[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75HS0HG6JC8DPYVQK127K4J":3,"skill-same:01M75HS0HG6JC8DPYVQK127K4J":79},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M75HS0HG6JC8DPYVQK127K4J","docker-agent-config",null,"Use this skill when creating or editing an agent.yaml (or .yml\u002F.hcl) configuration file for Docker Agent (cagent), including defining agents, models\u002Fproviders, built-in or MCP toolsets, multi-agent teams with sub_agents. Even if the user just says they want to \"build an AI agent with Docker\", \"make a coding agent config\", \"add a tool to my agent\", or \"set up a team of agents\", this skill applies. Covers agent properties (model, instruction, toolsets, sub_agents, fallback), the models\u002Fproviders sections, built-in toolsets (filesystem, shell, think, todo, memory, fetch), MCP toolset references, and named commands.","stanfish06\u002Fskillquarium","stanfish06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F93099613?v=4","01M75F1CK4ZW109ZK3T26VN52F","Zhiyuan","01M75F1CM53VH6F79DZ8GXKKES",12,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fdocker-agent-config\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: docker-agent-config\ndescription: Use this skill when creating or editing an agent.yaml (or .yml\u002F.hcl) configuration file for Docker Agent (cagent), including defining agents, models\u002Fproviders, built-in or MCP toolsets, multi-agent teams with sub_agents. Even if the user just says they want to \"build an AI agent with Docker\", \"make a coding agent config\", \"add a tool to my agent\", or \"set up a team of agents\", this skill applies. Covers agent properties (model, instruction, toolsets, sub_agents, fallback), the models\u002Fproviders sections, built-in toolsets (filesystem, shell, think, todo, memory, fetch), MCP toolset references, and named commands.\nlicense: Apache-2.0\ncompatibility: Requires the docker-agent CLI plugin (Docker Desktop 4.63+, or standalone via Homebrew\u002FGitHub releases). Verified against docker-agent as shipped with Docker CLI 29.7.2. Config directories still use the legacy `cagent` name (`~\u002F.config\u002Fcagent`, `~\u002F.cagent`).\n---\n\n# Docker Agent Configuration\n\n## Overview\nDocker Agent (the CLI is `docker agent`, the open-source project is `cagent`)\nruns AI agents declared in a YAML file instead of application code. This\nskill owns the `agent.yaml` artifact: the `agents` section (each entry's\n`model`, `instruction`, and its own `toolsets`\u002F`sub_agents`), the top-level\n`models`\u002F`providers` sections referenced from agents, and a top-level\n`commands` group agents can opt into with `use_commands`. It does not cover\ninvoking the CLI or serving\u002Fsharing the config — see Related\nskills.\n\n## When to use this skill\nActivate this skill when:\n- The user is creating, editing, or reviewing an `agent.yaml`\u002F`agent.yml`\u002F`agent.hcl` file.\n- The user wants to add a tool\u002Ftoolset, an MCP server, or a sub-agent to an agent config.\n- The user wants to choose or configure a model\u002Fprovider (OpenAI, Anthropic, Google, Bedrock, Docker Model Runner, custom endpoint) for an agent.\n- The user wants a multi-agent \"team\" with a coordinator delegating to specialists.\n\n## Do not use this skill when\nDo not use this skill when:\n- The task is about running the CLI (`docker agent run` flags, `--safety`, `--sandbox`, aliases, worktrees) — use `docker-agent-run`.\n- The task is about exposing an agent as a server (`serve mcp\u002Fapi\u002Fa2a\u002Facp\u002Fchat`), distributing it (`share push\u002Fpull`), or evaluating it (evaluation sessions, `--baseline` regression gates) — use `docker-agent-deploy`.\n- The task is about a generic Dockerfile or Compose service unrelated to Docker Agent — use `docker-build-strategies` or `docker-compose-patterns`.\n\n## Core guidance\n\n### File structure\n- Every config needs at least one agent under top-level `agents:`. The agent\n  named `root`, or the first agent defined, is the entry point that receives\n  user messages.