[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-letta-teleporting-between-environments":3,"mdc-ewyori-key":41,"related-repo-letta-teleporting-between-environments":632,"related-org-letta-teleporting-between-environments":725},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":36,"sourceUrl":39,"mdContent":40},"teleporting-between-environments","migrate agent conversations between environments","Moves the current agent conversation to Cloud or a Cloud-registered remote environment while coordinating machine-local files and setup. Use when the user says \"let's continue this task on cloud\", asks to continue or move work on another connected computer, wants to teleport between environments, or needs to upload or download artifacts before a handoff.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"letta","Letta","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fletta.png","letta-ai",[13,17,20],{"name":14,"slug":15,"type":16},"Operations","operations","tag",{"name":18,"slug":19,"type":16},"Agents","agents",{"name":21,"slug":22,"type":16},"Cloud","cloud",2831,"https:\u002F\u002Fgithub.com\u002Fletta-ai\u002Fletta-code","2026-08-14T04:52:06.902788",null,329,[29,30,31,32,33,8,34,35],"agent-memory","ai","claude","codex","continual-learning","memgpt","stateful-agents",{"repoUrl":24,"stars":23,"forks":27,"topics":37,"description":38},[29,30,31,32,33,8,34,35],"Stateful agents that are like people, with memory, identity, and the ability to learn and adapt","https:\u002F\u002Fgithub.com\u002Fletta-ai\u002Fletta-code\u002Ftree\u002FHEAD\u002Fsrc\u002Fskills\u002Fbuiltin\u002Fteleporting-between-environments","---\nname: teleporting-between-environments\ndescription: Moves the current agent conversation to Cloud or a Cloud-registered remote environment while coordinating machine-local files and setup. Use when the user says \"let's continue this task on cloud\", asks to continue or move work on another connected computer, wants to teleport between environments, or needs to upload or download artifacts before a handoff.\n---\n\n# Teleporting Between Environments\n\nTeleport the current agent and conversation without losing conversational memory. Prepare machine-local state first, then let the destination continue the same task.\n\n## Mental model\n\n- **Memory follows the agent; filesystem access does not.** Files, working directories, credentials, running processes, and local services belong to the computer currently executing the conversation.\n- Upload and download paths are relative to the current computer. Cloud cannot read a laptop path until the conversation teleports to that laptop.\n- The conversation’s managed Cloud sandbox remains alive while the conversation runs elsewhere.\n- Filesystem paths and cwd do not transfer between computers. Re-establish the destination’s repository, working directory, dependencies, credentials, and services after arrival.\n\n## Commands\n\n```bash\nletta teleport list\nletta teleport cloud\nletta teleport \u003Cenvironment>\n```\n\n- `list`: show accessible online remote targets. Desktop Local is excluded.\n- `cloud`: create or resume this conversation’s managed Cloud sandbox.\n- `\u003Cenvironment>`: target a listed remote environment by its friendly selector.\n\nTeleport cannot target Desktop Local yet. Once the conversation runs in Cloud,\nthe agent cannot programmatically return to Desktop Local. The user can still\nswitch manually with Desktop's environment picker. Do not run or recommend\n`letta teleport back`.\n\nTransfer files with the existing sandbox commands:\n\n```bash\nletta sandbox upload \u003Clocal-path>\nletta sandbox download \u003Csandbox-path> [--to \u003Clocal-path>]\n```\n\nDo not invent `letta teleport push`, `pull`, or remote file-listing commands. No sandbox ID or wake command is needed.\n\n## Prepare the handoff\n\nBefore teleporting:\n\n1. Identify the target and every file, repository state, credential, service, or setup step the task needs there.