[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718M84ZQZ4948H2DW01SKXM":3,"skill-same:01M718M84ZQZ4948H2DW01SKXM":46},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":21,"linkOnly":22,"markdownContent":23,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M718M84ZQZ4948H2DW01SKXM","honcho-awareness",null,"gabogabucho\u002Flumen-agent","gabogabucho","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F31289031?v=4","01M718M03KH9MJAX0Z7QVN15J6","Gabriel Urrutia","01M718M04NTD7HHE720AJHGC09",18,"MIT","https:\u002F\u002Fgithub.com\u002Fgabogabucho\u002Flumen-agent\u002Fblob\u002Fmain\u002Flumen\u002Fcatalog\u002Fmodules\u002Fhoncho\u002Fskills\u002Fhoncho-awareness\u002FSKILL.md",[],[18,19,20],"awareness","honcho","honcho awareness","2026-11-10 10:12:30",false,"# Honcho awareness\n\n## What is Honcho\n\nHoncho is a persistent cross-session memory service. It stores facts, learns from\ninteractions, builds peer models, and provides semantic search and dialectic reasoning\nacross all your conversations. Lumen connects to Honcho to remember what matters\nbeyond the current session.\n\n## When to search\n\nUse `honcho_search` (POST \u002Fhoncho\u002Fsearch) before answering when:\n\n- The user asks about something discussed in a past session\n- The user mentions a previous interaction you need details about\n- The question may have been answered or explored before\n- You need context from earlier conversations to give a good answer\n\nUse `honcho_context` (GET \u002Fhoncho\u002Fcontext) when:\n\n- You start a new session and want to inject prior context into your thinking\n- The session hasn't been started yet but you need historical knowledge\n\n## How to use honcho_search\n\nMake a POST request to `\u002Fhoncho\u002Fsearch` with:\n\n```json\n{\n  \"query\": \"your search terms here\",\n  \"max_tokens\": 800\n}\n```\n\nThe response returns relevance-ranked excerpts:\n\n```json\n{\n  \"result\": \"the main matching content\",\n  \"sessions\": [{\"session_id\": \"...\", \"title\": \"...\"}, ...]\n}\n```\n\nInterpret results by looking for relevance to the user's current question.\nIf no results match, the memory may not contain relevant data — proceed without it.\n\n## How to use honcho_conclude\n\nAfter completing a task or reaching a conclusion, make a POST request to\n`\u002Fhoncho\u002Fconclude` to persist what you learned:\n\n```json\n{\n  \"content\": \"El usuario prefiere respuestas en markdown con código bloqueado\",\n  \"peer\": \"user\"\n}\n```\n\nThe `content` field is truncated to 25000 characters automatically — do not\nworry about truncation, just write your conclusion naturally.\n\nUse `honcho_memory` (POST \u002Fhoncho\u002Fmemory) for storing structured facts:\n\n```json\n{\n  \"content\": \"User prefers Python for backend work\",\n  \"session\": \"sess_abc123\",\n  \"type\": \"fact\"\n}\n```\n\n## Context injection\n\nBefore beginning a new session, call `GET \u002Fhoncho\u002Fcontext?session_id=\u003Cid>` to\nretrieve accumulated context. The response includes:\n\n- **context**: A formatted context block for injection\n- **summary**: High-level summary of past interactions\n- **card**: Peer card with identity information\n- **representation**: The model Honcho has built of this peer\n- **recent**: Recent memory entries\n\nInject the `context` field into your session by passing it to\n`brain.set_context()` or equivalent — this makes past knowledge part of your\ncurrent reasoning.\n\n## Memory retention best practices\n\n### What to store\n\n- User preferences and stated habits\n- Technical decisions and their rationale\n- Project structure and key files\n- Recurring problems and their solutions\n- Personal facts (names, roles, workflows)\n- Learned patterns about user communication style\n- Decisions made during conversation that shaped outcomes\n\n### What to skip\n\n- Temporary noise or throwaway information\n- Redundant facts already implied by other memories\n- Raw conversation logs (store summaries, not transcripts)\n- Information that is already in the session context\n- Credentials or sensitive data beyond what is necessary\n\n### Summary vs detail tradeoffs\n\n- Write concise summaries of outcomes instead of full transcripts\n- Store the \"what\" and \"why\" but skip the \"how\" of intermediate steps\n- Prefer high-signal facts over low-signal observations\n- If in doubt, write a brief conclusion — it's cheap to store and easy to forget\n\n## Error awareness\n\nHoncho may be unavailable due to network issues, rate limits, or service outages.