[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75H52MAVC5YPAFES844YEC9":3,"skill-same:01M75H52MAVC5YPAFES844YEC9":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M75H52MAVC5YPAFES844YEC9","crewai",null,"Role-based multi-agent orchestration framework for building \"Crews\" of collaborating LLM agents (each with a role, goal, backstory, and optional tools) that execute sequential or hierarchical task pipelines, plus event-driven \"Flows\" for precise, single-LLM-call orchestration. Use when composing specialized agents (e.g. a research agent + an analysis agent + a writer agent) into a declarative pipeline for complex multi-step tasks like automated literature review or multi-agent research workflows. Distinct from LangGraph's explicit state-machine graphs and smolagents' minimal tool-calling loop — CrewAI is standalone (no LangChain dependency) and expresses orchestration as roles and delegated tasks rather than a graph or a single ReAct loop.","stanfish06\u002Fskillquarium","stanfish06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F93099613?v=4","01M75F1CK4ZW109ZK3T26VN52F","Zhiyuan","01M75F1CM53VH6F79DZ8GXKKES",12,"MIT","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fcrewai\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: crewai\ndescription: Role-based multi-agent orchestration framework for building \"Crews\" of collaborating LLM agents (each with a role, goal, backstory, and optional tools) that execute sequential or hierarchical task pipelines, plus event-driven \"Flows\" for precise, single-LLM-call orchestration. Use when composing specialized agents (e.g. a research agent + an analysis agent + a writer agent) into a declarative pipeline for complex multi-step tasks like automated literature review or multi-agent research workflows. Distinct from LangGraph's explicit state-machine graphs and smolagents' minimal tool-calling loop — CrewAI is standalone (no LangChain dependency) and expresses orchestration as roles and delegated tasks rather than a graph or a single ReAct loop.\nlicense: MIT\nallowed-tools:\n  - Read\n  - Write\n  - Edit\n  - Bash\ncompatibility: Requires Python >=3.10,\u003C3.14 and crewai 1.x. Routes most LLM providers through LiteLLM by default, so provider extras (crewai[anthropic], crewai[aws]\u002F[bedrock], crewai[azure-ai-inference], crewai[google-genai]) are usually optional; install crewai[tools] to pull in the separate crewai-tools package of prebuilt tools (web search, file readers, code execution, etc.).\nmetadata: {\"version\": \"1.0\", \"skill-author\": \"community\"}\n---\n\n# CrewAI\n\n## Overview\n\nCrewAI is a Python framework, built from scratch independent of LangChain, for orchestrating teams of LLM agents. It has two complementary orchestration models:\n\n- **Crews** — role-based, autonomous collaboration. You define `Agent`s (each with a `role`, `goal`, `backstory`, and optional `tools`\u002F`llm`) and `Task`s (each with a `description`, `expected_output`, and an assigned `agent`), then wire them into a `Crew` that runs tasks either `Process.sequential` (task N's output feeds task N+1) or `Process.hierarchical` (a manager agent dynamically delegates tasks to the crew).\n- **Flows** — event-driven, deterministic control. `@start()`\u002F`@listen()`-decorated methods let you chain individual LLM calls, conditionals, and (optionally) whole Crews with precise control, when you need more determinism than a fully autonomous Crew.\n\nWhere LangGraph models orchestration explicitly as a state-machine graph, and smolagents minimizes overhead around a single tool-calling loop, CrewAI's abstraction is closer to how a human team is briefed: each agent gets a persona and a goal, and delegates\u002Fcollaborates through natural-language task handoffs.\n\n## Installation\n\n```bash\nuv pip install crewai\nuv pip install \"crewai[tools]\"     # prebuilt tools package (web search, RAG, code exec, file I\u002FO, ...)