\n2. Finish work that requires the current computer. Verify relevant files exist before transferring them.\n3. Upload current-computer artifacts needed in Cloud and retain the returned `\u002Froot\u002Fdownloads\u002F...` paths in context.\n4. Retain enough context to recreate destination-local setup, including the repository, branch or revision, working directory, dependency commands, and next action.\n5. Run teleport only after all source-side preparation is complete.\n\n## Teleport is the final action\n\nRun the teleport command as the only command in the final Bash tool call. Do not chain later commands, poll the teleport operation, or invoke another source-side tool after it.\n\nThe CLI intentionally returns after the server accepts the handoff. Once the Bash result is persisted, the source yields at a clean turn or tool boundary and the destination resumes with no synthetic user message.\n\nIf the command reports an offline, stale, unsupported, same-source, or startup error, the conversation remains on the source. Surface the concrete error, correct it if possible, and retry only after the target is available.\n\n## Common workflows\n\n### Continue local work in Cloud\n\n1. Inspect the local task state and identify local-only artifacts or setup.\n2. Upload each artifact Cloud needs:\n\n   ```bash\n   letta sandbox upload \u003Clocal-path>\n   ```\n\n3. Retain each returned sandbox path.\n4. As the final action, run:\n\n   ```bash\n   letta teleport cloud\n   ```\n\n5. After continuation in Cloud, establish the Cloud-local cwd and repository setup before using the uploaded paths.\n\n### Return to Desktop Local\n\nThe agent cannot initiate this transition. Retain the next local action and ask\nthe user to select Local from Desktop's environment picker. After continuation\nlocally, resume the task from the retained context.\n\n### Continue on another connected computer\n\n1. Discover available targets if needed:\n\n   ```bash\n   letta teleport list\n   ```\n\n2. Prepare or upload everything the current computer owns.\n3. As the final action, run:\n\n   ```bash\n   letta teleport \u003Cenvironment>\n   ```\n",{"data":42,"body":43},{"name":4,"description":6},{"type":44,"children":45},"root",[46,54,60,67,98,104,189,224,237,242,345,366,372,377,414,420,425,430,435,441,448,536,542,547,553,626],{"type":47,"tag":48,"props":49,"children":50},"element","h1",{"id":4},[51],{"type":52,"value":53},"text","Teleporting Between Environments",{"type":47,"tag":55,"props":56,"children":57},"p",{},[58],{"type":52,"value":59},"Teleport the current agent and conversation without losing conversational memory. Prepare machine-local state first, then let the destination continue the same task.",{"type":47,"tag":61,"props":62,"children":64},"h2",{"id":63},"mental-model",[65],{"type":52,"value":66},"Mental model",{"type":47,"tag":68,"props":69,"children":70},"ul",{},[71,83,88,93],{"type":47,"tag":72,"props":73,"children":74},"li",{},[75,81],{"type":47,"tag":76,"props":77,"children":78},"strong",{},[79],{"type":52,"value":80},"Memory follows the agent; filesystem access does not.",{"type":52,"value":82}," Files, working directories, credentials, running processes, and local services belong to the computer currently executing the conversation.",{"type":47,"tag":72,"props":84,"children":85},{},[86],{"type":52,"value":87},"Upload and download paths are relative to the current computer. Cloud cannot read a laptop path until the conversation teleports to that laptop.",{"type":47,"tag":72,"props":89,"children":90},{},[91],{"type":52,"value":92},"The conversation’s managed Cloud sandbox remains alive while the conversation runs elsewhere.",{"type":47,"tag":72,"props":94,"children":95},{},[96],{"type":52,"value":97},"Filesystem paths and cwd do not transfer between computers. Re-establish the destination’s repository, working directory, dependencies, credentials, and services after