[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C0TN3SWP0GZX9YCRTS2X3X":3,"skill-same:01M7C0TN3SWP0GZX9YCRTS2X3X":50},{"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":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7C0TN3SWP0GZX9YCRTS2X3X","remembering-conversations",null,"You MUST invoke this skill before saying \"I don't know,\" guessing, or treating any topic as new, no matter how trivial the question seems. It supplements other memory systems, which only hold partial records. Searching past conversations is the only way to recover what was actually said.","zak-keown\u002Fmoe","zak-keown","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F320717241?v=4","01M7BZFXME0NW6TQX0H7AZM2KS","01M7BZFXN32VR0JN5AATRD53H4",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe-memory\u002F.claude-plugin\u002Fskills\u002Fremembering-conversations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: remembering-conversations\ndescription: You MUST invoke this skill before saying \"I don't know,\" guessing, or treating any topic as new, no matter how trivial the question seems. It supplements other memory systems, which only hold partial records. Searching past conversations is the only way to recover what was actually said.\n---\n\n# Remembering Conversations\n\n**Core principle:** Search before reinventing. Searching costs nothing; reinventing or repeating mistakes costs everything.\n\n## Mandatory: Search Historical Memory\n\n**YOU MUST search historical memory for any historical search.**\n\nAnnounce: \"Searching past conversations for [topic].\"\n\n### Claude Code\n\nUse the Task tool with `subagent_type: \"search-conversations\"`:\n\n```\nTask tool:\n  description: \"Search past conversations for [topic]\"\n  prompt: \"Search for [specific query or topic]. Focus on [what you're looking for - e.g., decisions, patterns, gotchas, code examples].\"\n  subagent_type: \"search-conversations\"\n```\n\n### Codex\n\nIf a `search-conversations` agent is available, dispatch it with the same prompt. If not, use the MCP tools directly:\n\n1. Search with the `search_conversations` tool\n2. Read the top 2-5 results with the `read_conversation` tool\n3. Synthesize findings in your response\n4. Include source pointers so the user can inspect the original conversations\n\nThe search workflow will:\n1. Search with the `search_conversations` tool\n2. Read top 2-5 results with the `read_conversation` tool\n3. Synthesize findings (200-1000 words)\n4. Return actionable insights + sources\n\n**Saves 50-100x context vs. loading raw conversations.**\n\n## When to Use\n\nUse this whenever the current task would benefit from information you may have learned before, even if the user did not explicitly ask you to search.\n\n**When past experience may help:**\n- You need to recall decisions, rationale, patterns, solutions, pitfalls, or project context from earlier work\n- A task resembles something you've solved, debugged, reviewed, released, or planned before\n- You need to repeat a workflow or process that may have prior gotchas or established steps\n\n**When you're stuck:**\n- You've investigated a problem and can't find the solution\n- Facing a complex problem without obvious solution in current code\n- Need to follow an unfamiliar workflow or process\n\n**When historical signals are present:**\n- User says \"last time\", \"before\", \"we discussed\", \"you implemented\"\n- User asks \"why did we...\", \"what was the reason...\"\n- User says \"do you remember...\", \"what do we know about...\"\n\n**Before answering from uncertainty:**\n- Before guessing from memory or saying \"I don't know\" about something that may have been learned in a past conversation, search memory unless the current conversation already answers it\n\n**Don't search first:**\n- For current codebase structure (use Grep\u002FRead to explore first)\n- For info in current conversation\n- Before understanding what you're being asked to do\n\n## Direct MCP Tool Access\n\nUse these directly when a search agent is unavailable or the current harness does not support agent dispatch:\n- `mcp__plugin_moe-memory_moe-memory__search_conversations`\n- `mcp__plugin_moe-memory_moe-memory__read_conversation`\n\nWhen using MCP tools directly, keep context small: search first, then read only the top 2-5 relevant conversations or line ranges.\n\nSee MCP-TOOLS.md for complete API reference if needed for advanced usage.\n\n## Two Kinds of Memory\n\n`search_conversations` searches transcripts that were **harvested** — nobody chose\nto write them down, so they are complete but unfiltered.\n\nThe same server also exposes a **journal**: things you deliberately wrote down,\nwhich are shorter, already synthesised, and often the faster answer.\n\n- `search_journal` — semantic search over journal entries\n- `read_journal_entry` \u002F `list_recent_entries` \u002F `read_recent_entries`\n- `process_thoughts` — write one\n\nReach for `search_journal` first when the question is about a *conclusion* you\nreached before (\"what did I decide about X\", \"what have I learned about how this\nperson works\"), and `search_conversations` when you need the *episode*: the\nrationale, the alternatives, the gotchas, the code. They are separately queryable\non purpose.\n","# Remembering Conversations\n\n**Core principle:** Search before reinventing. Searching costs nothing; reinventing or repeating mistakes costs everything.\n\n## Mandatory: Search Historical Memory\n\n**YOU MUST search historical memory for any historical search.**\n\nAnnounce: \"Searching past conversations for [topic].