\n\n# Provider extras are usually unnecessary — crewai talks to most providers via LiteLLM model strings\nuv pip install \"crewai[anthropic]\"   # only if you need the native (non-LiteLLM) Anthropic SDK path\n```\n\nSet the relevant provider API key as an environment variable (e.g. `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`) before running — CrewAI's default `llm=` resolution picks these up automatically via LiteLLM.\n\nCheck version: `python -c \"import crewai; print(crewai.__version__)\"` (targets the 1.15.x series).\n\n## When to Use vs. LangGraph \u002F smolagents\n\n| | CrewAI | LangGraph | smolagents |\n|---|---|---|---|\n| Mental model | Role-playing agents, delegated tasks | Explicit state-machine graph | Minimal single-agent tool-calling loop |\n| Best for | Multi-persona pipelines (researcher → analyst → writer) | Complex branching\u002Flooping control flow you want to see explicitly | Lightweight single-agent tool use, fast prototyping |\n| Determinism | Crews are more autonomous; Flows add explicit control | High (you define every edge) | Low-to-medium (ReAct loop) |\n\nReach for CrewAI when the natural decomposition of your problem is \"a team of specialists,\" and for LangGraph when you need to reason precisely about every possible transition between steps.\n\n## Core Concepts\n\n```python\nfrom crewai import Agent, Task, Crew, Process\n\nresearcher = Agent(\n    role=\"Senior Research Analyst\",\n    goal=\"Find and summarize the latest findings on {topic}\",\n    backstory=\"You are an expert at scanning literature and extracting the signal from noise.\",\n    verbose=True,\n)\n\nwriter = Agent(\n    role=\"Technical Writer\",\n    goal=\"Turn research findings into a clear, well-structured report\",\n    backstory=\"You write for a technical but time-constrained audience.\",\n    verbose=True,\n)\n\nresearch_task = Task(\n    description=\"Research recent developments in {topic} and list the 5 most important findings.\",\n    expected_output=\"A bulleted list of 5 findings, each with a one-sentence explanation.\",\n    agent=researcher,\n)\n\nwriting_task = Task(\n    description=\"Using the research findings, write a 3-paragraph summary report on {topic}.\",\n    expected_output=\"A 3-paragraph markdown report.\",\n    agent=writer,\n    context=[research_task],   # explicitly pass research_task's output into this task's context\n)\n\ncrew = Crew(\n    agents=[researcher, writer],\n    tasks=[research_task, writing_task],\n    process=Process.sequential,\n    verbose=True,\n)\n\nresult = crew.kickoff(inputs={\"topic\": \"CRISPR base editing\"})\nprint(result.raw)\n```\n\n`Process.hierarchical` instead assigns a manager LLM (set via `Crew(manager_llm=...)` or a dedicated manager `Agent`) that decides at runtime which agent handles which task — useful when the task breakdown isn't known ahead of time.\n\n## Tools\n\n```python\nfrom crewai.tools import tool\n\n@tool(\"Query internal database\")\ndef query_db(sql: str) -> str:\n    \"\"\"Run a read-only SQL query against the internal research database and return rows as text.\"\"\"\n    return run_query(sql)\n\nresearcher = Agent(role=\"...\", goal=\"...\", backstory=\"...\", tools=[query_db])\n```\n\n`crewai-tools` (via the `tools` extra) ships common prebuilt tools — web\u002Fserper search, file readers, directory readers, RAG tools, code-execution sandboxes — so custom `@tool` functions are usually only needed for internal\u002Fproprietary integrations.\n\n## Flows: Event-Driven Control\n\n```python\nfrom crewai.flow.flow import Flow, start, listen\n\nclass ResearchFlow(Flow):\n    @start()\n    def get_topic(self):\n        self.state[\"topic\"] = \"single-cell foundation models\"\n        return self.state[\"topic\"]\n\n    @listen(get_topic)\n    def run_research_crew(self, topic):\n        return research_crew.kickoff(inputs={\"topic\": topic})\n\n    @listen(run_research_crew)\n    def save_report(self, report):\n        with open(\"report.md\", \"w\") as f:\n            f.write(report.raw)\n\nResearchFlow().kickoff()\n```\n\nFlows can mix single LLM calls, plain Python logic, and whole `Crew.kickoff()` calls as steps — use them when a Crew alone gives you too little control over the sequence of operations.