arrival.",{"type":47,"tag":61,"props":99,"children":101},{"id":100},"commands",[102],{"type":52,"value":103},"Commands",{"type":47,"tag":105,"props":106,"children":111},"pre",{"className":107,"code":108,"language":109,"meta":110,"style":110},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","letta teleport list\nletta teleport cloud\nletta teleport \u003Cenvironment>\n","bash","",[112],{"type":47,"tag":113,"props":114,"children":115},"code",{"__ignoreMap":110},[116,138,155],{"type":47,"tag":117,"props":118,"children":121},"span",{"class":119,"line":120},"line",1,[122,127,133],{"type":47,"tag":117,"props":123,"children":125},{"style":124},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[126],{"type":52,"value":8},{"type":47,"tag":117,"props":128,"children":130},{"style":129},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[131],{"type":52,"value":132}," teleport",{"type":47,"tag":117,"props":134,"children":135},{"style":129},[136],{"type":52,"value":137}," list\n",{"type":47,"tag":117,"props":139,"children":141},{"class":119,"line":140},2,[142,146,150],{"type":47,"tag":117,"props":143,"children":144},{"style":124},[145],{"type":52,"value":8},{"type":47,"tag":117,"props":147,"children":148},{"style":129},[149],{"type":52,"value":132},{"type":47,"tag":117,"props":151,"children":152},{"style":129},[153],{"type":52,"value":154}," cloud\n",{"type":47,"tag":117,"props":156,"children":158},{"class":119,"line":157},3,[159,163,167,173,178,184],{"type":47,"tag":117,"props":160,"children":161},{"style":124},[162],{"type":52,"value":8},{"type":47,"tag":117,"props":164,"children":165},{"style":129},[166],{"type":52,"value":132},{"type":47,"tag":117,"props":168,"children":170},{"style":169},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[171],{"type":52,"value":172}," \u003C",{"type":47,"tag":117,"props":174,"children":175},{"style":129},[176],{"type":52,"value":177},"environmen",{"type":47,"tag":117,"props":179,"children":181},{"style":180},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[182],{"type":52,"value":183},"t",{"type":47,"tag":117,"props":185,"children":186},{"style":169},[187],{"type":52,"value":188},">\n",{"type":47,"tag":68,"props":190,"children":191},{},[192,203,213],{"type":47,"tag":72,"props":193,"children":194},{},[195,201],{"type":47,"tag":113,"props":196,"children":198},{"className":197},[],[199],{"type":52,"value":200},"list",{"type":52,"value":202},": show accessible online remote targets. Desktop Local is excluded.",{"type":47,"tag":72,"props":204,"children":205},{},[206,211],{"type":47,"tag":113,"props":207,"children":209},{"className":208},[],[210],{"type":52,"value":22},{"type":52,"value":212},": create or resume this conversation’s managed Cloud sandbox.",{"type":47,"tag":72,"props":214,"children":215},{},[216,222],{"type":47,"tag":113,"props":217,"children":219},{"className":218},[],[220],{"type":52,"value":221},"\u003Cenvironment>",{"type":52,"value":223},": target a listed remote environment by its friendly selector.",{"type":47,"tag":55,"props":225,"children":226},{},[227,229,235],{"type":52,"value":228},"Teleport cannot target Desktop Local yet. Once the conversation runs in Cloud,\nthe agent cannot programmatically return to Desktop Local. The user can still\nswitch manually with Desktop's environment picker. Do not run or recommend\n",{"type":47,"tag":113,"props":230,"children":232},{"className":231},[],[233],{"type":52,"value":234},"letta teleport back",{"type":52,"value":236},".",{"type":47,"tag":55,"props":238,"children":239},{},[240],{"type":52,"value":241},"Transfer files with the existing sandbox commands:",{"type":47,"tag":105,"props":243,"children":245},{"className":107,"code":244,"language":109,"meta":110,"style":110},"letta sandbox upload \u003Clocal-path>\nletta sandbox download \u003Csandbox-path> [--to \u003Clocal-path>]\n",[246],{"type":47,"tag":113,"props":247,"children":248},{"__ignoreMap":110},[249,284],{"type":47,"tag":117,"props":250,"children":251},{"class":119,"line":120},[252,256,261,266,270,275,280],{"type":47,"tag":117,"props":253,"children":254},{"style":124},[255],{"type":52,"value":8},{"type":47,"tag":117,"props":257,"children":258},{"style":129},[259],{"type":52,"value":260}," sandbox",{"type":47,"tag":117,"props":262,"children":263},{"style":129},[264],{"type":52,"value":265}," upload",{"type":47,"tag":117,"props":267,"children":268},{"style":169},[269],{"type":52,"value":172},{"type":47,"tag":117,"props":271,"children":272},{"style":129},[273],{"type":52,"value":274},"local-pat",{"type":47,"tag":117,"props":276,"children":277},{"style":180},[278],{"type":52,"value":279},"h",{"type":47,"tag":117,"props":281,"children":282},{"style":169},[283],{"type":52,"value":188},{"type":47,"tag":117,"props":285,"children":286},{"class":119,"line":140},[287,291,295,300,304,309,313,318,323,328,332,336,340],{"type":47,"tag":117,"props":288,"children":289},{"style":124},[290],{"type":52,"value":8},{"type":47,"tag":117,"props":292,"children":293},{"style":129},[294],{"type":52,"value":260},{"type":47,"tag":117,"props":296,"children":297},{"style":129},[298],{"type":52,"value":299}," download",{"type":47,"tag":117,"props":301,"children":302},{"style":169},[303],{"type":52,"value":172},{"type":47,"tag":117,"props":305,"children":306},{"style":129},[307],{"type":52,"value":308},"sandbox-pat",{"type":47,"tag":117,"props":310,"children":311},{"style":180},[312],{"type":52,"value":279},{"type":47,"tag":117,"props":314,"children":315},{"style":169},[316],{"type":52,"value":317},">",{"type":47,"tag":117,"props":319,"children":320},{"style":180},[321],{"type":52,"value":322}," [--to ",{"type":47,"tag":117,"props":324,"children":325},{"style":169},[326],{"type":52,"value":327},"\u003C",{"type":47,"tag":117,"props":329,"children":330},{"style":129},[331],{"type":52,"value":274},{"type":47,"tag":117,"props":333,"children":334},{"style":180},[335],{"type":52,"value":279},{"type":47,"tag":117,"props":337,"children":338},{"style":169},[339],{"type":52,"value":317},{"type":47,"tag":117,"props":341,"children":342},{"style":129},[343],{"type":52,"value":344},"]\n",{"type":47,"tag":55,"props":346,"children":347},{},[348,350,356,358,364],{"type":52,"value":349},"Do not invent ",{"type":47,"tag":113,"props":351,"children":353},{"className":352},[],[354],{"type":52,"value":355},"letta teleport push",{"type":52,"value":357},", ",{"type":47,"tag":113,"props":359,"children":361},{"className":360},[],[362],{"type":52,"value":363},"pull",{"type":52,"value":365},", or remote file-listing commands. No sandbox ID or wake command is needed.",{"type":47,"tag":61,"props":367,"children":369},{"id":368},"prepare-the-handoff",[370],{"type":52,"value":371},"Prepare the handoff",{"type":47,"tag":55,"props":373,"children":374},{},[375],{"type":52,"value":376},"Before teleporting:",{"type":47,"tag":378,"props":379,"children":380},"ol",{},[381,386,391,404,409],{"type":47,"tag":72,"props":382,"children":383},{},[384],{"type":52,"value":385},"Identify the target and every file, repository state, credential, service, or setup step the task needs there.",{"type":47,"tag":72,"props":387,"children":388},{},[389],{"type":52,"value":390},"Finish work that requires the current computer. Verify relevant files exist before transferring them.",{"type":47,"tag":72,"props":392,"children":393},{},[394,396,402],{"type":52,"value":395},"Upload current-computer artifacts needed in Cloud and retain the returned ",{"type":47,"tag":113,"props":397,"children":399},{"className":398},[],[400],{"type":52,"value":401},"\u002Froot\u002Fdownloads\u002F...",{"type":52,"value":403}," paths in context.",{"type":47,"tag":72,"props":405,"children":406},{},[407],{"type":52,"value":408},"Retain enough context to recreate destination-local setup, including the repository, branch or revision, working directory, dependency commands, and next action.",{"type":47,"tag":72,"props":410,"children":411},{},[412],{"type":52,"value":413},"Run