[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JNEJW52KYCFZ9XWXBC89G":3,"skill-same:01M71JNEJW52KYCFZ9XWXBC89G":70},{"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":23,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M71JNEJW52KYCFZ9XWXBC89G","memory-synthesis",null,"Distil daily notes, finished plans, and reports into short, grounded updates to agent-workspace\u002Fmemory\u002Fproject\u002F.","Qredence\u002Ffleet-pi","Qredence","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F148253410?v=4","01M71JMZV03PM051165HJA27F0","qredence","01M71JMZVM3QEE4DJZZ0J20M1Z",9,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi\u002Fblob\u002Fmain\u002Fagent-workspace\u002Fpi\u002Fskills\u002Fmemory-synthesis\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34],"memory","Synthesis","memory synthesis","notes","workspace","short","daily","reports","project","plans","updates","2026-11-10 10:12:30",false,"---\nname: memory-synthesis\ndescription: Distil daily notes, finished plans, and reports into short, grounded updates to agent-workspace\u002Fmemory\u002Fproject\u002F.\n---\n\n# Memory Synthesis Skill\n\n## When to use it\n\nUse this skill when raw notes, completed plans, traces, or repeated\nobservations need to become durable memory that future agents can rely on.\n\n## Inputs\n\n- `memory\u002Fdaily\u002F**`\n- completed or abandoned plans\n- useful traces or reports\n- repeated observations from recent implementation work\n\n## Outputs\n\n- concise updates to `memory\u002Fproject\u002F**`\n- distilled notes in `memory\u002Fsummaries\u002F**`\n- targeted research-note updates when outside guidance affects Fleet Pi\n\nCanonical project memory files:\n\n- `memory\u002Fproject\u002Farchitecture.md` for stable structure, runtime boundaries,\n  and recurring data-flow facts\n- `memory\u002Fproject\u002Fdecisions.md` for decisions and rationale\n- `memory\u002Fproject\u002Fpreferences.md` for stable user or project preferences\n- `memory\u002Fproject\u002Fopen-questions.md` for unresolved questions\n- `memory\u002Fproject\u002Fknown-issues.md` for durable rough edges and workarounds\n\n## Procedure\n\n1. Gather raw material from daily notes, plans, traces, and recent task\n   summaries.\n2. Remove one-off chatter, duplicated facts, and transient command output.\n3. Group surviving facts by durable purpose: architecture, decisions,\n   preferences, known issues, or open questions.\n4. Write the smallest update that would help a future agent act better.\n5. Prefer the canonical project memory file that matches the fact. Create an\n   ad hoc project-memory file only when explicitly requested, for temporary\n   harness tests, or for raw material that will be synthesized later.\n6. Link back to the triggering plan, artifact, or repository evidence when\n   helpful.\n\n## Quality checklist\n\n- The synthesized note is shorter and clearer than the raw material.\n- Claims are grounded in repository evidence or clearly labeled as tentative.\n- The destination file is the narrowest one that fits.\n- No raw logs or daily-note chatter were promoted unchanged.\n- A future agent could tell why this memory matters.\n","# Memory Synthesis Skill\n\n## When to use it\n\nUse this skill when raw notes, completed plans, traces, or repeated\nobservations need to become durable memory that future agents can rely on.\n\n## Inputs\n\n- `memory\u002Fdaily\u002F**`\n- completed or abandoned plans\n- useful traces or reports\n- repeated observations from recent implementation work\n\n## Outputs\n\n- concise updates to `memory\u002Fproject\u002F**`\n- distilled notes in `memory\u002Fsummaries\u002F**`\n- targeted research-note updates when outside guidance affects Fleet Pi\n\nCanonical project memory files:\n\n- `memory\u002Fproject\u002Farchitecture.md` for stable structure, runtime boundaries,\n  and recurring data-flow facts\n- `memory\u002Fproject\u002Fdecisions.md` for decisions and rationale\n- `memory\u002Fproject\u002Fpreferences.md` for stable user or project preferences\n- `memory\u002Fproject\u002Fopen-questions.md` for unresolved questions\n- `memory\u002Fproject\u002Fknown-issues.md` for durable rough edges and workarounds\n\n## Procedure\n\n1. Gather raw material from daily notes, plans, traces, and recent task\n   summaries.\n2. Remove one-off chatter, duplicated facts, and transient command output.\n3. Group surviving facts by durable purpose: architecture, decisions,\n   preferences, known issues, or open questions.\n4. Write the smallest update that would help a future agent act better.\n5. Prefer the canonical project memory file that matches the fact. Create an\n   ad hoc project-memory file only when explicitly requested, for temporary\n   harness tests, or for raw material that will be synthesized later.\n6. Link back to the triggering plan, artifact, or repository evidence when\n   helpful.