[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-langchain-langsmith-code-eval":3,"mdc-jo0mi5-key":39,"related-repo-langchain-langsmith-code-eval":545,"related-org-langchain-langsmith-code-eval":571},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":29,"repoUrl":30,"updatedAt":31,"license":32,"forks":33,"topics":34,"repo":35,"sourceUrl":37,"mdContent":38},"langsmith-code-eval","create code-based evaluators for LangSmith","Creates code-based evaluators for LangSmith-traced agents. Use when building custom evaluation logic, testing tool usage patterns, or scoring agent outputs programmatically. Triggers on requests to evaluate agents, create evaluators, or run experiments against LangSmith datasets.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"langchain","LangChain","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Flangchain.png","langchain-ai",[13,17,20,23,26],{"name":14,"slug":15,"type":16},"Observability","observability","tag",{"name":18,"slug":19,"type":16},"LLM","llm",{"name":21,"slug":22,"type":16},"Evals","evals",{"name":24,"slug":25,"type":16},"LangSmith","langsmith",{"name":27,"slug":28,"type":16},"Testing","testing",2,"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flca-skills","2026-04-06T18:26:45.540902",null,1,[],{"repoUrl":30,"stars":29,"forks":33,"topics":36,"description":32},[],"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flca-skills\u002Ftree\u002FHEAD\u002Fskills\u002Flangsmith-code-eval","---\nname: langsmith-code-eval\ndescription: Creates code-based evaluators for LangSmith-traced agents. Use when building custom evaluation logic, testing tool usage patterns, or scoring agent outputs programmatically. Triggers on requests to evaluate agents, create evaluators, or run experiments against LangSmith datasets.\n---\n\n# LangSmith Code Evaluator Creation\n\nCreates evaluators for LangSmith experiments through structured inspection and implementation.\n\n## Prerequisites\n\n- `langsmith` Python package installed\n- `LANGSMITH_API_KEY` environment variable set (check project's `.env` file)\n\n## Workflow\n\nCopy this checklist and track progress:\n\n```\nEvaluator Creation Progress:\n- [ ] Step 1: Gather info from user\n- [ ] Step 2: Inspect trace and dataset structure\n- [ ] Step 3: Read agent code\n- [ ] Step 4: Write evaluator\n- [ ] Step 5: Write experiment runner\n- [ ] Step 6: Run and iterate\n```\n\n### Step 1: Gather Info from User\n\n**IMPORTANT: Do NOT search or explore the codebase. Ask the user all of these questions upfront using AskUserQuestion before doing anything else.**\n\nAsk the user the following in a single AskUserQuestion call:\n\n1. **Python command**: How do you run Python in this project? (e.g., `python`, `python3`, `uv run python`, `poetry run python`)\n2. **Agent file path**: What is the path to your agent file?\n3. **LangSmith project name**: What is your LangSmith project name (where traces are logged)?\n4. **LangSmith dataset name**: What is the name of the dataset to evaluate against?\n5. **Evaluation goal**: What behavior should pass vs fail? Common types:\n   - **Tool usage**: Did the agent call the correct tool?\n   - **Output correctness**: Does output match expected format\u002Fcontent?\n   - **Policy compliance**: Did it follow specific rules?\n   - **Classification**: Did it categorize correctly?\n\n### Step 2: Inspect Trace and Dataset Structure\n\nUsing the info from Step 1, run the inspection scripts located in this skill's directory:\n\n```bash\n{python_cmd} {skill_dir}\u002Fscripts\u002Finspect_trace.py PROJECT_NAME [RUN_ID]\n{python_cmd} {skill_dir}\u002Fscripts\u002Finspect_dataset.py DATASET_NAME\n```\n\nReplace `{python_cmd}` with the command from Step 1, and `{skill_dir}` with this skill's directory path.\n\n**Verify the trace matches the agent:**\n- Does the trace type match? (e.g., OpenAI trace for OpenAI agent)\n- Does it contain the data needed for evaluation?\n- If mismatched, clarify before proceeding.\n\n**From the dataset inspection, note:**\n- Input schema (what gets passed to the agent)\n- Output schema (reference\u002Fexpected outputs)\n- Metadata fields (e.g., `expected_tool`, `difficulty`, labels)\n\n**The dataset metadata often contains ground truth for evaluation** (e.g., which tool should be called, expected classification).