[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-letta-transcribe":3,"mdc--u9a8ci-key":34,"related-repo-letta-transcribe":467,"related-org-letta-transcribe":587},{"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":29,"sourceUrl":32,"mdContent":33},"transcribe","transcribe audio files to text","Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio\u002Fvideo, extract text from recordings, or label speakers in interviews or meetings.",{"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},"Transcription","transcription","tag",{"name":18,"slug":19,"type":16},"Audio","audio",{"name":21,"slug":22,"type":16},"Speech","speech",127,"https:\u002F\u002Fgithub.com\u002Fletta-ai\u002Fskills","2026-07-13T06:24:49.433116",null,20,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"A shared repository for skills. Intended to be used with Letta Code, Claude Code, Codex CLI, and other agents that support skills.","https:\u002F\u002Fgithub.com\u002Fletta-ai\u002Fskills\u002Ftree\u002FHEAD\u002Ftools\u002Ftranscribe","---\nname: \"transcribe\"\ndescription: \"Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio\u002Fvideo, extract text from recordings, or label speakers in interviews or meetings.\"\n---\n\n\n# Audio Transcribe\n\nTranscribe audio using OpenAI, with optional speaker diarization when requested. Prefer the bundled CLI for deterministic, repeatable runs.\n\n## Workflow\n1. Collect inputs: audio file path(s), desired response format (text\u002Fjson\u002Fdiarized_json), optional language hint, and any known speaker references.\n2. Verify `OPENAI_API_KEY` is set. If missing, ask the user to set it locally (do not ask them to paste the key).\n3. Run the bundled `transcribe_diarize.py` CLI with sensible defaults (fast text transcription).\n4. Validate the output: transcription quality, speaker labels, and segment boundaries; iterate with a single targeted change if needed.\n5. Save outputs under `output\u002Ftranscribe\u002F` when working in this repo.\n\n## Decision rules\n- Default to `gpt-4o-mini-transcribe` with `--response-format text` for fast transcription.\n- If the user wants speaker labels or diarization, use `--model gpt-4o-transcribe-diarize --response-format diarized_json`.\n- If audio is longer than ~30 seconds, keep `--chunking-strategy auto`.\n- Prompting is not supported for `gpt-4o-transcribe-diarize`.\n\n## Output conventions\n- Use `output\u002Ftranscribe\u002F\u003Cjob-id>\u002F` for evaluation runs.\n- Use `--out-dir` for multiple files to avoid overwriting.\n\n## Dependencies (install if missing)\nPrefer `uv` for dependency management.\n\n```\nuv pip install openai\n```\nIf `uv` is unavailable:\n```\npython3 -m pip install openai\n```\n\n## Environment\n- `OPENAI_API_KEY` must be set for live API calls.\n- If the key is missing, instruct the user to create one in the OpenAI platform UI and export it in their shell.\n- Never ask the user to paste the full key in chat.\n\n## Skill path (set once)\n\n```bash\n# Set to the directory containing this SKILL.md\nexport TRANSCRIBE_CLI=\"\u003Cpath-to-skill>\u002Fscripts\u002Ftranscribe_diarize.py\"\n```\n\nReplace `\u003Cpath-to-skill>` with the actual skill installation directory (e.g. `.skills\u002Ftranscribe` or `~\u002F.letta\u002Fskills\u002Ftranscribe`).\n\n## CLI quick start\nSingle file (fast text default):\n```\npython3 \"$TRANSCRIBE_CLI\" \\\n  path\u002Fto\u002Faudio.wav \\\n  --out transcript.txt\n```\n\nDiarization with known speakers (up to 4):\n```\npython3 \"$TRANSCRIBE_CLI\" \\\n  meeting.m4a \\\n  --model gpt-4o-transcribe-diarize \\\n  --known-speaker \"Alice=refs\u002Falice.wav\" \\\n  --known-speaker \"Bob=refs\u002Fbob.wav\" \\\n  --response-format diarized_json \\\n  --out-dir output\u002Ftranscribe\u002Fmeeting\n```\n\nPlain text output (explicit):\n```\npython3 \"$TRANSCRIBE_CLI\" \\\n  interview.mp3 \\\n  --response-format text \\\n  --out interview.txt\n```\n\n## Reference map\n- `references\u002Fapi.md`: supported formats, limits, response formats, and known-speaker notes.