\n  ```yaml\n  agents:\n    root:\n      model: anthropic\u002Fclaude-sonnet-4-5\n      description: A coding assistant\n      instruction: |\n        You are an expert developer. Help users write clean,\n        efficient code. Explain your reasoning step by step.\n      toolsets:\n        - type: filesystem\n        - type: shell\n        - type: think\n  ```\n- Required agent properties: `model`, `description`, `instruction` (or\n  `instruction_file`). `description` is not decoration — other agents read it\n  to decide whether to delegate to this one, so keep it accurate.\n- Use `instruction_file` (a relative path, no `..`) instead of an inline\n  `instruction` for long prompts; this keeps diffs focused on behavior, not\n  YAML escaping. `instruction` and `instruction_file` are mutually exclusive.\n  `instruction_file` is not supported for agents loaded from an OCI reference\n  or URL — inline `instruction` there.\n\n### Models and providers\n- Two ways to set a model: inline `provider\u002Fmodel` shorthand, or a named\n  entry under top-level `models:` referencing a `provider`. Use the named\n  form whenever you need `temperature`, `max_tokens`, `thinking_budget`, or\n  reuse across agents.\n  ```yaml\n  models:\n    claude:\n      provider: anthropic\n      model: claude-sonnet-4-5\n      max_tokens: 64000\n\n  agents:\n    root:\n      model: claude\n  ```\n- Built-in provider keys: `openai`, `anthropic`, `google`, `amazon-bedrock`,\n  `dmr` (Docker Model Runner, local, no API key), `ollama` (local). Dozens of\n  additional built-in aliases exist (`mistral`, `groq`, `xai`, `together`,\n  `azure`, `github-copilot`, `openrouter`, ...) — each needs its own\n  `\u003CPROVIDER>_API_KEY`-style env var; run `docker agent models --all` to see\n  what's resolvable, and `docker agent setup` to register credentials\n  interactively instead of hand-editing env vars.\n- Never hardcode an API key in `agent.yaml`. Provider credentials come from\n  environment variables (`token_key` for custom providers) or from\n  `~\u002F.config\u002Fcagent\u002F.env` written by `docker agent setup`.\n- Prefer `dmr\u002F\u003Cmodel>` for agents that must run offline or must not send data\n  to a third party; it costs nothing and needs no credential. The model must\n  be pulled locally first with `docker model pull \u003Cmodel>` — run\n  `docker agent doctor` to diagnose missing or unavailable models. Use a paid\n  cloud provider only when the task needs it.\n- Give resilience-critical agents a `fallback` so a provider outage or rate\n  limit does not stop the run:\n  ```yaml\n  agents:\n    root:\n      model: anthropic\u002Fclaude-sonnet-4-5\n      fallback:\n        models: [openai\u002Fgpt-5, google\u002Fgemini-3.5-flash]\n        retries: 2      # per model, for 5xx errors\n        cooldown: 1m    # stick with fallback after a 429\n  ```\n- For a self-hosted\u002FOpenAI-compatible endpoint (vLLM, LiteLLM, a corporate\n  gateway), define a `providers:` entry with `base_url` and `token_key`\n  rather than putting the URL inline on every model:\n  ```yaml\n  providers:\n    my_gateway:\n      base_url: https:\u002F\u002Fapi.example.com\u002Fv1\n      token_key: MY_API_KEY\n  models:\n    my_model:\n      provider: my_gateway\n      model: gpt-4o\n  ```\n\n### Toolsets\n- Built-in toolsets need no external dependency: `filesystem`, `shell`,\n  `think`, `todo`, `tasks`, `memory`, `fetch`, `background-jobs`, `script`,\n  `lsp`, `api`. Add one per list entry:\n  ```yaml\n  toolsets:\n    - type: filesystem\n    - type: shell\n  ```\n- If an agent only describes a plan but never executes it, add `type: todo`\n  (or `shell`) — a common symptom of an agent missing the tool it needs to\n  act, not a model problem.\n- For external tools, prefer an MCP server from Docker's MCP catalog over a\n  bespoke integration — it runs containerized and is reusable across agents:\n  ```yaml\n  toolsets:\n    - type: mcp\n      ref: docker:duckduckgo\n  ```\n  Local stdio and remote HTTP\u002FSSE MCP servers are also supported; see\n  `references\u002Ftoolsets-and-providers.md`.