teleport only after all source-side preparation is complete.",{"type":47,"tag":61,"props":415,"children":417},{"id":416},"teleport-is-the-final-action",[418],{"type":52,"value":419},"Teleport is the final action",{"type":47,"tag":55,"props":421,"children":422},{},[423],{"type":52,"value":424},"Run the teleport command as the only command in the final Bash tool call. Do not chain later commands, poll the teleport operation, or invoke another source-side tool after it.",{"type":47,"tag":55,"props":426,"children":427},{},[428],{"type":52,"value":429},"The CLI intentionally returns after the server accepts the handoff. Once the Bash result is persisted, the source yields at a clean turn or tool boundary and the destination resumes with no synthetic user message.",{"type":47,"tag":55,"props":431,"children":432},{},[433],{"type":52,"value":434},"If the command reports an offline, stale, unsupported, same-source, or startup error, the conversation remains on the source. Surface the concrete error, correct it if possible, and retry only after the target is available.",{"type":47,"tag":61,"props":436,"children":438},{"id":437},"common-workflows",[439],{"type":52,"value":440},"Common workflows",{"type":47,"tag":442,"props":443,"children":445},"h3",{"id":444},"continue-local-work-in-cloud",[446],{"type":52,"value":447},"Continue local work in Cloud",{"type":47,"tag":378,"props":449,"children":450},{},[451,456,499,504,531],{"type":47,"tag":72,"props":452,"children":453},{},[454],{"type":52,"value":455},"Inspect the local task state and identify local-only artifacts or setup.",{"type":47,"tag":72,"props":457,"children":458},{},[459,461],{"type":52,"value":460},"Upload each artifact Cloud needs:",{"type":47,"tag":105,"props":462,"children":464},{"className":107,"code":463,"language":109,"meta":110,"style":110},"letta sandbox upload \u003Clocal-path>\n",[465],{"type":47,"tag":113,"props":466,"children":467},{"__ignoreMap":110},[468],{"type":47,"tag":117,"props":469,"children":470},{"class":119,"line":120},[471,475,479,483,487,491,495],{"type":47,"tag":117,"props":472,"children":473},{"style":124},[474],{"type":52,"value":8},{"type":47,"tag":117,"props":476,"children":477},{"style":129},[478],{"type":52,"value":260},{"type":47,"tag":117,"props":480,"children":481},{"style":129},[482],{"type":52,"value":265},{"type":47,"tag":117,"props":484,"children":485},{"style":169},[486],{"type":52,"value":172},{"type":47,"tag":117,"props":488,"children":489},{"style":129},[490],{"type":52,"value":274},{"type":47,"tag":117,"props":492,"children":493},{"style":180},[494],{"type":52,"value":279},{"type":47,"tag":117,"props":496,"children":497},{"style":169},[498],{"type":52,"value":188},{"type":47,"tag":72,"props":500,"children":501},{},[502],{"type":52,"value":503},"Retain each returned sandbox path.",{"type":47,"tag":72,"props":505,"children":506},{},[507,509],{"type":52,"value":508},"As the final action, run:",{"type":47,"tag":105,"props":510,"children":512},{"className":107,"code":511,"language":109,"meta":110,"style":110},"letta teleport cloud\n",[513],{"type":47,"tag":113,"props":514,"children":515},{"__ignoreMap":110},[516],{"type":47,"tag":117,"props":517,"children":518},{"class":119,"line":120},[519,523,527],{"type":47,"tag":117,"props":520,"children":521},{"style":124},[522],{"type":52,"value":8},{"type":47,"tag":117,"props":524,"children":525},{"style":129},[526],{"type":52,"value":132},{"type":47,"tag":117,"props":528,"children":529},{"style":129},[530],{"type":52,"value":154},{"type":47,"tag":72,"props":532,"children":533},{},[534],{"type":52,"value":535},"After continuation in Cloud, establish the Cloud-local cwd and repository setup before using the uploaded paths.",{"type":47,"tag":442,"props":537,"children":539},{"id":538},"return-to-desktop-local",[540],{"type":52,"value":541},"Return to Desktop Local",{"type":47,"tag":55,"props":543,"children":544},{},[545],{"type":52,"value":546},"The