\n\n## Quality checklist\n\n- The synthesized note is shorter and clearer than the raw material.\n- Claims are grounded in repository evidence or clearly labeled as tentative.\n- The destination file is the narrowest one that fits.\n- No raw logs or daily-note chatter were promoted unchanged.\n- A future agent could tell why this memory matters.\n",{"name":5,"description":7},"main","dde78dd776888d344120e4ac31a8c98b6e404a37","agent-workspace\u002Fpi\u002Fskills\u002Fmemory-synthesis",0,"https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi","https:\u002F\u002Fdocs.qredence.ai\u002F","https:\u002F\u002Fgithub.com\u002FQredence","qredence.ai","AI Systems","2026-11-11 07:04:24",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add Qredence\u002Ffleet-pi --skill memory-synthesis",{"tool":56,"command":57},"bunx","bunx skills add Qredence\u002Ffleet-pi --skill memory-synthesis",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Qredence\u002Ffleet-pi --skill memory-synthesis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi\u002Fblob\u002Fmain\u002Fagent-workspace\u002Fpi\u002Fskills\u002Fmemory-synthesis\u002FSKILL.md",true,[64],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"changelog.md","REFERENCE","参考文档",97,"https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi\u002Fblob\u002Fmain\u002Fagent-workspace\u002Fpi\u002Fskills\u002Fmemory-synthesis\u002Fchangelog.md",[71,83,105,116,153,160],{"skillNo":72,"name":5,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":35},"01M71JNK0ZH65KVP3FPBF3PDX2","Distil daily notes, finished plans, and reports into short, grounded updates to memory\u002Fproject\u002F. Use when raw notes pile up or the user asks to consolidate memory.","https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi\u002Fblob\u002Fmain\u002Ftemplates\u002Fagent-workspace\u002Fpi\u002Fskills\u002Fmemory-synthesis\u002FSKILL.md",[],[25,24,26,33,77,78,27,31,79,34,80,81,82,29,30,32],"user","consolidate memory","consolidate","when","use","up",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":35},"01M71JNHJHMQ4KXE6M5HS24B29","execution-plan","Write a resumable plan under plans\u002Factive\u002F for multi-step work, then keep its progress and decision logs current. Use when a task spans several steps or sessions.","https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi\u002Fblob\u002Fmain\u002Ftemplates\u002Fagent-workspace\u002Fpi\u002Fskills\u002Fexecution-plan\u002FSKILL.md",[],[90,91,92,93,94,95,96,97,98,99,80,81,33,100,101,102,103,104],"execution plan","plan","execution","progress","write","work","multi","task","logs","keep","sessions","decision","for","active","steps",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":35},"01M71JNFZEWWKFRTN3DNJVXV3H","doc-gardening","Clean up stale, duplicated, or contradictory notes in this workspace. Use when memory or plans feel noisy or out of date.","https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi\u002Fblob\u002Fmain\u002Ftemplates\u002Fagent-workspace\u002Fpi\u002Fskills\u002Fdoc-gardening\u002FSKILL.md",[],[112,113,114,28,80,81,33,115,82,24,27],"doc gardening","doc","stale","clean",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":134,"publishedAt":35},"01M71JNCB3F8FAQ0VD1R04TMPY","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","MIT","https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi\u002Fblob\u002Fmain\u002Fagent-workspace\u002Fpi\u002Fskills\u002Ffrontend-design\u002FSKILL.md",[123,126,129],{"categoryNo":124,"categoryName":125,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":130,"categoryName":131,"taxonomyType":132,"taxonomyTypeDesc":133},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,80,81],"frontend design","design","frontend","landing","applications","aesthetics","generic","ui design","css","pages","examples","with","react components","react","web ui","components","code","artifacts",{"skillNo":154,"name":85,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":159,"publishedAt":35},"01M71JNA89XRB5VM8SXPV6MPBE","Write a resumable plan under agent-workspace\u002Fplans\u002F for multi-step work and keep its progress and decision logs current.","https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi\u002Fblob\u002Fmain\u002Fagent-workspace\u002Fpi\u002Fskills\u002Fexecution-plan\u002FSKILL.md",[158],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[90,91,92,28,94,93,95,96,98,99,33,101,102],{"skillNo":161,"name":107,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":35},"01M71JN8SNFR0C8TRH34Z1E90N","Clean up stale, duplicated, or contradictory agent-facing docs and memory in agent-workspace\u002F. Use when notes feel noisy or out of date.","https:\u002F\u002Fgithub.com\u002FQredence\u002Ffleet-pi\u002Fblob\u002Fmain\u002Fagent-workspace\u002Fpi\u002Fskills\u002Fdoc-gardening\u002FSKILL.md",[165],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[112,113,115,81,80,24,82,114,167,27,28],"docs"]