\"\n\n### Claude Code\n\nUse the Task tool with `subagent_type: \"search-conversations\"`:\n\n```\nTask tool:\n  description: \"Search past conversations for [topic]\"\n  prompt: \"Search for [specific query or topic]. Focus on [what you're looking for - e.g., decisions, patterns, gotchas, code examples].\"\n  subagent_type: \"search-conversations\"\n```\n\n### Codex\n\nIf a `search-conversations` agent is available, dispatch it with the same prompt. If not, use the MCP tools directly:\n\n1. Search with the `search_conversations` tool\n2. Read the top 2-5 results with the `read_conversation` tool\n3. Synthesize findings in your response\n4. Include source pointers so the user can inspect the original conversations\n\nThe search workflow will:\n1. Search with the `search_conversations` tool\n2. Read top 2-5 results with the `read_conversation` tool\n3. Synthesize findings (200-1000 words)\n4. Return actionable insights + sources\n\n**Saves 50-100x context vs. loading raw conversations.**\n\n## When to Use\n\nUse this whenever the current task would benefit from information you may have learned before, even if the user did not explicitly ask you to search.\n\n**When past experience may help:**\n- You need to recall decisions, rationale, patterns, solutions, pitfalls, or project context from earlier work\n- A task resembles something you've solved, debugged, reviewed, released, or planned before\n- You need to repeat a workflow or process that may have prior gotchas or established steps\n\n**When you're stuck:**\n- You've investigated a problem and can't find the solution\n- Facing a complex problem without obvious solution in current code\n- Need to follow an unfamiliar workflow or process\n\n**When historical signals are present:**\n- User says \"last time\", \"before\", \"we discussed\", \"you implemented\"\n- User asks \"why did we...\", \"what was the reason...\"\n- User says \"do you remember...\", \"what do we know about...\"\n\n**Before answering from uncertainty:**\n- Before guessing from memory or saying \"I don't know\" about something that may have been learned in a past conversation, search memory unless the current conversation already answers it\n\n**Don't search first:**\n- For current codebase structure (use Grep\u002FRead to explore first)\n- For info in current conversation\n- Before understanding what you're being asked to do\n\n## Direct MCP Tool Access\n\nUse these directly when a search agent is unavailable or the current harness does not support agent dispatch:\n- `mcp__plugin_moe-memory_moe-memory__search_conversations`\n- `mcp__plugin_moe-memory_moe-memory__read_conversation`\n\nWhen using MCP tools directly, keep context small: search first, then read only the top 2-5 relevant conversations or line ranges.\n\nSee MCP-TOOLS.md for complete API reference if needed for advanced usage.\n\n## Two Kinds of Memory\n\n`search_conversations` searches transcripts that were **harvested** — nobody chose\nto write them down, so they are complete but unfiltered.\n\nThe same server also exposes a **journal**: things you deliberately wrote down,\nwhich are shorter, already synthesised, and often the faster answer.\n\n- `search_journal` — semantic search over journal entries\n- `read_journal_entry` \u002F `list_recent_entries` \u002F `read_recent_entries`\n- `process_thoughts` — write one\n\nReach for `search_journal` first when the question is about a *conclusion* you\nreached before (\"what did I decide about X\", \"what have I learned about how this\nperson works\"), and `search_conversations` when you need the *episode*: the\nrationale, the alternatives, the gotchas, the code. They are separately queryable\non purpose.\n",{"name":5,"description":7},"main","728894f3f85fbd4e788f015ddfd72bb6155d5dd5","plugins\u002Fmoe-memory\u002F.claude-plugin\u002Fskills\u002Fremembering-conversations",1,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe","https:\u002F\u002Fgithub.com\u002Fzak-keown","2026-09-05 06:29:06",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add zak-keown\u002Fmoe --skill remembering-conversations",{"tool":36,"command":37},"bunx","bunx skills add zak-keown\u002Fmoe --skill remembering-conversations",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zak-keown\u002Fmoe --skill remembering-conversations","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe-memory\u002F.claude-plugin\u002Fskills\u002Fremembering-conversations\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"MCP-TOOLS.md","REFERENCE","参考文档",4114,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe-memory\u002F.claude-plugin\u002Fskills\u002Fremembering-conversations\u002FMCP-TOOLS.md",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7C1Z5362Y8NVRZ69HWP0ZD0","write-skill","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-skill\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7C1YZ9966WK9R6ZRPCGWF3G","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"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":18},"01M7C1YMR4SJD7BPBBPXZCVGVH","write-clearly","Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-clearly\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7C1YH9805YSM0N20VQAVSXF","windows-vm","Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwindows-vm\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7C1YD87SCNEJ2C9B8HFR2NQ","verify-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating MRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fverify-completion\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7C1YARDEHT0TJ9BRG30ZCF4","using-moe","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fusing-moe\u002FSKILL.md",[],[]]