\n",{"data":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,48,54,61,116,122,184,190,218,224,237,249,261,270,276,299,305,364,393,399,404,413,418,427,432,441,447,461],{"type":40,"tag":41,"props":42,"children":44},"element","h1",{"id":43},"audio-transcribe",[45],{"type":46,"value":47},"text","Audio Transcribe",{"type":40,"tag":49,"props":50,"children":51},"p",{},[52],{"type":46,"value":53},"Transcribe audio using OpenAI, with optional speaker diarization when requested. Prefer the bundled CLI for deterministic, repeatable runs.",{"type":40,"tag":55,"props":56,"children":58},"h2",{"id":57},"workflow",[59],{"type":46,"value":60},"Workflow",{"type":40,"tag":62,"props":63,"children":64},"ol",{},[65,71,85,98,103],{"type":40,"tag":66,"props":67,"children":68},"li",{},[69],{"type":46,"value":70},"Collect inputs: audio file path(s), desired response format (text\u002Fjson\u002Fdiarized_json), optional language hint, and any known speaker references.",{"type":40,"tag":66,"props":72,"children":73},{},[74,76,83],{"type":46,"value":75},"Verify ",{"type":40,"tag":77,"props":78,"children":80},"code",{"className":79},[],[81],{"type":46,"value":82},"OPENAI_API_KEY",{"type":46,"value":84}," is set. If missing, ask the user to set it locally (do not ask them to paste the key).",{"type":40,"tag":66,"props":86,"children":87},{},[88,90,96],{"type":46,"value":89},"Run the bundled ",{"type":40,"tag":77,"props":91,"children":93},{"className":92},[],[94],{"type":46,"value":95},"transcribe_diarize.py",{"type":46,"value":97}," CLI with sensible defaults (fast text transcription).",{"type":40,"tag":66,"props":99,"children":100},{},[101],{"type":46,"value":102},"Validate the output: transcription quality, speaker labels, and segment boundaries; iterate with a single targeted change if needed.",{"type":40,"tag":66,"props":104,"children":105},{},[106,108,114],{"type":46,"value":107},"Save outputs under ",{"type":40,"tag":77,"props":109,"children":111},{"className":110},[],[112],{"type":46,"value":113},"output\u002Ftranscribe\u002F",{"type":46,"value":115}," when working in this repo.",{"type":40,"tag":55,"props":117,"children":119},{"id":118},"decision-rules",[120],{"type":46,"value":121},"Decision rules",{"type":40,"tag":123,"props":124,"children":125},"ul",{},[126,147,160,172],{"type":40,"tag":66,"props":127,"children":128},{},[129,131,137,139,145],{"type":46,"value":130},"Default to ",{"type":40,"tag":77,"props":132,"children":134},{"className":133},[],[135],{"type":46,"value":136},"gpt-4o-mini-transcribe",{"type":46,"value":138}," with ",{"type":40,"tag":77,"props":140,"children":142},{"className":141},[],[143],{"type":46,"value":144},"--response-format text",{"type":46,"value":146}," for fast transcription.",{"type":40,"tag":66,"props":148,"children":149},{},[150,152,158],{"type":46,"value":151},"If the user wants speaker labels or diarization, use ",{"type":40,"tag":77,"props":153,"children":155},{"className":154},[],[156],{"type":46,"value":157},"--model gpt-4o-transcribe-diarize --response-format diarized_json",{"type":46,"value":159},".",{"type":40,"tag":66,"props":161,"children":162},{},[163,165,171],{"type":46,"value":164},"If audio is longer than ~30 seconds, keep ",{"type":40,"tag":77,"props":166,"children":168},{"className":167},[],[169],{"type":46,"value":170},"--chunking-strategy auto",{"type":46,"value":159},{"type":40,"tag":66,"props":173,"children":174},{},[175,177,183],{"type":46,"value":176},"Prompting is not supported for ",{"type":40,"tag":77,"props":178,"children":180},{"className":179},[],[181],{"type":46,"value":182},"gpt-4o-transcribe-diarize",{"type":46,"value":159},{"type":40,"tag":55,"props":185,"children":187},{"id":186},"output-conventions",[188],{"type":46,"value":189},"Output conventions",{"type":40,"tag":123,"props":191,"children":192},{},[193,206],{"type":40,"tag":66,"props":194,"children":195},{},[196,198,204],{"type":46,"value":197},"Use ",{"type":40,"tag":77,"props":199,"children":201},{"className":200},[],[202],{"type":46,"value":203},"output\u002Ftranscribe\u002F\u003Cjob-id>\u002F",{"type":46,"value":205}," for evaluation runs.",{"type":40,"tag":66,"props":207,"children":208},{},[209,210,216],{"type":46,"value":197},{"type":40,"tag":77,"props":211,"children":213},{"className":212},[],[214],{"type":46,"value":215},"--out-dir",{"type":46,"value":217}," for multiple files to avoid overwriting.",{"type":40,"tag":55,"props":219,"children":221},{"id":220},"dependencies-install-if-missing",[222],{"type":46,"value":223},"Dependencies (install if missing)",{"type":40,"tag":49,"props":225,"children":226},{},[227,229,235],{"type":46,"value":228},"Prefer ",{"type":40,"tag":77,"props":230,"children":232},{"className":231},[],[233],{"type":46,"value":234},"uv",{"type":46,"value":236}," for dependency management.",{"type":40,"tag":238,"props":239,"children":243},"pre",{"className":240,"code":242,"language":46},[241],"language-text","uv pip install openai\n",[244],{"type":40,"tag":77,"props":245,"children":247},{"__ignoreMap":246},"",[248],{"type":46,"value":242},{"type":40,"tag":49,"props":250,"children":251},{},[252,254,259],{"type":46,"value":253},"If ",{"type":40,"tag":77,"props":255,"children":257},{"className":256},[],[258],{"type":46,"value":234},{"type":46,"value":260}," is unavailable:",{"type":40,"tag":238,"props":262,"children":265},{"className":263,"code":264,"language":46},[241],"python3 -m pip install openai\n",[266],{"type":40,"tag":77,"props":267,"children":268},{"__ignoreMap":246},[269],{"type":46,"value":264},{"type":40,"tag":55,"props":271,"children":273},{"id":272},"environment",[274],{"type":46,"value":275},"Environment",{"type":40,"tag":123,"props":277,"children":278},{},[279,289,294],{"type":40,"tag":66,"props":280,"children":281},{},[282,287],{"type":40,"tag":77,"props":283,"children":285},{"className":284},[],[286],{"type":46,"value":82},{"type":46,"value":288}," must be set for live API calls.",{"type":40,"tag":66,"props":290,"children":291},{},[292],{"type":46,"value":293},"If the key is missing, instruct the user to create one in the OpenAI platform UI and export it in their shell.",{"type":40,"tag":66,"props":295,"children":296},{},[297],{"type":46,"value":298},"Never ask the user to paste the full key in chat.",{"type":40,"tag":55,"props":300,"children":302},{"id":301},"skill-path-set-once",[303],{"type":46,"value":304},"Skill path (set once)",{"type":40,"tag":238,"props":306,"children":310},{"className":307,"code":308,"language":309,"meta":246,"style":246},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Set to the directory containing this SKILL.md\nexport TRANSCRIBE_CLI=\"\u003Cpath-to-skill>\u002Fscripts\u002Ftranscribe_diarize.py\"\n","bash",[311],{"type":40,"tag":77,"props":312,"children":313},{"__ignoreMap":246},[314,326],{"type":40,"tag":315,"props":316,"children":319},"span",{"class":317,"line":318},"line",1,[320],{"type":40,"tag":315,"props":321,"children":323},{"style":322},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[324],{"type":46,"value":325},"# Set to the directory containing this SKILL.md\n",{"type":40,"tag":315,"props":327,"children":329},{"class":317,"line":328},2,[330,336,342,348,353,359],{"type":40,"tag":315,"props":331,"children":333},{"style":332},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[334],{"type":46,"value":335},"export",{"type":40,"tag":315,"props":337,"children":339},{"style":338},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[340],{"type":46,"value":341}," TRANSCRIBE_CLI",{"type":40,"tag":315,"props":343,"children":345},{"style":344},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[346],{"type":46,"value":347},"=",{"type":40,"tag":315,"props":349,"children":350},{"style":344},[351],{"type":46,"value":352},"\"",{"type":40,"tag":315,"props":354,"children":356},{"style":355},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[357],{"type":46,"value":358},"\u003Cpath-to-skill>\u002Fscripts\u002Ftranscribe_diarize.py",{"type":40,"tag":315,"props":360,"children":361},{"style":344},[362],{"type":46,"value":363},"\"\n",{"type":40,"tag":49,"props":365,"children":366},{},[367,369,375,377,383,385,391],{"type":46,"value":368},"Replace ",{"type":40,"tag":77,"props":370,"children":372},{"className":371},[],[373],{"type":46,"value":374},"\u003Cpath-to-skill>",{"type":46,"value":376}," with the actual skill installation directory (e.g. ",{"type":40,"tag":77,"props":378,"children":380},{"className":379},[],[381],{"type":46,"value":382},".skills\u002Ftranscribe",{"type":46,"value":384}," or ",{"type":40,"tag":77,"props":386,"children":388},{"className":387},[],[389],{"type":46,"value":390},"~\u002F.letta\u002Fskills\u002Ftranscribe",{"type":46,"value":392},").",{"type":40,"tag":55,"props":394,"children":396},{"id":395},"cli-quick-start",[397],{"type":46,"value":398},"CLI quick start",{"type":40,"tag":49,"props":400,"children":401},{},[402],{"type":46,"value":403},"Single file (fast text default):",{"type":40,"tag":238,"props":405,"children":408},{"className":406,"code":407,"language":46},[241],"python3 \"$TRANSCRIBE_CLI\" \\\n  path\u002Fto\u002Faudio.wav \\\n  --out transcript.txt\n",[409],{"type":40,"tag":77,"props":410,"children":411},{"__ignoreMap":246},[412],{"type":46,"value":407},{"type":40,"tag":49,"props":414,"children":415},{},[416],{"type":46,"value":417},"Diarization with known speakers (up to 4):",{"type":40,"tag":238,"props":419,"children":422},{"className":420,"code":421,"language":46},[241],"python3 \"$TRANSCRIBE_CLI\" \\\n  meeting.m4a \\\n  --model gpt-4o-transcribe-diarize \\\n  --known-speaker \"Alice=refs\u002Falice.wav\" \\\n  --known-speaker \"Bob=refs\u002Fbob.wav\" \\\n  --response-format diarized_json \\\n  --out-dir output\u002Ftranscribe\u002Fmeeting\n",[423],{"type":40,"tag":77,"props":424,"children":425},{"__ignoreMap":246},[426],{"type":46,"value":421},{"type":40,"tag":49,"props":428,"children":429},{},[430],{"type":46,"value":431},"Plain text output (explicit):",{"type":40,"tag":238,"props":433,"children":436},{"className":434,"code":435,"language":46},[241],"python3 \"$TRANSCRIBE_CLI\" \\\n  interview.mp3 \\\n  --response-format text \\\n  --out interview.txt\n",[437],{"type":40,"tag":77,"props":438,"children":439},{"__ignoreMap":246},[440],{"type":46,"value":435},{"type":40,"tag":55,"props":442,"children":444},{"id":443},"reference-map",[445],{"type":46,"value":446},"Reference map",{"type":40,"tag":123,"props":448,"children":449},{},[450],{"type":40,"tag":66,"props":451,"children":452},{},[453,459],{"type":40,"tag":77,"props":454,"children":456},{"className":455},[],[457],{"type":46,"value":458},"references\u002Fapi.md",{"type":46,"value":460},": supported formats, limits, response formats, and known-speaker notes.",{"type":40,"tag":462,"props":463,"children":464},"style",{},[465],{"type":46,"value":466},"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":468,"total":586},[469,485,502,521,536,557,567],{"slug":470,"name":470,"fn":471,"description":472,"org":473,"tags":474,"stars":23,"repoUrl":24,"updatedAt":484},"1password","manage secrets with 1Password CLI","Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading\u002Finjecting\u002Frunning secrets via op.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[475,478,481],{"name":476,"slug":477,"type":16},"Authentication","authentication",{"name":479,"slug":480,"type":16},"CLI","cli",{"name":482,"slug":483,"type":16},"Security","security","2026-07-13T06:24:39.504387",{"slug":486,"name":486,"fn":487,"description":488,"org":489,"tags":490,"stars":23,"repoUrl":24,"updatedAt":501},"agent-slack","automate Slack messaging and workflows","Slack automation CLI — read\u002Fsend\u002Fsearch messages, browse threads and channels, manage channels, download attachments, look up users, and run workflows.