\n- Use `defer: true` on a toolset (MCP or otherwise) to load its tools\n  on-demand instead of at startup, when the agent has many toolsets and\n  startup latency matters.\n- Set `readonly: true` on an agent to restrict every toolset it uses to\n  read-only tools — use this for reviewer\u002Fanalysis agents that must not\n  mutate anything.\n\n### Multi-agent teams\n- A coordinator delegates via `sub_agents: [name, ...]`; listing sub-agents\n  automatically enables the `transfer_task` tool on the parent.\n  ```yaml\n  # Fragment: coder and reviewer are defined separately in the full asset.\n  agents:\n    root:\n      sub_agents: [coder, reviewer]\n  ```\n  Use `assets\u002Fteam-agent.yaml` for the complete runnable team, including\n  the reviewer's `readonly: true` restriction. Keep that restriction when\n  adapting the template; a filesystem toolset alone also exposes writes.\n- `sub_agents` also accepts external OCI references (`myorg\u002Fagent:tag`).\n  Pin external references to a digest (`name@sha256:...`) in production\n  configs to skip the per-run registry lookup that a tag incurs.\n- Use `transfer_task` (via `sub_agents`) for delegation with a clean,\n  isolated result; use a `commands:` entry with an `agent:` field only when\n  you want the user to *become* that agent for the rest of the session.\n\n### Safety and hygiene\n- Set `redact_secrets: true` on any agent that runs shell\u002Ffetch tools against\n  untrusted input. It scrubs recognized secret patterns from tool arguments,\n  outgoing messages, and tool output. This is defense in depth, not a\n  guarantee: arbitrary passwords, tokens, or customer data may go undetected.\n- Set `max_iterations` on any agent that loops autonomously (default is\n  unlimited) to bound cost and prevent runaway loops; `max_consecutive_tool_calls`\n  (default 5) already guards against identical-call loops.\n- Keep credentials, tokens, and sensitive customer data out of `instruction`,\n  `instruction_file`, and command prompts, whether literal or interpolated.\n  `${env.VAR}` expands values into prompt text sent to the model; storing a\n  value in an env file does not prevent this disclosure. Use interpolation\n  only for non-sensitive context.\n- Supply provider credentials through `docker agent setup` or the provider's\n  supported environment variables. For custom providers, `token_key: MY_API_KEY`\n  names the environment variable, not its value; do not interpolate it.\n  Configure tool\u002FMCP credentials through that integration's authentication\n  mechanism, not through prompts or model-supplied tool arguments. Prompts\n  should describe the authenticated capability without containing its secret.\n  Do not ask the agent to read or print credential files or environment values\n  to check authentication.\n\n## Related skills\n- For running the agent (`docker agent run`, safety modes, sandbox, aliases), use `docker-agent-run`.\n- For serving, sharing, or evaluating the agent, use `docker-agent-deploy`.\n\n## References\n- `references\u002Ftoolsets-and-providers.md` — full built-in toolset list, MCP connection modes, and the provider\u002Fenv-var table.\n- `references\u002Fsources.md` — provenance of every rule in this skill.\n\n## Assets\n- `assets\u002Fteam-agent.yaml` — a runnable multi-agent team template (coordinator + coder + reviewer).\n\n## Checks\n- Before running an agent, follow `checks\u002Fverification.md` to confirm its\n  resolved config, exposed tools, and provider connectivity, then smoke-test it.\n","# Docker Agent Configuration\n\n## Overview\nDocker Agent (the CLI is `docker agent`, the open-source project is `cagent`)\nruns AI agents declared in a YAML file instead of application code. This\nskill owns the `agent.yaml` artifact: the `agents` section (each entry's\n`model`, `instruction`, and its own `toolsets`\u002F`sub_agents`), the top-level\n`models`\u002F`providers` sections referenced from agents, and a top-level\n`commands` group agents can opt into with `use_commands`. It does not cover\ninvoking the CLI or serving\u002Fsharing the config — see Related\nskills.