\n\n### Step 3: Read Agent Code\n\nRead the agent file provided in Step 1 to identify:\n- Entry point function (look for `@traceable` decorator)\n- Available tools\n- Output format (what the function returns)\n\n### Step 4: Write the Evaluator\n\nCreate evaluator functions based on trace and dataset structure. See [EVALUATOR_REFERENCE.md](EVALUATOR_REFERENCE.md) for function signatures and return formats.\n\n### Step 5: Write Experiment Runner\n\nCreate a script that:\n1. Imports the agent's entry function\n2. Wraps it as a target function\n3. Runs `evaluate()` or `aevaluate()` against the dataset\n\nSee [EVALUATOR_REFERENCE.md](EVALUATOR_REFERENCE.md) for `evaluate()` usage.\n\n### Step 6: Run and Iterate\n\nExecute the experiment, review results in LangSmith, refine evaluators as needed.\n",{"data":40,"body":41},{"name":4,"description":6},{"type":42,"children":43},"root",[44,53,59,66,101,107,112,124,131,140,145,272,278,283,311,332,340,358,366,399,409,415,420,446,452,465,471,476,510,528,534,539],{"type":45,"tag":46,"props":47,"children":49},"element","h1",{"id":48},"langsmith-code-evaluator-creation",[50],{"type":51,"value":52},"text","LangSmith Code Evaluator Creation",{"type":45,"tag":54,"props":55,"children":56},"p",{},[57],{"type":51,"value":58},"Creates evaluators for LangSmith experiments through structured inspection and implementation.",{"type":45,"tag":60,"props":61,"children":63},"h2",{"id":62},"prerequisites",[64],{"type":51,"value":65},"Prerequisites",{"type":45,"tag":67,"props":68,"children":69},"ul",{},[70,82],{"type":45,"tag":71,"props":72,"children":73},"li",{},[74,80],{"type":45,"tag":75,"props":76,"children":78},"code",{"className":77},[],[79],{"type":51,"value":25},{"type":51,"value":81}," Python package installed",{"type":45,"tag":71,"props":83,"children":84},{},[85,91,93,99],{"type":45,"tag":75,"props":86,"children":88},{"className":87},[],[89],{"type":51,"value":90},"LANGSMITH_API_KEY",{"type":51,"value":92}," environment variable set (check project's ",{"type":45,"tag":75,"props":94,"children":96},{"className":95},[],[97],{"type":51,"value":98},".env",{"type":51,"value":100}," file)",{"type":45,"tag":60,"props":102,"children":104},{"id":103},"workflow",[105],{"type":51,"value":106},"Workflow",{"type":45,"tag":54,"props":108,"children":109},{},[110],{"type":51,"value":111},"Copy this checklist and track progress:",{"type":45,"tag":113,"props":114,"children":118},"pre",{"className":115,"code":117,"language":51},[116],"language-text","Evaluator Creation Progress:\n- [ ] Step 1: Gather info from user\n- [ ] Step 2: Inspect trace and dataset structure\n- [ ] Step 3: Read agent code\n- [ ] Step 4: Write evaluator\n- [ ] Step 5: Write experiment runner\n- [ ] Step 6: Run and iterate\n",[119],{"type":45,"tag":75,"props":120,"children":122},{"__ignoreMap":121},"",[123],{"type":51,"value":117},{"type":45,"tag":125,"props":126,"children":128},"h3",{"id":127},"step-1-gather-info-from-user",[129],{"type":51,"value":130},"Step 1: Gather Info from User",{"type":45,"tag":54,"props":132,"children":133},{},[134],{"type":45,"tag":135,"props":136,"children":137},"strong",{},[138],{"type":51,"value":139},"IMPORTANT: Do NOT search or explore the codebase. Ask the user all of these questions upfront using AskUserQuestion before doing anything else.",{"type":45,"tag":54,"props":141,"children":142},{},[143],{"type":51,"value":144},"Ask the user the following in a single AskUserQuestion call:",{"type":45,"tag":146,"props":147,"children":148},"ol",{},[149,189,199,209,219],{"type":45,"tag":71,"props":150,"children":151},{},[152,157,159,165,167,173,174,180,181,187],{"type":45,"tag":135,"props":153,"children":154},{},[155],{"type":51,"value":156},"Python command",{"type":51,"value":158},": How do you run Python in this project? (e.g., ",{"type":45,"tag":75,"props":160,"children":162},{"className":161},[],[163],{"type":51,"value":164},"python",{"type":51,"value":166},", ",{"type":45,"tag":75,"props":168,"children":170},{"className":169},[],[171],{"type":51,"value":172},"python3",{"type":51,"value":166},{"type":45,"tag":75,"props":175,"children":177},{"className":176},[],[178],{"type":51,"value":179},"uv