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[491,494,495,498],{"name":492,"slug":493,"type":16},"Automation","automation",{"name":479,"slug":480,"type":16},{"name":496,"slug":497,"type":16},"Messaging","messaging",{"name":499,"slug":500,"type":16},"Slack","slack","2026-07-13T06:23:51.908511",{"slug":503,"name":503,"fn":504,"description":505,"org":506,"tags":507,"stars":23,"repoUrl":24,"updatedAt":520},"ai-news","fetch and summarize AI news","Fetch and summarize recent AI news from curated RSS feeds (Hugging Face, VentureBeat, The Verge, OpenAI, Anthropic, DeepMind, etc.) and YouTube channels (Yannic Kilcher, Two Minute Papers, AI Explained, etc.). Also fetches full transcripts for specific YouTube videos. Use when the user asks about recent AI news, what's happened in AI lately, summaries of AI research or product announcements, or wants a digest of what's going on in the AI space.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[508,511,514,517],{"name":509,"slug":510,"type":16},"Communications","communications",{"name":512,"slug":513,"type":16},"LLM","llm",{"name":515,"slug":516,"type":16},"Research","research",{"name":518,"slug":519,"type":16},"Summarization","summarization","2026-07-13T06:24:20.520223",{"slug":522,"name":522,"fn":523,"description":524,"org":525,"tags":526,"stars":23,"repoUrl":24,"updatedAt":535},"creating-letta-code-channels","build and debug Letta Code channels","Builds and debugs Letta Code channels, including first-party channel adapters and dynamic user channel plugins under ~\u002F.letta\u002Fchannels. Use when adding Telegram, WhatsApp, Bluesky, Slack, Discord, or custom channel support; testing channel routing, pairing, MessageChannel, runtime dependencies, or channel plugin manifests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[527,530,533,534],{"name":528,"slug":529,"type":16},"Agents","agents",{"name":531,"slug":532,"type":16},"API Development","api-development",{"name":496,"slug":497,"type":16},{"name":499,"slug":500,"type":16},"2026-07-13T06:25:55.843495",{"slug":537,"name":537,"fn":538,"description":539,"org":540,"tags":541,"stars":23,"repoUrl":24,"updatedAt":556},"datadog","query Datadog observability data","Query Datadog observability data (logs, metrics, monitors, dashboards, hosts) via direct API. Use when investigating production issues, checking monitors, searching logs, or accessing Datadog data.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[542,544,547,550,553],{"name":543,"slug":537,"type":16},"Datadog",{"name":545,"slug":546,"type":16},"Logs","logs",{"name":548,"slug":549,"type":16},"Metrics","metrics",{"name":551,"slug":552,"type":16},"Monitoring","monitoring",{"name":554,"slug":555,"type":16},"Observability","observability","2026-07-13T06:24:27.990605",{"slug":558,"name":558,"fn":559,"description":560,"org":561,"tags":562,"stars":23,"repoUrl":24,"updatedAt":566},"discord","automate Discord server and channel tasks","Discord automation CLI — send\u002Fread\u002Fsearch messages, manage channels and servers, react, create threads, pin messages, and look up users.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[563,564,565],{"name":492,"slug":493,"type":16},{"name":479,"slug":480,"type":16},{"name":496,"slug":497,"type":16},"2026-07-13T06:24:26.62387",{"slug":568,"name":568,"fn":569,"description":570,"org":571,"tags":572,"stars":23,"repoUrl":24,"updatedAt":585},"doc","create and edit Word documents","Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts\u002Frender_docx.py` for visual checks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[573,576,579,582],{"name":574,"slug":575,"type":16},"Documents","documents",{"name":577,"slug":578,"type":16},"DOCX","docx",{"name":580,"slug":581,"type":16},"Office","office",{"name":583,"slug":584,"type":16},"Word","word","2026-07-13T06:23:44.299568",45,{"items":588,"total":743},[589,603,618,630,642,656,666,677,689,705,716,728],{"slug":590,"name":590,"fn":591,"description":592,"org":593,"tags":594,"stars":600,"repoUrl":601,"updatedAt":602},"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},[595,596,597],{"name":528,"slug":529,"type":16},{"name":492,"slug":493,"type":16},{"name":598,"slug":599,"type":16},"GitHub","github",2831,"https:\u002F\u002Fgithub.com\u002Fletta-ai\u002Fletta-code","2026-07-13T06:22:58.45767",{"slug":604,"name":605,"fn":606,"description":607,"org":608,"tags":609,"stars":600,"repoUrl":601,"updatedAt":617},"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},[610,611,614],{"name":528,"slug":529,"type":16},{"name":612,"slug":613,"type":16},"AI