\n\n## Memory\n\nCrews support short-term memory (within a run), long-term memory (persisted across runs via a local vector store), and entity memory (tracked facts about specific entities). Enable with `Crew(memory=True)`; for production use, back it with an explicit vector store config rather than the default local one so memory survives across deployments.\n\n## Project Scaffolding\n\n```bash\ncrewai create crew my_project\ncd my_project\ncrewai run\n```\n\nThis generates the JSON-first layout: agent definitions live in `agents\u002F*.jsonc`, while tasks, process, and input defaults live in `crew.jsonc`. If you need the older Python\u002FYAML layout with `crew.py`, `config\u002Fagents.yaml`, and `config\u002Ftasks.yaml`, create it explicitly:\n\n```bash\ncrewai create crew my_project --classic\n```\n\n## Observability\n\nCrewAI emits OpenTelemetry traces (via `opentelemetry-sdk`, bundled as a dependency) and has a hosted \"Crew Control Plane\" (part of the commercial AMP Suite) for tracing\u002Fmonitoring in production; for local debugging, `verbose=True` on `Agent`\u002F`Crew`\u002F`Task` prints each agent's reasoning and tool calls to stdout.\n\n## Common Pitfalls\n\n- **Vague `expected_output`.** CrewAI agents use `expected_output` to judge when a task is \"done\" — a vague description (e.g., \"a summary\") produces inconsistent, sometimes incomplete outputs; be concrete about format and length (\"a bulleted list of exactly 5 findings\").\n- **Duplicate or overlapping `role`s confuse hierarchical delegation.** In `Process.hierarchical`, the manager picks an agent by matching the task to agent roles\u002Fgoals; near-identical roles across agents lead to unpredictable delegation. Keep roles distinct.\n- **Missing `context=[...]` between sequential tasks.** In `Process.sequential`, CrewAI passes prior task outputs forward automatically by order, but for non-adjacent dependencies (task 3 needs task 1's output, not task 2's) you must set `context=` explicitly or the dependency is silently dropped.\n- **Cost\u002Flatency compounding in long sequential crews.** Each agent call is a full LLM round-trip (sometimes with its own tool-calling sub-loop); a 5-agent sequential crew can be significantly slower\u002Fcostlier than one well-prompted single-agent call — reserve multi-agent Crews for genuinely decomposable problems, not everything.\n- **Tool description mutation.** Recent versions (1.15.x) intentionally stop rewriting a tool's authored description at construction time — if you're relying on CrewAI to auto-generate\u002Fadjust a tool's description for the LLM, write the description you actually want up front instead.\n- **Rate limits from `verbose=True` chains during development.** Verbose mode is invaluable for debugging but doesn't reduce actual LLM calls; if you're hitting provider rate limits while iterating, that's real traffic, not a logging artifact — reduce `max_iterations`\u002Fagent count while debugging.\n\n## Resources\n\n- Docs: https:\u002F\u002Fdocs.crewai.com\u002F\n- Source: https:\u002F\u002Fgithub.com\u002FcrewAIInc\u002FcrewAI\n- crewai-tools: https:\u002F\u002Fgithub.com\u002FcrewAIInc\u002FcrewAI-tools\n- Learning platform: https:\u002F\u002Flearn.crewai.com\u002F\n","# CrewAI\n\n## Overview\n\nCrewAI is a Python framework, built from scratch independent of LangChain, for orchestrating teams of LLM agents. It has two complementary orchestration models:\n\n- **Crews** — role-based, autonomous collaboration. You define `Agent`s (each with a `role`, `goal`, `backstory`, and optional `tools`\u002F`llm`) and `Task`s (each with a `description`, `expected_output`, and an assigned `agent`), then wire them into a `Crew` that runs tasks either `Process.sequential` (task N's output feeds task N+1) or `Process.hierarchical` (a manager agent dynamically delegates tasks to the crew).