run python",{"type":51,"value":166},{"type":45,"tag":75,"props":182,"children":184},{"className":183},[],[185],{"type":51,"value":186},"poetry run python",{"type":51,"value":188},")",{"type":45,"tag":71,"props":190,"children":191},{},[192,197],{"type":45,"tag":135,"props":193,"children":194},{},[195],{"type":51,"value":196},"Agent file path",{"type":51,"value":198},": What is the path to your agent file?",{"type":45,"tag":71,"props":200,"children":201},{},[202,207],{"type":45,"tag":135,"props":203,"children":204},{},[205],{"type":51,"value":206},"LangSmith project name",{"type":51,"value":208},": What is your LangSmith project name (where traces are logged)?",{"type":45,"tag":71,"props":210,"children":211},{},[212,217],{"type":45,"tag":135,"props":213,"children":214},{},[215],{"type":51,"value":216},"LangSmith dataset name",{"type":51,"value":218},": What is the name of the dataset to evaluate against?",{"type":45,"tag":71,"props":220,"children":221},{},[222,227,229],{"type":45,"tag":135,"props":223,"children":224},{},[225],{"type":51,"value":226},"Evaluation goal",{"type":51,"value":228},": What behavior should pass vs fail? Common types:\n",{"type":45,"tag":67,"props":230,"children":231},{},[232,242,252,262],{"type":45,"tag":71,"props":233,"children":234},{},[235,240],{"type":45,"tag":135,"props":236,"children":237},{},[238],{"type":51,"value":239},"Tool usage",{"type":51,"value":241},": Did the agent call the correct tool?",{"type":45,"tag":71,"props":243,"children":244},{},[245,250],{"type":45,"tag":135,"props":246,"children":247},{},[248],{"type":51,"value":249},"Output correctness",{"type":51,"value":251},": Does output match expected format\u002Fcontent?",{"type":45,"tag":71,"props":253,"children":254},{},[255,260],{"type":45,"tag":135,"props":256,"children":257},{},[258],{"type":51,"value":259},"Policy compliance",{"type":51,"value":261},": Did it follow specific rules?",{"type":45,"tag":71,"props":263,"children":264},{},[265,270],{"type":45,"tag":135,"props":266,"children":267},{},[268],{"type":51,"value":269},"Classification",{"type":51,"value":271},": Did it categorize correctly?",{"type":45,"tag":125,"props":273,"children":275},{"id":274},"step-2-inspect-trace-and-dataset-structure",[276],{"type":51,"value":277},"Step 2: Inspect Trace and Dataset Structure",{"type":45,"tag":54,"props":279,"children":280},{},[281],{"type":51,"value":282},"Using the info from Step 1, run the inspection scripts located in this skill's directory:",{"type":45,"tag":113,"props":284,"children":288},{"className":285,"code":286,"language":287,"meta":121,"style":121},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","{python_cmd} {skill_dir}\u002Fscripts\u002Finspect_trace.py PROJECT_NAME [RUN_ID]\n{python_cmd} {skill_dir}\u002Fscripts\u002Finspect_dataset.py DATASET_NAME\n","bash",[289],{"type":45,"tag":75,"props":290,"children":291},{"__ignoreMap":121},[292,303],{"type":45,"tag":293,"props":294,"children":296},"span",{"class":295,"line":33},"line",[297],{"type":45,"tag":293,"props":298,"children":300},{"style":299},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[301],{"type":51,"value":302},"{python_cmd} {skill_dir}\u002Fscripts\u002Finspect_trace.py PROJECT_NAME [RUN_ID]\n",{"type":45,"tag":293,"props":304,"children":305},{"class":295,"line":29},[306],{"type":45,"tag":293,"props":307,"children":308},{"style":299},[309],{"type":51,"value":310},"{python_cmd} {skill_dir}\u002Fscripts\u002Finspect_dataset.py DATASET_NAME\n",{"type":45,"tag":54,"props":312,"children":313},{},[314,316,322,324,330],{"type":51,"value":315},"Replace ",{"type":45,"tag":75,"props":317,"children":319},{"className":318},[],[320],{"type":51,"value":321},"{python_cmd}",{"type":51,"value":323}," with the command from Step 1, and ",{"type":45,"tag":75,"props":325,"children":327},{"className":326},[],[328],{"type":51,"value":329},"{skill_dir}",{"type":51,"value":331}," with this skill's directory path.",{"type":45,"tag":54,"props":333,"children":334},{},[335],{"type":45,"tag":135,"props":336,"children":337},{},[338],{"type":51,"value":339},"Verify the trace matches the