Context","ai-context",{"name":615,"slug":616,"type":16},"Debugging","debugging","2026-07-13T06:22:50.151002",{"slug":619,"name":619,"fn":620,"description":621,"org":622,"tags":623,"stars":600,"repoUrl":601,"updatedAt":629},"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},[624,625,626],{"name":528,"slug":529,"type":16},{"name":492,"slug":493,"type":16},{"name":627,"slug":628,"type":16},"MCP","mcp","2026-07-13T06:23:37.646079",{"slug":631,"name":631,"fn":632,"description":633,"org":634,"tags":635,"stars":600,"repoUrl":601,"updatedAt":641},"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},[636,637,638],{"name":528,"slug":529,"type":16},{"name":492,"slug":493,"type":16},{"name":639,"slug":640,"type":16},"Coding","coding","2026-07-23T05:42:38.133565",{"slug":643,"name":643,"fn":644,"description":645,"org":646,"tags":647,"stars":600,"repoUrl":601,"updatedAt":655},"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},[648,649,652],{"name":528,"slug":529,"type":16},{"name":650,"slug":651,"type":16},"Documentation","documentation",{"name":653,"slug":654,"type":16},"Plugin Development","plugin-development","2026-07-13T06:22:56.998659",{"slug":657,"name":657,"fn":658,"description":659,"org":660,"tags":661,"stars":600,"repoUrl":601,"updatedAt":665},"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},[662,663,664],{"name":528,"slug":529,"type":16},{"name":492,"slug":493,"type":16},{"name":479,"slug":480,"type":16},"2026-07-13T06:23:18.266798",{"slug":667,"name":667,"fn":668,"description":669,"org":670,"tags":671,"stars":600,"repoUrl":601,"updatedAt":676},"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},[672,673],{"name":479,"slug":480,"type":16},{"name":674,"slug":675,"type":16},"Engineering","engineering","2026-07-13T06:23:27.465985",{"slug":678,"name":678,"fn":679,"description":680,"org":681,"tags":682,"stars":600,"repoUrl":601,"updatedAt":688},"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},[683,684,685],{"name":528,"slug":529,"type":16},{"name":639,"slug":640,"type":16},{"name":686,"slug":687,"type":16},"Multi-Agent","multi-agent","2026-07-26T05:46:56.388845",{"slug":690,"name":690,"fn":691,"description":692,"org":693,"tags":694,"stars":600,"repoUrl":601,"updatedAt":704},"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},[695,698,701],{"name":696,"slug":697,"type":16},"Configuration","configuration",{"name":699,"slug":700,"type":16},"Desktop","desktop",{"name":702,"slug":703,"type":16},"Themes","themes","2026-07-13T06:23:41.407811",{"slug":706,"name":706,"fn":707,"description":708,"org":709,"tags":710,"stars":600,"repoUrl":601,"updatedAt":715},"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},[711,712],{"name":528,"slug":529,"type":16},{"name":713,"slug":714,"type":16},"Management","management","2026-07-16T06:02:17.297841",{"slug":717,"name":717,"fn":718,"description":719,"org":720,"tags":721,"stars":600,"repoUrl":601,"updatedAt":727},"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},[722,723,726],{"name":528,"slug":529,"type":16},{"name":724,"slug":725,"type":16},"AI Infrastructure","ai-infrastructure",{"name":696,"slug":697,"type":16},"2026-07-13T06:23:08.838181",{"slug":729,"name":729,"fn":730,"description":731,"org":732,"tags":733,"stars":600,"repoUrl":601,"updatedAt":742},"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},[734,737,740],{"name":735,"slug":736,"type":16},"Creative","creative",{"name":738,"slug":739,"type":16},"Graphics","graphics",{"name":741,"slug":729,"type":16},"Image Generation","2026-07-13T06:23:06.189403",69]