\n- **Flows** — event-driven, deterministic control. `@start()`\u002F`@listen()`-decorated methods let you chain individual LLM calls, conditionals, and (optionally) whole Crews with precise control, when you need more determinism than a fully autonomous Crew.\n\nWhere LangGraph models orchestration explicitly as a state-machine graph, and smolagents minimizes overhead around a single tool-calling loop, CrewAI's abstraction is closer to how a human team is briefed: each agent gets a persona and a goal, and delegates\u002Fcollaborates through natural-language task handoffs.\n\n## Installation\n\n```bash\nuv pip install crewai\nuv pip install \"crewai[tools]\"     # prebuilt tools package (web search, RAG, code exec, file I\u002FO, ...)\n\n# Provider extras are usually unnecessary — crewai talks to most providers via LiteLLM model strings\nuv pip install \"crewai[anthropic]\"   # only if you need the native (non-LiteLLM) Anthropic SDK path\n```\n\nSet the relevant provider API key as an environment variable (e.g. `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`) before running — CrewAI's default `llm=` resolution picks these up automatically via LiteLLM.\n\nCheck version: `python -c \"import crewai; print(crewai.__version__)\"` (targets the 1.15.x series).\n\n## When to Use vs. LangGraph \u002F smolagents\n\n| | CrewAI | LangGraph | smolagents |\n|---|---|---|---|\n| Mental model | Role-playing agents, delegated tasks | Explicit state-machine graph | Minimal single-agent tool-calling loop |\n| Best for | Multi-persona pipelines (researcher → analyst → writer) | Complex branching\u002Flooping control flow you want to see explicitly | Lightweight single-agent tool use, fast prototyping |\n| Determinism | Crews are more autonomous; Flows add explicit control | High (you define every edge) | Low-to-medium (ReAct loop) |\n\nReach for CrewAI when the natural decomposition of your problem is \"a team of specialists,\" and for LangGraph when you need to reason precisely about every possible transition between steps.\n\n## Core Concepts\n\n```python\nfrom crewai import Agent, Task, Crew, Process\n\nresearcher = Agent(\n    role=\"Senior Research Analyst\",\n    goal=\"Find and summarize the latest findings on {topic}\",\n    backstory=\"You are an expert at scanning literature and extracting the signal from noise.\",\n    verbose=True,\n)\n\nwriter = Agent(\n    role=\"Technical Writer\",\n    goal=\"Turn research findings into a clear, well-structured report\",\n    backstory=\"You write for a technical but time-constrained audience.\",\n    verbose=True,\n)\n\nresearch_task = Task(\n    description=\"Research recent developments in {topic} and list the 5 most important findings.\",\n    expected_output=\"A bulleted list of 5 findings, each with a one-sentence explanation.\",\n    agent=researcher,\n)\n\nwriting_task = Task(\n    description=\"Using the research findings, write a 3-paragraph summary report on {topic}.\",\n    expected_output=\"A 3-paragraph markdown report.\",\n    agent=writer,\n    context=[research_task],   # explicitly pass research_task's output into this task's context\n)\n\ncrew = Crew(\n    agents=[researcher, writer],\n    tasks=[research_task, writing_task],\n    process=Process.sequential,\n    verbose=True,\n)\n\nresult = crew.kickoff(inputs={\"topic\": \"CRISPR base editing\"})\nprint(result.raw)\n```\n\n`Process.hierarchical` instead assigns a manager LLM (set via `Crew(manager_llm=...)` or a dedicated manager `Agent`) that decides at runtime which agent handles which task — useful when the task breakdown isn't known ahead of time.\n\n## Tools\n\n```python\nfrom crewai.tools import tool\n\n@tool(\"Query internal database\")\ndef query_db(sql: str) -> str:\n    \"\"\"Run a read-only SQL query against the internal research database and return rows as text.