agent:",{"type":45,"tag":67,"props":341,"children":342},{},[343,348,353],{"type":45,"tag":71,"props":344,"children":345},{},[346],{"type":51,"value":347},"Does the trace type match? (e.g., OpenAI trace for OpenAI agent)",{"type":45,"tag":71,"props":349,"children":350},{},[351],{"type":51,"value":352},"Does it contain the data needed for evaluation?",{"type":45,"tag":71,"props":354,"children":355},{},[356],{"type":51,"value":357},"If mismatched, clarify before proceeding.",{"type":45,"tag":54,"props":359,"children":360},{},[361],{"type":45,"tag":135,"props":362,"children":363},{},[364],{"type":51,"value":365},"From the dataset inspection, note:",{"type":45,"tag":67,"props":367,"children":368},{},[369,374,379],{"type":45,"tag":71,"props":370,"children":371},{},[372],{"type":51,"value":373},"Input schema (what gets passed to the agent)",{"type":45,"tag":71,"props":375,"children":376},{},[377],{"type":51,"value":378},"Output schema (reference\u002Fexpected outputs)",{"type":45,"tag":71,"props":380,"children":381},{},[382,384,390,391,397],{"type":51,"value":383},"Metadata fields (e.g., ",{"type":45,"tag":75,"props":385,"children":387},{"className":386},[],[388],{"type":51,"value":389},"expected_tool",{"type":51,"value":166},{"type":45,"tag":75,"props":392,"children":394},{"className":393},[],[395],{"type":51,"value":396},"difficulty",{"type":51,"value":398},", labels)",{"type":45,"tag":54,"props":400,"children":401},{},[402,407],{"type":45,"tag":135,"props":403,"children":404},{},[405],{"type":51,"value":406},"The dataset metadata often contains ground truth for evaluation",{"type":51,"value":408}," (e.g., which tool should be called, expected classification).",{"type":45,"tag":125,"props":410,"children":412},{"id":411},"step-3-read-agent-code",[413],{"type":51,"value":414},"Step 3: Read Agent Code",{"type":45,"tag":54,"props":416,"children":417},{},[418],{"type":51,"value":419},"Read the agent file provided in Step 1 to identify:",{"type":45,"tag":67,"props":421,"children":422},{},[423,436,441],{"type":45,"tag":71,"props":424,"children":425},{},[426,428,434],{"type":51,"value":427},"Entry point function (look for ",{"type":45,"tag":75,"props":429,"children":431},{"className":430},[],[432],{"type":51,"value":433},"@traceable",{"type":51,"value":435}," decorator)",{"type":45,"tag":71,"props":437,"children":438},{},[439],{"type":51,"value":440},"Available tools",{"type":45,"tag":71,"props":442,"children":443},{},[444],{"type":51,"value":445},"Output format (what the function returns)",{"type":45,"tag":125,"props":447,"children":449},{"id":448},"step-4-write-the-evaluator",[450],{"type":51,"value":451},"Step 4: Write the Evaluator",{"type":45,"tag":54,"props":453,"children":454},{},[455,457,463],{"type":51,"value":456},"Create evaluator functions based on trace and dataset structure. See ",{"type":45,"tag":458,"props":459,"children":461},"a",{"href":460},"EVALUATOR_REFERENCE.md",[462],{"type":51,"value":460},{"type":51,"value":464}," for function signatures and return formats.",{"type":45,"tag":125,"props":466,"children":468},{"id":467},"step-5-write-experiment-runner",[469],{"type":51,"value":470},"Step 5: Write Experiment Runner",{"type":45,"tag":54,"props":472,"children":473},{},[474],{"type":51,"value":475},"Create a script that:",{"type":45,"tag":146,"props":477,"children":478},{},[479,484,489],{"type":45,"tag":71,"props":480,"children":481},{},[482],{"type":51,"value":483},"Imports the agent's entry function",{"type":45,"tag":71,"props":485,"children":486},{},[487],{"type":51,"value":488},"Wraps it as a target function",{"type":45,"tag":71,"props":490,"children":491},{},[492,494,500,502,508],{"type":51,"value":493},"Runs ",{"type":45,"tag":75,"props":495,"children":497},{"className":496},[],[498],{"type":51,"value":499},"evaluate()",{"type":51,"value":501}," or ",{"type":45,"tag":75,"props":503,"children":505},{"className":504},[],[506],{"type":51,"value":507},"aevaluate()",{"type":51,"value":509}," against the dataset",{"type":45,"tag":54,"props":511,"children":512},{},[513,515,519,521,526],{"type":51,"value":514},"See ",{"type":45,"tag":458,"props":516,"children":517},{"href":460},[518],{"type":51,"value":460},{"type":51,"value":520}," for ",{"type":45,"tag":75,"props":522,"children":524},{"className":523},[],[525],{"type":51,"value":499},{"type":51,"value":527}," usage.",{"type":45,"tag":125,"props":529,"children":531},{"id":530},"step-6-run-and-iterate",[532],{"type":51,"value":533},"Step 6: Run and Iterate",{"type":45,"tag":54,"props":535,"children":536},{},[537],{"type":51,"value":538},"Execute the experiment, review results in LangSmith, refine evaluators as needed.",{"type":45,"tag":540,"props":541,"children":542},"style",{},[543],{"type":51,"value":544},"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":546,"total":29},[547,555],{"slug":4,"name":4,"fn":5,"description":6,"org":548,"tags":549,"stars":29,"repoUrl":30,"updatedAt":31},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[550,551,552,553,554],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":27,"slug":28,"type":16},{"slug":556,"name":556,"fn":557,"description":558,"org":559,"tags":560,"stars":29,"repoUrl":30,"updatedAt":570},"langsmith-fetch","fetch LangSmith traces for debugging","Fetches LangSmith traces for debugging agent behavior. Use when troubleshooting agent issues, reviewing conversation history, or investigating tool calls.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[561,564,565,566,567],{"name":562,"slug":563,"type":16},"Debugging","debugging",{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":568,"slug":569,"type":16},"Tracing","tracing","2026-04-06T18:26:44.25513",{"items":572,"total":749},[573,594,605,622,635,650,667,682,696,706,717,736],{"slug":574,"name":574,"fn":575,"description":576,"org":577,"tags":578,"stars":591,"repoUrl":592,"updatedAt":593},"analyze-market","perform market analysis and size estimation","Perform a market analysis for a product category or segment. Trigger on: market analysis, market size, TAM SAM SOM, market opportunity, industry analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[579,582,585,588],{"name":580,"slug":581,"type":16},"Marketing","marketing",{"name":583,"slug":584,"type":16},"Research","research",{"name":586,"slug":587,"type":16},"Sales","sales",{"name":589,"slug":590,"type":16},"Strategy","strategy",26592,"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Fdeepagents","2026-04-18T04:46:54.557115",{"slug":595,"name":595,"fn":596,"description":597,"org":598,"tags":599,"stars":591,"repoUrl":592,"updatedAt":604},"arxiv-search","search arXiv for academic research papers","Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look up preprints, find academic articles in physics, math, CS, biology, statistics, or related fields.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[600,601],{"name":583,"slug":584,"type":16},{"name":602,"slug":603,"type":16},"Search","search","2026-05-13T06:11:01.203061",{"slug":606,"name":606,"fn":607,"description":608,"org":609,"tags":610,"stars":591,"repoUrl":592,"updatedAt":621},"blog-post","write SEO-optimized blog posts","Write long-form blog posts with SEO optimization and clear structure.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[611,614,615,618],{"name":612,"slug":613,"type":16},"Content Creation","content-creation",{"name":580,"slug":581,"type":16},{"name":616,"slug":617,"type":16},"SEO","seo",{"name":619,"slug":620,"type":16},"Writing","writing","2026-04-15T05:00:54.149813",{"slug":623,"name":623,"fn":624,"description":625,"org":626,"tags":627,"stars":591,"repoUrl":592,"updatedAt":634},"competitor-analysis","analyze competitors and market positioning","Analyze competitors in a given market segment. Trigger on: competitive landscape, competitor analysis, market comparison, competitive positioning.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[628,631,632,633],{"name":629,"slug":630,"type":16},"Competitive Intelligence","competitive-intelligence",{"name":580,"slug":581,"type":16},{"name":583,"slug":584,"type":16},{"name":589,"slug":590,"type":16},"2026-04-18T04:46:55.79306",{"slug":636,"name":636,"fn":637,"description":638,"org":639,"tags":640,"stars":591,"repoUrl":592,"updatedAt":649},"deepagents-thread-inspector","inspect local Deep Agents conversation threads","Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse ~\u002F.deepagents\u002F.state\u002Fsessions.db and a thread UUID or prefix.