[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EMX6NDVW7KDGCFZHF2P9AP":3,"skill-same:01M7EMX6NDVW7KDGCFZHF2P9AP":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7EMX6NDVW7KDGCFZHF2P9AP","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.","Rainbow609\u002Fagent-skills","Rainbow609","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F101709481?v=4","01M7EMQ6CNBNP7TVFZ4Z63RZXD","01M7EMQ6ENV4B0Y542WKXNZBSM",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-agent-config\u002FSKILL.md",[],[],"2026-11-15 14:19:17",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. 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. 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":14,"description":7,"compatibility":23},"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`).","main","18e26686a1432c54293deba762caad02ba886925","upstream\u002Fdocker\u002Fskills\u002Fdocker-agent-config","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills","https:\u002F\u002Fgithub.com\u002FRainbow609","2026-11-15 11:39:03",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add Rainbow609\u002Fagent-skills --skill docker-agent-config",{"tool":36,"command":37},"bunx","bunx skills add Rainbow609\u002Fagent-skills --skill docker-agent-config",{"tool":39,"command":40},"pnpm","pnpm dlx skills add Rainbow609\u002Fagent-skills --skill docker-agent-config","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-agent-config\u002FSKILL.md",true,[44,50,56,60,64,68],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",369,"https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-agent-config\u002Fagents\u002Fopenai.yaml",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Fteam-agent.yaml","ASSET","资产文件",936,"https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-agent-config\u002Fassets\u002Fteam-agent.yaml",{"path":57,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":58,"sourceHtmlUrl":59},"checks\u002Fverification.md",2268,"https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-agent-config\u002Fchecks\u002Fverification.md",{"path":61,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsources.md",1869,"https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-agent-config\u002Freferences\u002Fsources.md",{"path":65,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftoolsets-and-providers.md",3419,"https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-agent-config\u002Freferences\u002Ftoolsets-and-providers.md",{"path":69,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":70,"sourceHtmlUrl":71},"skill.yaml",1065,"https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-agent-config\u002Fskill.yaml",[73,82,90,97,104,111],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":77,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M7EN4N53ENQWQE5NDRT64NDC","archify","Create validated architecture, workflow, sequence, data-flow, lifecycle\u002Fstate, entity-relationship, class\u002Finterface, tree, timeline, and execution waterfall diagrams as explorable standalone HTML with inline SVG, dark\u002Flight themes, optional motion, and image\u002FSVG\u002FWebM export. Accept plain-language requirements or Mermaid; inspect repository evidence for code-backed diagrams. Use when visualizing infrastructure, cloud\u002Fsecurity networks, API calls, data pipelines, ETL\u002FELT, state machines, database schemas, class contracts, module hierarchies, incident\u002Frelease histories, or request and agent-run timings. Also use for everyday subjects with steps, parts, relationships, or states: leave and travel plans, applications and approvals, renting conversations, money or document flows, and order progress. Not for numeric charts or dashboards.","MIT","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Ftt-a1i\u002Farchify\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Ftt-a1i\u002Farchify\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":77,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M7EN4GGKJXFVK85685S30141","distilly","Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague, relationship, or celebrity source material into reusable Person Profiles for agents.","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Ftitanwings\u002Fdistilly\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Ftitanwings\u002Fdistilly\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M7EMZQREVCNAJA9DY7NQ7M7Q","docker-sandboxes-network-credentials","Use this skill when configuring what a Docker Sandboxes (`sbx`) sandbox can reach on the network or which credentials it authenticates with, even if the user just says they want to \"let the agent call an internal API\", \"block all network access\", \"give the agent a GitHub token\", or \"use a private registry image for a sandbox\". Covers `sbx policy init\u002Fallow\u002Fdeny\u002Fls\u002Finspect\u002Flog\u002Fcheck\u002Frm network` (global and per-sandbox egress rules, deny-over-allow precedence) and `sbx secret set\u002Fset-custom\u002Fls\u002Frm\u002Fimport` (service secrets, dynamic secrets via --ref\u002F--command, and registry pull credentials with their host-pulls-only-by-default injection scope).","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-sandboxes-network-credentials\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M7EMZE6V7A70RR2AMMDAGP3S","docker-sandboxes-lifecycle","Use this skill when creating, running, reattaching to, listing, stopping, or removing Docker Sandboxes (the standalone `sbx` CLI that runs AI coding agents in isolated microVMs), even if the user just says they want to \"run claude in a sandbox\", \"isolate an agent from my repo\", \"give an agent its own git clone\", or \"clean up old sandboxes\". Covers `sbx run`\u002F`sbx create` (including the built-in agents claude, codex, cursor, devin, docker-agent, gemini, opencode, shell), workspace bind-mount vs `--clone` isolation, additional read-only workspaces, reattaching by `--name`, `sbx ls`\u002F`stop`\u002F`rm`\u002F`prune`, `sbx exec`, `sbx cp`, and `sbx ports`.","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-sandboxes-lifecycle\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M7EMZ2BN8Z7P5H557RS8WYP2","docker-sandboxes-kits","Use this skill when authoring, validating, packaging, signing, or composing a Docker Sandboxes kit `spec.yaml` (`sbx kit add\u002Finspect\u002Fpack\u002Fpull\u002Fpush\u002Fsign\u002Fvalidate\u002Fverify`), even if the user just says they want to \"add a tool to a sandbox agent\", \"build a reusable sandbox extension\", \"publish a kit to a registry\", or \"give a mixin its own credentials and network access\". Covers the kit-spec v2 grammar (`kind: sandbox` vs `kind: mixin`, the `sandbox:` block, `permissions.network`, `ports`, `credentials` apiKey\u002Foauth, `environment`, `setup` install\u002Fstartup\u002Ffiles, `volumes`, `args`, `extends`, `mixins`, `requires.agent`), composition via `--kit`\u002F`sbx kit add`, and distribution (pack\u002Fpush\u002Fpull\u002Fsign\u002Fverify\u002Fprovenance).","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-sandboxes-kits\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M7EMYQZXA60B14ZQEXMSWNVG","docker-sandboxes-env","Use this skill when authoring, planning, or running a declarative `sbxenv.yaml` file for Docker Sandboxes (`sbx env create\u002Frun\u002Fplan\u002Fexec\u002Frm`), even if the user just says they want to \"check in a sandbox config\", \"make onboarding reproducible for a sandbox\", \"run a setup script before the agent starts\", or \"define arguments for a shared sandbox environment\". Covers the sbxenv.yaml schema (schemaVersion, agent, kits, workspace\u002FadditionalWorkspaces, args, env, secrets, registries, bindings, mcp, ports, sandboxOptions), host `lifecycle:` commands (initialize\u002FpostCreate\u002FpreRemove) and their approval-plan model, multi-file merge (`-f`-style deep merge and the user-level `.sbxenv.yaml` base layer), and file-write-protection (`sandboxOptions.writableEnvFiles`).","https:\u002F\u002Fgithub.com\u002FRainbow609\u002Fagent-skills\u002Fblob\u002Fmain\u002Fupstream\u002Fdocker\u002Fskills\u002Fdocker-sandboxes-env\u002FSKILL.md",[],[]]