\"\"\"\n    return run_query(sql)\n\nresearcher = Agent(role=\"...\", goal=\"...\", backstory=\"...\", tools=[query_db])\n```\n\n`crewai-tools` (via the `tools` extra) ships common prebuilt tools — web\u002Fserper search, file readers, directory readers, RAG tools, code-execution sandboxes — so custom `@tool` functions are usually only needed for internal\u002Fproprietary integrations.\n\n## Flows: Event-Driven Control\n\n```python\nfrom crewai.flow.flow import Flow, start, listen\n\nclass ResearchFlow(Flow):\n    @start()\n    def get_topic(self):\n        self.state[\"topic\"] = \"single-cell foundation models\"\n        return self.state[\"topic\"]\n\n    @listen(get_topic)\n    def run_research_crew(self, topic):\n        return research_crew.kickoff(inputs={\"topic\": topic})\n\n    @listen(run_research_crew)\n    def save_report(self, report):\n        with open(\"report.md\", \"w\") as f:\n            f.write(report.raw)\n\nResearchFlow().kickoff()\n```\n\nFlows can mix single LLM calls, plain Python logic, and whole `Crew.kickoff()` calls as steps — use them when a Crew alone gives you too little control over the sequence of operations.\n\n## Memory\n\nCrews support short-term memory (within a run), long-term memory (persisted across runs via a local vector store), and entity memory (tracked facts about specific entities). Enable with `Crew(memory=True)`; for production use, back it with an explicit vector store config rather than the default local one so memory survives across deployments.\n\n## Project Scaffolding\n\n```bash\ncrewai create crew my_project\ncd my_project\ncrewai run\n```\n\nThis generates the JSON-first layout: agent definitions live in `agents\u002F*.jsonc`, while tasks, process, and input defaults live in `crew.jsonc`. If you need the older Python\u002FYAML layout with `crew.py`, `config\u002Fagents.yaml`, and `config\u002Ftasks.yaml`, create it explicitly:\n\n```bash\ncrewai create crew my_project --classic\n```\n\n## Observability\n\nCrewAI emits OpenTelemetry traces (via `opentelemetry-sdk`, bundled as a dependency) and has a hosted \"Crew Control Plane\" (part of the commercial AMP Suite) for tracing\u002Fmonitoring in production; for local debugging, `verbose=True` on `Agent`\u002F`Crew`\u002F`Task` prints each agent's reasoning and tool calls to stdout.\n\n## Common Pitfalls\n\n- **Vague `expected_output`.** CrewAI agents use `expected_output` to judge when a task is \"done\" — a vague description (e.g., \"a summary\") produces inconsistent, sometimes incomplete outputs; be concrete about format and length (\"a bulleted list of exactly 5 findings\").\n- **Duplicate or overlapping `role`s confuse hierarchical delegation.** In `Process.hierarchical`, the manager picks an agent by matching the task to agent roles\u002Fgoals; near-identical roles across agents lead to unpredictable delegation. Keep roles distinct.\n- **Missing `context=[...]` between sequential tasks.** In `Process.sequential`, CrewAI passes prior task outputs forward automatically by order, but for non-adjacent dependencies (task 3 needs task 1's output, not task 2's) you must set `context=` explicitly or the dependency is silently dropped.\n- **Cost\u002Flatency compounding in long sequential crews.** Each agent call is a full LLM round-trip (sometimes with its own tool-calling sub-loop); a 5-agent sequential crew can be significantly slower\u002Fcostlier than one well-prompted single-agent call — reserve multi-agent Crews for genuinely decomposable problems, not everything.\n- **Tool description mutation.** Recent versions (1.15.x) intentionally stop rewriting a tool's authored description at construction time — if you're relying on CrewAI to auto-generate\u002Fadjust a tool's description for the LLM, write the description you actually want up front instead.\n- **Rate limits from `verbose=True` chains during development.