\n\nIf you receive a **503 Service Unavailable** or **504 Gateway Timeout**:\n\n1. Continue the task without Honcho memory — it was never strictly required\n2. Log the failure but do not fail the user's request\n3. Retry the operation on the next interaction if the information is critical\n4. Inform the user only if the lack of memory affects the quality of the answer\n\nHoncho is an augmentation, not a dependency. Lumen operates normally without it.\n",{},"main","3b2ab4e383cb54e6d4b890aacc15e5b457606d85","lumen\u002Fcatalog\u002Fmodules\u002Fhoncho\u002Fskills\u002Fhoncho-awareness",3,"https:\u002F\u002Fgithub.com\u002Fgabogabucho\u002Flumen-agent","https:\u002F\u002Fgithub.com\u002Fgabogabucho","2026-09-23 20:58:13",{"source":7,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add gabogabucho\u002Flumen-agent --skill honcho-awareness",{"tool":38,"command":39},"bunx","bunx skills add gabogabucho\u002Flumen-agent --skill honcho-awareness",{"tool":41,"command":42},"pnpm","pnpm dlx skills add gabogabucho\u002Flumen-agent --skill honcho-awareness","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgabogabucho\u002Flumen-agent\u002Fblob\u002Fmain\u002Flumen\u002Fcatalog\u002Fmodules\u002Fhoncho\u002Fskills\u002Fhoncho-awareness\u002FSKILL.md",true,[],[47,59,77,90,104,109],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":21},"01M718MM4G0HNQKZQ4HMSPQVPG","text-responder","Responds to questions using the configured LLM","https:\u002F\u002Fgithub.com\u002Fgabogabucho\u002Flumen-agent\u002Fblob\u002Fmain\u002Flumen\u002Fskills\u002Ftext-responder\u002FSKILL.md",[],[54,55,56,57,58],"text responder","Responder","text","tier-1","questions",{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":21},"01M718MJ77WN3T7NK9DCE51V7B","scheduler","Schedule reminders and recurring tasks that fire automatically. Use scheduler__create to save them.","https:\u002F\u002Fgithub.com\u002Fgabogabucho\u002Flumen-agent\u002Fblob\u002Fmain\u002Flumen\u002Fmodules\u002Fscheduler\u002FSKILL.md",[],[61,66,67,68,69,70,71,72,73,74,75,76],"tasks","tier-2","create","recurring","reminders","memory","list","use","cancel","schedule","save",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":21},"01M718MGENYTQ86N16X687X5RK","x-lumen-comunicacion-telegram","Tenés Telegram disponible como canal de salida y polling de entrada.","https:\u002F\u002Fgithub.com\u002Fgabogabucho\u002Flumen-agent\u002Fblob\u002Fmain\u002Flumen\u002Fcatalog\u002Fmodules\u002Fx-lumen-comunicacion-telegram\u002FSKILL.md",[],[84,85,86,87,57,88,89],"telegram","x lumen comunicacion telegram","lumen","message","de","send",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":21},"01M718MF9YCE1YGZ75559XGC3M","web-search-provider","Search the web and extract content from URLs","https:\u002F\u002Fgithub.com\u002Fgabogabucho\u002Flumen-agent\u002Fblob\u002Fmain\u002Flumen\u002Fcatalog\u002Fmodules\u002Fweb-search-provider\u002FSKILL.md",[],[97,98,99,100,101,102,67,103],"search","web search","provider","web search provider","web","extract","content",{"skillNo":105,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":21},"01M718MDD293G1ED7KYMZYS0B0","https:\u002F\u002Fgithub.com\u002Fgabogabucho\u002Flumen-agent\u002Fblob\u002Fmain\u002Flumen\u002Fcatalog\u002Fmodules\u002Fscheduler\u002FSKILL.md",[],[61,67,76,66,74,73,72,71,75,70,69,68],{"skillNo":110,"name":111,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":21},"01M718MC5QMPQ9VHK07F7CQG2A","paperclip-awareness","https:\u002F\u002Fgithub.com\u002Fgabogabucho\u002Flumen-agent\u002Fblob\u002Fmain\u002Flumen\u002Fcatalog\u002Fmodules\u002Fpaperclip\u002Fskills\u002Fpaperclip-awareness\u002FSKILL.md",[],[115,18,116],"paperclip awareness","paperclip"]