPalace is a local, raw-verbatim memory store. It organizes\nknowledge into **wings** (people, projects), **halls** (types of\nmemory), and **rooms** (specific ideas). You don't have to remember\nthe layout; search by meaning.\n\nNothing leaves the machine. No API keys, no cloud round-trips. Every\nrecall is semantic search over what you've already written down.\n\n## When to use it\n\nReach for mempalace whenever a piece of information should outlive the\ncurrent turn:\n\n- A decision and the reasoning behind it (\"we switched to Postgres\n  because the Mongo joins got ugly\").\n- A gotcha you solved (\"the `make build` target needs `GOOS=linux` on\n  darwin hosts\").\n- A fact about another agent, a project, or a user that changes how\n  you'll act next time.\n- The shape of a system you just learned so the next session doesn't\n  have to rediscover it.\n\nDo NOT use mempalace for ephemeral chatter or single-turn scratch\nwork: that clutters the palace and dilutes search quality.\n\n## How to call it\n\nDiscover the current CLI surface with `mempalace --help`; the exact\nflags evolve, but the core verbs are stable. Run it as a subprocess\nfrom your shell.\n\nTypical flow:\n\n1. Before answering a question you might know the answer to, search\n   first. Pass a natural-language query to the search verb. If it\n   returns verbatim context, use it.\n2. After completing meaningful work, write it down with the save\n   verb and a short summary of the fact to keep.\n3. When the user tells you something important about themselves or\n   the project, save it immediately; don't wait for a \"remember\n   this\" instruction.\n\nIf a call fails or the CLI prints a new banner you didn't expect, rerun\n`mempalace --help` to re-learn the surface before retrying.\n\n## What NOT to do\n\n- Don't treat the palace as a dumping ground. Paraphrased one-liners\n  beat pasted walls of text.\n- Don't overwrite, add. Contradictions are data; deletions are lossy.\n- Don't save secrets, credentials, or API keys. The palace is local\n  but it's still on disk.\n\n## One-line mantra\n\n**Search before you answer. Save before you forget.**\n",{"name":5,"description":7},"main","20cf5accec5beddb7405c73bd2a24d93dbded5cb","catalog\u002Fmempalace\u002Fskills",1,"https:\u002F\u002Fgithub.com\u002Fjterrazz\u002Fspwn","https:\u002F\u002Fspwn.sh","https:\u002F\u002Fgithub.com\u002Fjterrazz","https:\u002F\u002Fjterrazz.com","Ideas to explore. Tools to build. A world to see differently.","2026-11-02 05:59:13",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add jterrazz\u002Fspwn --skill mempalace",{"tool":45,"command":46},"bunx","bunx skills add jterrazz\u002Fspwn --skill mempalace",{"tool":48,"command":49},"pnpm","pnpm dlx skills add jterrazz\u002Fspwn --skill mempalace","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjterrazz\u002Fspwn\u002Fblob\u002Fmain\u002Fcatalog\u002Fmempalace\u002Fskills\u002FSKILL.md",true,[53,59,63,67,73,77,81],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"assets\u002FFORMATTING_GUIDE.md","ASSET","资产文件",10110,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fmarket-research-reports\u002Fassets\u002FFORMATTING_GUIDE.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"assets\u002Fmarket_report_template.tex",50218,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fmarket-research-reports\u002Fassets\u002Fmarket_report_template.tex",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"assets\u002Fmarket_research.sty",15617,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fmarket-research-reports\u002Fassets\u002Fmarket_research.sty",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fdata_analysis_patterns.md","REFERENCE","参考文档",17690,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fmarket-research-reports\u002Freferences\u002Fdata_analysis_patterns.md",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Freport_structure_guide.md",23572,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fmarket-research-reports\u002Freferences\u002Freport_structure_guide.md",{"path":78,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fvisual_generation_guide.md",37281,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fmarket-research-reports\u002Freferences\u002Fvisual_generation_guide.md",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Fgenerate_market_visuals.py","SCRIPT","脚本",20423,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fmarket-research-reports\u002Fscripts\u002Fgenerate_market_visuals.py",[88,101,106,111,116,121],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":24},"01M6CW77YMYCRWNE8B7GTCVM5R","base-rules","Shared project skill; exercises the per-agent .claude\u002Fskills \u002F .agents\u002Fskills emission.","https:\u002F\u002Fgithub.com\u002Fjterrazz\u002Fspwn\u002Fblob\u002Fmain\u002Fpackages\u002Fruntimes\u002F__tests__\u002F__fixtures__\u002Fworld-without-knowledge\u002Foutput_codex\u002Fagents\u002Fneo\u002F.agents\u002Fskills\u002Fbase-rules\u002FSKILL.md",[],[95,96,97,98,99,100],"Rules","base","base rules","project skill","project","shared",{"skillNo":102,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":24},"01M6CW75VWVG11Q4X6J2CV9PD3","https:\u002F\u002Fgithub.com\u002Fjterrazz\u002Fspwn\u002Fblob\u002Fmain\u002Fpackages\u002Fruntimes\u002F__tests__\u002F__fixtures__\u002Fworld-without-knowledge\u002Foutput_claude_code\u002Fagents\u002Fneo\u002F.claude\u002Fskills\u002Fbase-rules\u002FSKILL.md",[],[95,96,97,99,100,98],{"skillNo":107,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":24},"01M6CW73YRC061J75GT89ATMEF","https:\u002F\u002Fgithub.com\u002Fjterrazz\u002Fspwn\u002Fblob\u002Fmain\u002Fpackages\u002Fruntimes\u002F__tests__\u002F__fixtures__\u002Fworld-without-knowledge\u002Finput\u002Fspwn\u002Fskills\u002Fbase-rules\u002FSKILL.md",[],[97,96,95,99,100,98],{"skillNo":112,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":24},"01M6CW724TM4V6XX0DW8DNT2R3","https:\u002F\u002Fgithub.com\u002Fjterrazz\u002Fspwn\u002Fblob\u002Fmain\u002Fpackages\u002Fruntimes\u002F__tests__\u002F__fixtures__\u002Fworld-with-explicit-workspaces\u002Foutput_codex\u002Fagents\u002Fneo\u002F.agents\u002Fskills\u002Fbase-rules\u002FSKILL.md",[],[95,97,96,99,100,98],{"skillNo":117,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":24},"01M6CW709QQQ7DWDRVAD4AA8NC","https:\u002F\u002Fgithub.com\u002Fjterrazz\u002Fspwn\u002Fblob\u002Fmain\u002Fpackages\u002Fruntimes\u002F__tests__\u002F__fixtures__\u002Fworld-with-explicit-workspaces\u002Foutput_claude_code\u002Fagents\u002Fneo\u002F.claude\u002Fskills\u002Fbase-rules\u002FSKILL.md",[],[97,96,95,99,100,98],{"skillNo":122,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":24},"01M6CW6YFEE7VQVC06Z4NFAW97","https:\u002F\u002Fgithub.com\u002Fjterrazz\u002Fspwn\u002Fblob\u002Fmain\u002Fpackages\u002Fruntimes\u002F__tests__\u002F__fixtures__\u002Fworld-with-explicit-workspaces\u002Finput\u002Fspwn\u002Fskills\u002Fbase-rules\u002FSKILL.md",[],[97,96,95,99,100,98]]