** Verbose mode is invaluable for debugging but doesn't reduce actual LLM calls; if you're hitting provider rate limits while iterating, that's real traffic, not a logging artifact — reduce `max_iterations`\u002Fagent count while debugging.\n\n## Resources\n\n- Docs: https:\u002F\u002Fdocs.crewai.com\u002F\n- Source: https:\u002F\u002Fgithub.com\u002FcrewAIInc\u002FcrewAI\n- crewai-tools: https:\u002F\u002Fgithub.com\u002FcrewAIInc\u002FcrewAI-tools\n- Learning platform: https:\u002F\u002Flearn.crewai.com\u002F\n",{"name":5,"license":15,"metadata":24,"description":7,"allowed-tools":27,"compatibility":32},{"version":25,"skill-author":26},"1.0","community",[28,29,30,31],"Read","Write","Edit","Bash","Requires Python >=3.10,\u003C3.14 and crewai 1.x. Routes most LLM providers through LiteLLM by default, so provider extras (crewai[anthropic], crewai[aws]\u002F[bedrock], crewai[azure-ai-inference], crewai[google-genai]) are usually optional; install crewai[tools] to pull in the separate crewai-tools package of prebuilt tools (web search, file readers, code execution, etc.).","master","49e49abf2f670d429e0b7e2c0349739c3fdd5cbe","skills\u002Fcrewai",5,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium","https:\u002F\u002Fgithub.com\u002Fstanfish06","https:\u002F\u002Fwww.stanfish.dev\u002F","2026-11-14 21:31:37",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add stanfish06\u002Fskillquarium --skill crewai",{"tool":47,"command":48},"bunx","bunx skills add stanfish06\u002Fskillquarium --skill crewai",{"tool":50,"command":51},"pnpm","pnpm dlx skills add stanfish06\u002Fskillquarium --skill crewai","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fcrewai\u002FSKILL.md",true,[],[56,63,72,79,86,93],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M76ZJTRVA456GD7K8Y3EP82H","zarr-python","Stores and queries chunked N-D scientific arrays with Zarr-Python 3, including codecs, sharding, S3\u002FGCS storage, and NumPy\u002FDask\u002FXarray integration. Use for array layout, bounded I\u002FO, format migration, or scientific metadata preservation.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M76ZJQZ15Q1HKC5V85NHE325","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M76ZJ8ASZ4QYQ70Y6SBA4Z4S","xarray","N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF\u002FGRIB\u002FZarr files, climate\u002Fweather\u002Foceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fxarray\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M76ZHFBXD6VXPQ02VCEG202B","writing-mstest-tests","Use when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for \"review\" when corrected code or edits are wanted, even for one pasted assertion or passing tests with bad failure output. Covers expected\u002Factual labels; generic Boolean, collection, string, numeric, null, identity, exception, hard-cast, and object[] checks; TestContext\u002Flifecycle; timeout\u002Fcancellation; OS\u002FCI conditions, retry, cleanup, parallelization, MSTest.Sdk project setup, and MSTESTxxxx. Honor the installed MSTest version. DO NOT USE to design new test cases (code-testing), perform report-only audits, create project files rather than explain MSTest setup, run tests, migrate frameworks, or handle non-MSTest\u002Fnon-.NET code.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-mstest-tests\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M76ZDFDF4N88RH6HSYGS7GP2","wgs-prs","End-to-end WGS to polygenic risk score pipeline. Takes paired-end FASTQ files (or a pre-existing VCF) through nf-core\u002Fsarek for variant calling, applies VCF QC (normalisation, hard filtering, Ti\u002FTv and Het\u002FHom checks), then computes polygenic risk scores via the PGS Catalog. Fills the FASTQ to VCF gap upstream of the gwas-prs skill.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwgs-prs\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M76ZCC1SC68J42QK4MDC8RCG","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[]]