\n\n## When to use this skill\nActivate this skill when:\n- The user is creating, editing, or reviewing an `agent.yaml`\u002F`agent.yml`\u002F`agent.hcl` file.\n- The user wants to add a tool\u002Ftoolset, an MCP server, or a sub-agent to an agent config.\n- The user wants to choose or configure a model\u002Fprovider (OpenAI, Anthropic, Google, Bedrock, Docker Model Runner, custom endpoint) for an agent.\n- The user wants a multi-agent \"team\" with a coordinator delegating to specialists.\n\n## Do not use this skill when\nDo not use this skill when:\n- The task is about running the CLI (`docker agent run` flags, `--safety`, `--sandbox`, aliases, worktrees) — use `docker-agent-run`.\n- The task is about exposing an agent as a server (`serve mcp\u002Fapi\u002Fa2a\u002Facp\u002Fchat`), distributing it (`share push\u002Fpull`), or evaluating it (evaluation sessions, `--baseline` regression gates) — use `docker-agent-deploy`.\n- The task is about a generic Dockerfile or Compose service unrelated to Docker Agent — use `docker-build-strategies` or `docker-compose-patterns`.\n\n## Core guidance\n\n### File structure\n- Every config needs at least one agent under top-level `agents:`. The agent\n  named `root`, or the first agent defined, is the entry point that receives\n  user messages.\n  ```yaml\n  agents:\n    root:\n      model: anthropic\u002Fclaude-sonnet-4-5\n      description: A coding assistant\n      instruction: |\n        You are an expert developer. Help users write clean,\n        efficient code. Explain your reasoning step by step.\n      toolsets:\n        - type: filesystem\n        - type: shell\n        - type: think\n  ```\n- Required agent properties: `model`, `description`, `instruction` (or\n  `instruction_file`). `description` is not decoration — other agents read it\n  to decide whether to delegate to this one, so keep it accurate.\n- Use `instruction_file` (a relative path, no `..`) instead of an inline\n  `instruction` for long prompts; this keeps diffs focused on behavior, not\n  YAML escaping. `instruction` and `instruction_file` are mutually exclusive.\n  `instruction_file` is not supported for agents loaded from an OCI reference\n  or URL — inline `instruction` there.\n\n### Models and providers\n- Two ways to set a model: inline `provider\u002Fmodel` shorthand, or a named\n  entry under top-level `models:` referencing a `provider`. Use the named\n  form whenever you need `temperature`, `max_tokens`, `thinking_budget`, or\n  reuse across agents.\n  ```yaml\n  models:\n    claude:\n      provider: anthropic\n      model: claude-sonnet-4-5\n      max_tokens: 64000\n\n  agents:\n    root:\n      model: claude\n  ```\n- Built-in provider keys: `openai`, `anthropic`, `google`, `amazon-bedrock`,\n  `dmr` (Docker Model Runner, local, no API key), `ollama` (local). Dozens of\n  additional built-in aliases exist (`mistral`, `groq`, `xai`, `together`,\n  `azure`, `github-copilot`, `openrouter`, ...) — each needs its own\n  `\u003CPROVIDER>_API_KEY`-style env var; run `docker agent models --all` to see\n  what's resolvable, and `docker agent setup` to register credentials\n  interactively instead of hand-editing env vars.\n- Never hardcode an API key in `agent.yaml`. Provider credentials come from\n  environment variables (`token_key` for custom providers) or from\n  `~\u002F.config\u002Fcagent\u002F.env` written by `docker agent setup`.\n- Prefer `dmr\u002F\u003Cmodel>` for agents that must run offline or must not send data\n  to a third party; it costs nothing and needs no credential. The model must\n  be pulled locally first with `docker model pull \u003Cmodel>` — run\n  `docker agent doctor` to diagnose missing or unavailable models. Use a paid\n  cloud provider only when the task needs it.