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[641,644,645,646],{"name":642,"slug":643,"type":16},"Agents","agents",{"name":562,"slug":563,"type":16},{"name":9,"slug":8,"type":16},{"name":647,"slug":648,"type":16},"SQLite","sqlite","2026-07-24T06:08:57.102689",{"slug":651,"name":651,"fn":652,"description":653,"org":654,"tags":655,"stars":591,"repoUrl":592,"updatedAt":666},"langgraph-docs","build stateful agents with LangGraph","Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[656,657,660,663],{"name":642,"slug":643,"type":16},{"name":658,"slug":659,"type":16},"Documentation","documentation",{"name":661,"slug":662,"type":16},"LangGraph","langgraph",{"name":664,"slug":665,"type":16},"Multi-Agent","multi-agent","2026-05-13T06:11:03.650877",{"slug":668,"name":668,"fn":669,"description":670,"org":671,"tags":672,"stars":591,"repoUrl":592,"updatedAt":681},"remember","capture knowledge into persistent memory","Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[673,674,675,678],{"name":642,"slug":643,"type":16},{"name":658,"slug":659,"type":16},{"name":676,"slug":677,"type":16},"Knowledge Management","knowledge-management",{"name":679,"slug":680,"type":16},"Memory","memory","2026-05-13T06:10:58.510037",{"slug":683,"name":683,"fn":684,"description":685,"org":686,"tags":687,"stars":591,"repoUrl":592,"updatedAt":695},"skill-creator","create agent skills and tool integrations","Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like \"create a skill\", \"new skill\", \"make a skill\", \"skill for X\", \"how do I create a skill\", or \"help me build a skill\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[688,689,692],{"name":642,"slug":643,"type":16},{"name":690,"slug":691,"type":16},"Engineering","engineering",{"name":693,"slug":694,"type":16},"Plugin Development","plugin-development","2026-05-13T06:10:59.88449",{"slug":697,"name":697,"fn":698,"description":699,"org":700,"tags":701,"stars":591,"repoUrl":592,"updatedAt":705},"social-media","create optimized social media posts","Create social media posts optimized for engagement across platforms.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[702,703,704],{"name":612,"slug":613,"type":16},{"name":580,"slug":581,"type":16},{"name":619,"slug":620,"type":16},"2026-04-15T05:00:55.37452",{"slug":707,"name":707,"fn":708,"description":709,"org":710,"tags":711,"stars":591,"repoUrl":592,"updatedAt":716},"web-research","conduct and synthesize web research","Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[712,713,714,715],{"name":642,"slug":643,"type":16},{"name":664,"slug":665,"type":16},{"name":583,"slug":584,"type":16},{"name":602,"slug":603,"type":16},"2026-05-13T06:11:04.930044",{"slug":718,"name":718,"fn":719,"description":720,"org":721,"tags":722,"stars":733,"repoUrl":734,"updatedAt":735},"mermaid-diagrams","embed Mermaid diagrams in documentation","Embed Mermaid diagrams in generated wiki pages. Use whenever documenting a runtime or request flow, a call sequence, a state machine or lifecycle, a data model or entity relationships, or non-trivial control flow, since these are clearer as a diagram than as prose. Also use when an update run touches a page that already contains a mermaid fence, or a page that contains a text fence a previous run degraded.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[723,726,727,730],{"name":724,"slug":725,"type":16},"Diagrams","diagrams",{"name":658,"slug":659,"type":16},{"name":728,"slug":729,"type":16},"Markdown","markdown",{"name":731,"slug":732,"type":16},"Technical Writing","technical-writing",12181,"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Fopenwiki","2026-07-24T06:09:01.089597",{"slug":737,"name":737,"fn":738,"description":739,"org":740,"tags":741,"stars":733,"repoUrl":734,"updatedAt":748},"write-connector","implement OpenWiki source connectors","Add a new built-in OpenWiki source connector. Use when a user asks to create or implement an OpenWiki connector.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[742,745],{"name":743,"slug":744,"type":16},"API Development","api-development",{"name":746,"slug":747,"type":16},"Integrations","integrations","2026-07-18T05:48:23.961804",41]