agent cannot initiate this transition. Retain the next local action and ask\nthe user to select Local from Desktop's environment picker. After continuation\nlocally, resume the task from the retained context.",{"type":47,"tag":442,"props":548,"children":550},{"id":549},"continue-on-another-connected-computer",[551],{"type":52,"value":552},"Continue on another connected computer",{"type":47,"tag":378,"props":554,"children":555},{},[556,583,588],{"type":47,"tag":72,"props":557,"children":558},{},[559,561],{"type":52,"value":560},"Discover available targets if needed:",{"type":47,"tag":105,"props":562,"children":564},{"className":107,"code":563,"language":109,"meta":110,"style":110},"letta teleport list\n",[565],{"type":47,"tag":113,"props":566,"children":567},{"__ignoreMap":110},[568],{"type":47,"tag":117,"props":569,"children":570},{"class":119,"line":120},[571,575,579],{"type":47,"tag":117,"props":572,"children":573},{"style":124},[574],{"type":52,"value":8},{"type":47,"tag":117,"props":576,"children":577},{"style":129},[578],{"type":52,"value":132},{"type":47,"tag":117,"props":580,"children":581},{"style":129},[582],{"type":52,"value":137},{"type":47,"tag":72,"props":584,"children":585},{},[586],{"type":52,"value":587},"Prepare or upload everything the current computer owns.",{"type":47,"tag":72,"props":589,"children":590},{},[591,592],{"type":52,"value":508},{"type":47,"tag":105,"props":593,"children":595},{"className":107,"code":594,"language":109,"meta":110,"style":110},"letta teleport \u003Cenvironment>\n",[596],{"type":47,"tag":113,"props":597,"children":598},{"__ignoreMap":110},[599],{"type":47,"tag":117,"props":600,"children":601},{"class":119,"line":120},[602,606,610,614,618,622],{"type":47,"tag":117,"props":603,"children":604},{"style":124},[605],{"type":52,"value":8},{"type":47,"tag":117,"props":607,"children":608},{"style":129},[609],{"type":52,"value":132},{"type":47,"tag":117,"props":611,"children":612},{"style":169},[613],{"type":52,"value":172},{"type":47,"tag":117,"props":615,"children":616},{"style":129},[617],{"type":52,"value":177},{"type":47,"tag":117,"props":619,"children":620},{"style":180},[621],{"type":52,"value":183},{"type":47,"tag":117,"props":623,"children":624},{"style":169},[625],{"type":52,"value":188},{"type":47,"tag":627,"props":628,"children":629},"style",{},[630],{"type":52,"value":631},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":633,"total":724},[634,648,663,675,687,701,713],{"slug":635,"name":635,"fn":636,"description":637,"org":638,"tags":639,"stars":23,"repoUrl":24,"updatedAt":647},"acquiring-skills","discover and install agent skills","Discover and install skills from Hermes, ClawHub, GitHub, and other registries. Load this skill whenever a user asks for a capability you don't already have — image generation, social media, email, calendar, finance, DevOps, search, browser automation, etc.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[640,641,644],{"name":18,"slug":19,"type":16},{"name":642,"slug":643,"type":16},"Automation","automation",{"name":645,"slug":646,"type":16},"GitHub","github","2026-07-13T06:22:58.45767",{"slug":649,"name":650,"fn":651,"description":652,"org":653,"tags":654,"stars":23,"repoUrl":24,"updatedAt":662},"context-doctor","Context Doctor","repair system prompt and memory degradation","Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[655,656,659],{"name":18,"slug":19,"type":16},{"name":657,"slug":658,"type":16},"AI Context","ai-context",{"name":660,"slug":661,"type":16},"Debugging","debugging","2026-07-13T06:22:50.151002",{"slug":664,"name":664,"fn":665,"description":666,"org":667,"tags":668,"stars":23,"repoUrl":24,"updatedAt":674},"converting-mcps-to-skills","connect MCP servers to create skills","Connect to MCP (Model Context Protocol) servers and create skills for repeated use. Load when a user wants to use an MCP server, connect to external tools via MCP, or when they mention MCP, model context protocol, or specific MCP servers.