\n- Give resilience-critical agents a `fallback` so a provider outage or rate\n  limit does not stop the run:\n  ```yaml\n  agents:\n    root:\n      model: anthropic\u002Fclaude-sonnet-4-5\n      fallback:\n        models: [openai\u002Fgpt-5, google\u002Fgemini-3.5-flash]\n        retries: 2      # per model, for 5xx errors\n        cooldown: 1m    # stick with fallback after a 429\n  ```\n- For a self-hosted\u002FOpenAI-compatible endpoint (vLLM, LiteLLM, a corporate\n  gateway), define a `providers:` entry with `base_url` and `token_key`\n  rather than putting the URL inline on every model:\n  ```yaml\n  providers:\n    my_gateway:\n      base_url: https:\u002F\u002Fapi.example.com\u002Fv1\n      token_key: MY_API_KEY\n  models:\n    my_model:\n      provider: my_gateway\n      model: gpt-4o\n  ```\n\n### Toolsets\n- Built-in toolsets need no external dependency: `filesystem`, `shell`,\n  `think`, `todo`, `tasks`, `memory`, `fetch`, `background-jobs`, `script`,\n  `lsp`, `api`. Add one per list entry:\n  ```yaml\n  toolsets:\n    - type: filesystem\n    - type: shell\n  ```\n- If an agent only describes a plan but never executes it, add `type: todo`\n  (or `shell`) — a common symptom of an agent missing the tool it needs to\n  act, not a model problem.\n- For external tools, prefer an MCP server from Docker's MCP catalog over a\n  bespoke integration — it runs containerized and is reusable across agents:\n  ```yaml\n  toolsets:\n    - type: mcp\n      ref: docker:duckduckgo\n  ```\n  Local stdio and remote HTTP\u002FSSE MCP servers are also supported; see\n  `references\u002Ftoolsets-and-providers.md`.\n- Use `defer: true` on a toolset (MCP or otherwise) to load its tools\n  on-demand instead of at startup, when the agent has many toolsets and\n  startup latency matters.\n- Set `readonly: true` on an agent to restrict every toolset it uses to\n  read-only tools — use this for reviewer\u002Fanalysis agents that must not\n  mutate anything.\n\n### Multi-agent teams\n- A coordinator delegates via `sub_agents: [name, ...]`; listing sub-agents\n  automatically enables the `transfer_task` tool on the parent.\n  ```yaml\n  # Fragment: coder and reviewer are defined separately in the full asset.\n  agents:\n    root:\n      sub_agents: [coder, reviewer]\n  ```\n  Use `assets\u002Fteam-agent.yaml` for the complete runnable team, including\n  the reviewer's `readonly: true` restriction. Keep that restriction when\n  adapting the template; a filesystem toolset alone also exposes writes.\n- `sub_agents` also accepts external OCI references (`myorg\u002Fagent:tag`).\n  Pin external references to a digest (`name@sha256:...`) in production\n  configs to skip the per-run registry lookup that a tag incurs.\n- Use `transfer_task` (via `sub_agents`) for delegation with a clean,\n  isolated result; use a `commands:` entry with an `agent:` field only when\n  you want the user to *become* that agent for the rest of the session.\n\n### Safety and hygiene\n- Set `redact_secrets: true` on any agent that runs shell\u002Ffetch tools against\n  untrusted input. It scrubs recognized secret patterns from tool arguments,\n  outgoing messages, and tool output. This is defense in depth, not a\n  guarantee: arbitrary passwords, tokens, or customer data may go undetected.\n- Set `max_iterations` on any agent that loops autonomously (default is\n  unlimited) to bound cost and prevent runaway loops; `max_consecutive_tool_calls`\n  (default 5) already guards against identical-call loops.\n- Keep credentials, tokens, and sensitive customer data out of `instruction`,\n  `instruction_file`, and command prompts, whether literal or interpolated.\n  `${env.VAR}` expands values into prompt text sent to the model; storing a\n  value in an env file does not prevent this disclosure. Use interpolation\n  only for non-sensitive context.\n- Supply provider credentials through `docker agent setup` or the provider's\n  supported environment variables. For custom providers, `token_key: MY_API_KEY`\n  names the environment variable, not its value; do not interpolate it.