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[669,670,671],{"name":18,"slug":19,"type":16},{"name":642,"slug":643,"type":16},{"name":672,"slug":673,"type":16},"MCP","mcp","2026-07-13T06:23:37.646079",{"slug":676,"name":676,"fn":677,"description":678,"org":679,"tags":680,"stars":23,"repoUrl":24,"updatedAt":686},"creating-mods","create and edit Letta Code mods","Creates and edits trusted local Letta Code mods, including tools, slash commands, local-only model providers, lifecycle\u002Fturn events, scoped conversation helpers, panels, and capability-gated behavior. Use when asked to make a mod, add an agent-callable tool, add a slash command, add a local provider\u002Fmodel adapter, transform turns, react to app events, or add lightweight mod UI outside the dedicated \u002Fstatusline flow.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[681,682,683],{"name":18,"slug":19,"type":16},{"name":642,"slug":643,"type":16},{"name":684,"slug":685,"type":16},"Coding","coding","2026-07-23T05:42:38.133565",{"slug":688,"name":688,"fn":689,"description":690,"org":691,"tags":692,"stars":23,"repoUrl":24,"updatedAt":700},"creating-skills","create and update agent skills","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[693,694,697],{"name":18,"slug":19,"type":16},{"name":695,"slug":696,"type":16},"Documentation","documentation",{"name":698,"slug":699,"type":16},"Plugin Development","plugin-development","2026-07-13T06:22:56.998659",{"slug":702,"name":702,"fn":703,"description":704,"org":705,"tags":706,"stars":23,"repoUrl":24,"updatedAt":712},"customizing-commands","create and manage Letta slash commands","Creates, edits, and enables Letta Code mod-provided slash commands. Use when the user asks to add a custom \u002Fcommand, slash command, command shortcut, scoped conversation-backed command, or command-driven panel behavior.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[707,708,709],{"name":18,"slug":19,"type":16},{"name":642,"slug":643,"type":16},{"name":710,"slug":711,"type":16},"CLI","cli","2026-07-13T06:23:18.266798",{"slug":714,"name":714,"fn":715,"description":716,"org":717,"tags":718,"stars":23,"repoUrl":24,"updatedAt":723},"customizing-statusline","customize Letta Code statusline mods","Creates, edits, and migrates Letta Code statusline mods. Use when handling the \u002Fstatusline command or continuing work started by \u002Fstatusline.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[719,720],{"name":710,"slug":711,"type":16},{"name":721,"slug":722,"type":16},"Engineering","engineering","2026-07-13T06:23:27.465985",20,{"items":726,"total":834},[727,733,739,745,751,757,763,768,780,796,807,819],{"slug":635,"name":635,"fn":636,"description":637,"org":728,"tags":729,"stars":23,"repoUrl":24,"updatedAt":647},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[730,731,732],{"name":18,"slug":19,"type":16},{"name":642,"slug":643,"type":16},{"name":645,"slug":646,"type":16},{"slug":649,"name":650,"fn":651,"description":652,"org":734,"tags":735,"stars":23,"repoUrl":24,"updatedAt":662},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[736,737,738],{"name":18,"slug":19,"type":16},{"name":657,"slug":658,"type":16},{"name":660,"slug":661,"type":16},{"slug":664,"name":664,"fn":665,"description":666,"org":740,"tags":741,"stars":23,"repoUrl":24,"updatedAt":674},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[742,743,744],{"name":18,"slug":19,"type":16},{"name":642,"slug":643,"type":16},{"name":672,"slug":673,"type":16},{"slug":676,"name":676,"fn":677,"description":678,"org":746,"tags":747,"stars":23,"repoUrl":24,"updatedAt":686},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[748,749,750],{"name":18,"slug":19,"type":16},{"name":642,"slug":643,"type":16},{"name":684,"slug":685,"type":16},{"slug":688,"name":688,"fn":689,"description":690,"org":752,"tags":753,"stars":23,"repoUrl":24,"updatedAt":700},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[754,755,756],{"name":18,"slug":19,"type":16},{"name":695,"slug":696,"type":16},{"name":698,"slug":699,"type":16},{"slug":702,"name":702,"fn":703,"description":704,"org":758,"tags":759,"stars":23,"repoUrl":24,"updatedAt":712},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[760,761,762],{"name":18,"slug":19,"type":16},{"name":642,"slug":643,"type":16},{"name":710,"slug":711,"type":16},{"slug":714,"name":714,"fn":715,"description":716,"org":764,"tags":765,"stars":23,"repoUrl":24,"updatedAt":723},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[766,767],{"name":710,"slug":711,"type":16},{"name":721,"slug":722,"type":16},{"slug":769,"name":769,"fn":770,"description":771,"org":772,"tags":773,"stars":23,"repoUrl":24,"updatedAt":779},"dispatching-coding-agents","dispatch stateless coding agents","Dispatch stateless coding agents (Claude Code or Codex) via Bash. Use when you're stuck, need a second opinion, or need parallel research on a hard problem. They have no memory — you must provide all context.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[774,775,776],{"name":18,"slug":19,"type":16},{"name":684,"slug":685,"type":16},{"name":777,"slug":778,"type":16},"Multi-Agent","multi-agent","2026-07-26T05:46:56.388845",{"slug":781,"name":781,"fn":782,"description":783,"org":784,"tags":785,"stars":23,"repoUrl":24,"updatedAt":795},"editing-letta-code-desktop-preferences","edit Letta Code Desktop preferences","Edits Letta Code Desktop (LCD) preferences by safely reading and updating ~\u002F.letta\u002Fdesktop_preferences.json. Use only when the user asks to change current Desktop\u002FLCD settings such as theme, default working directory, remote access preference, or remote environment name via the preferences JSON.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[786,789,792],{"name":787,"slug":788,"type":16},"Configuration","configuration",{"name":790,"slug":791,"type":16},"Desktop","desktop",{"name":793,"slug":794,"type":16},"Themes","themes","2026-07-13T06:23:41.407811",{"slug":797,"name":797,"fn":798,"description":799,"org":800,"tags":801,"stars":23,"repoUrl":24,"updatedAt":806},"finding-agents","locate and manage agents on server","Find other agents on the same server. Use when the user asks about other agents, wants to migrate memory from another agent, or needs to find an agent by name or tags.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[802,803],{"name":18,"slug":19,"type":16},{"name":804,"slug":805,"type":16},"Management","management","2026-07-16T06:02:17.297841",{"slug":808,"name":808,"fn":809,"description":810,"org":811,"tags":812,"stars":23,"repoUrl":24,"updatedAt":818},"generating-mod-envs","generate Letta mod learning environments","Generates and reviews mod learning env JSON files for Letta Code local mods. Use when asked to teach, learn, or optimize a mod behavior; create, draft, validate, improve, or explain envs for `\u002Fmods learn --env`; or design evaluation scenarios, memory fixtures, requiredResultMarkers, requiredTraceMarkers, negative controls, and candidate diversity hints.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[813,814,817],{"name":18,"slug":19,"type":16},{"name":815,"slug":816,"type":16},"AI Infrastructure","ai-infrastructure",{"name":787,"slug":788,"type":16},"2026-07-13T06:23:08.838181",{"slug":820,"name":820,"fn":821,"description":822,"org":823,"tags":824,"stars":23,"repoUrl":24,"updatedAt":833},"image-generation","generate images from text prompts","Generate images from text prompts (and optionally edit\u002Fremix input images). Use when the user asks to create, generate, draw, render, or edit an image, illustration, logo, icon, diagram, or photo.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[825,828,831],{"name":826,"slug":827,"type":16},"Creative","creative",{"name":829,"slug":830,"type":16},"Graphics","graphics",{"name":832,"slug":820,"type":16},"Image Generation","2026-07-13T06:23:06.189403",70]