\n  Configure tool\u002FMCP credentials through that integration's authentication\n  mechanism, not through prompts or model-supplied tool arguments. Prompts\n  should describe the authenticated capability without containing its secret.\n  Do not ask the agent to read or print credential files or environment values\n  to check authentication.\n\n## Related skills\n- For running the agent (`docker agent run`, safety modes, sandbox, aliases), use `docker-agent-run`.\n- For serving, sharing, or evaluating the agent, use `docker-agent-deploy`.\n\n## References\n- `references\u002Ftoolsets-and-providers.md` — full built-in toolset list, MCP connection modes, and the provider\u002Fenv-var table.\n- `references\u002Fsources.md` — provenance of every rule in this skill.\n\n## Assets\n- `assets\u002Fteam-agent.yaml` — a runnable multi-agent team template (coordinator + coder + reviewer).\n\n## Checks\n- Before running an agent, follow `checks\u002Fverification.md` to confirm its\n  resolved config, exposed tools, and provider connectivity, then smoke-test it.\n",{"name":5,"license":15,"description":7,"compatibility":24},"Requires the docker-agent CLI plugin (Docker Desktop 4.63+, or standalone via Homebrew\u002FGitHub releases). Verified against docker-agent as shipped with Docker CLI 29.7.2. Config directories still use the legacy `cagent` name (`~\u002F.config\u002Fcagent`, `~\u002F.cagent`).","master","7d24eff4820d45615e9c35d1a23587fcb2afcc1a","skills\u002Fdocker-agent-config",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":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add stanfish06\u002Fskillquarium --skill docker-agent-config",{"tool":39,"command":40},"bunx","bunx skills add stanfish06\u002Fskillquarium --skill docker-agent-config",{"tool":42,"command":43},"pnpm","pnpm dlx skills add stanfish06\u002Fskillquarium --skill docker-agent-config","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fdocker-agent-config\u002FSKILL.md",true,[47,53,59,63,67,71,75],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",369,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fdocker-agent-config\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"assets\u002Fteam-agent.yaml","ASSET","资产文件",936,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fdocker-agent-config\u002Fassets\u002Fteam-agent.yaml",{"path":60,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":61,"sourceHtmlUrl":62},"checks\u002Fverification.md",2268,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fdocker-agent-config\u002Fchecks\u002Fverification.md",{"path":64,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":65,"sourceHtmlUrl":66},"evals\u002Fdocker-agent-config.md",5334,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fdocker-agent-config\u002Fevals\u002Fdocker-agent-config.md",{"path":68,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fsources.md",1869,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fdocker-agent-config\u002Freferences\u002Fsources.md",{"path":72,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Ftoolsets-and-providers.md",3419,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fdocker-agent-config\u002Freferences\u002Ftoolsets-and-providers.md",{"path":76,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":77,"sourceHtmlUrl":78},"skill.yaml",1065,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fdocker-agent-config\u002Fskill.yaml",[80,88,96,103,110,117],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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.","MIT","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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.","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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"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":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":124,"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",[],[]]