[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DEPAKABSBX2015JPDP5HZ7":3,"skill-same:01M7DEPAKABSBX2015JPDP5HZ7":51},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7DEPAKABSBX2015JPDP5HZ7","create-subagent",null,"Create custom Codex subagents for specialized tasks. Use when the user wants a reusable reviewer, debugger, researcher, worker, or other custom agent with its own model, sandbox, tools, or instructions.","odellsallis93\u002Fskills-repo","odellsallis93","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F87449759?v=4","01M7DEG0QK6S7ZF5TAZZH1JKT9","ODell Sallis","01M7DEG0R9VYQBMCTWBFXHBZDS",0,"MIT","https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo\u002Fblob\u002Fmain\u002Fplugins\u002Fodell-codex\u002Fskills\u002Fcreate-subagent\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: create-subagent\ndescription: >-\n  Create custom Codex subagents for specialized tasks. Use when the user wants\n  a reusable reviewer, debugger, researcher, worker, or other custom agent with\n  its own model, sandbox, tools, or instructions.\n---\n\n# Create custom Codex subagents\n\nCreate a reusable custom agent as a standalone TOML configuration file. Infer the job and scope from the conversation when the answer is clear. Ask only when the missing choice would materially change the agent.\n\n## Choose the scope\n\n| Location | Scope |\n|---|---|\n| `\u003Crepo>\u002F.codex\u002Fagents\u002F\u003Cname>.toml` | One trusted project |\n| `~\u002F.codex\u002Fagents\u002F\u003Cname>.toml` | All local projects for this user |\n\nPrefer the project location for repository-specific knowledge or team-shared behavior. Prefer the user location for personal agents that should work in unrelated repositories.\n\nProject agent files load only when Codex trusts the project. If a project and user agent share the same `name`, the project configuration layer takes precedence.\n\n## File format\n\nEvery custom agent file must define `name`, `description`, and `developer_instructions`.\n\n```toml\nname = \"code_reviewer\"\ndescription = \"Review changed code for correctness, security, regressions, and missing tests.\"\nsandbox_mode = \"read-only\"\n\ndeveloper_instructions = \"\"\"\nReview the current changes like a code owner.\nLead with concrete findings and cite the affected files.\nIgnore style-only comments unless they hide a real defect.\nDo not edit files unless the parent agent explicitly asks for a fix.\n\"\"\"\n```\n\nUse a simple snake_case `name`. Match the filename to the name when practical. The `name` field remains the source of truth.\n\n## Optional settings\n\nA custom agent file is a Codex configuration layer. Add only settings needed for that role:\n\n- `model` and `model_reasoning_effort`\n- `sandbox_mode`\n- `mcp_servers`\n- `skills.config`\n\nDo not copy the full user configuration into each agent. Unspecified values inherit from the parent session.\n\n## Workflow\n\n1. Decide the agent's one job and whether it is project-scoped or user-scoped.\n2. Check for an existing file or agent with the same name. Preserve unrelated content and never overwrite silently.\n3. Create the `.codex\u002Fagents` directory only when it is missing.\n4. Write a TOML file with the three required fields.\n5. Add model, reasoning, sandbox, MCP, or skill settings only when the job requires them.\n6. Parse or inspect the TOML for syntax errors.\n7. Test the agent with a small realistic task. Restart Codex if a new definition is not discovered in the current session.\n\n## Quality rules\n\n- Keep each agent focused on one kind of work.\n- Describe when the parent should choose it in concrete terms.\n- Put durable role behavior in `developer_instructions`.\n- Set a read-only sandbox for review and research roles unless they must edit.\n- Preserve the user's model choice and authorization limits.\n\nFor current schema details, consult the official Codex subagents documentation before using an unfamiliar configuration key.\n","# Create custom Codex subagents\n\nCreate a reusable custom agent as a standalone TOML configuration file. Infer the job and scope from the conversation when the answer is clear. Ask only when the missing choice would materially change the agent.\n\n## Choose the scope\n\n| Location | Scope |\n|---|---|\n| `\u003Crepo>\u002F.codex\u002Fagents\u002F\u003Cname>.toml` | One trusted project |\n| `~\u002F.codex\u002Fagents\u002F\u003Cname>.toml` | All local projects for this user |\n\nPrefer the project location for repository-specific knowledge or team-shared behavior. Prefer the user location for personal agents that should work in unrelated repositories.\n\nProject agent files load only when Codex trusts the project. If a project and user agent share the same `name`, the project configuration layer takes precedence.\n\n## File format\n\nEvery custom agent file must define `name`, `description`, and `developer_instructions`.\n\n```toml\nname = \"code_reviewer\"\ndescription = \"Review changed code for correctness, security, regressions, and missing tests.\"\nsandbox_mode = \"read-only\"\n\ndeveloper_instructions = \"\"\"\nReview the current changes like a code owner.\nLead with concrete findings and cite the affected files.\nIgnore style-only comments unless they hide a real defect.\nDo not edit files unless the parent agent explicitly asks for a fix.\n\"\"\"\n```\n\nUse a simple snake_case `name`. Match the filename to the name when practical. The `name` field remains the source of truth.\n\n## Optional settings\n\nA custom agent file is a Codex configuration layer. Add only settings needed for that role:\n\n- `model` and `model_reasoning_effort`\n- `sandbox_mode`\n- `mcp_servers`\n- `skills.config`\n\nDo not copy the full user configuration into each agent. Unspecified values inherit from the parent session.\n\n## Workflow\n\n1. Decide the agent's one job and whether it is project-scoped or user-scoped.\n2. Check for an existing file or agent with the same name. Preserve unrelated content and never overwrite silently.\n3. Create the `.codex\u002Fagents` directory only when it is missing.\n4. Write a TOML file with the three required fields.\n5. Add model, reasoning, sandbox, MCP, or skill settings only when the job requires them.\n6. Parse or inspect the TOML for syntax errors.\n7. Test the agent with a small realistic task. Restart Codex if a new definition is not discovered in the current session.\n\n## Quality rules\n\n- Keep each agent focused on one kind of work.\n- Describe when the parent should choose it in concrete terms.\n- Put durable role behavior in `developer_instructions`.\n- Set a read-only sandbox for review and research roles unless they must edit.\n- Preserve the user's model choice and authorization limits.\n\nFor current schema details, consult the official Codex subagents documentation before using an unfamiliar configuration key.\n",{"name":5,"description":7},"main","1c9c71cb8682c1f18c7a54bc09a9ddfe2f70b80d","plugins\u002Fodell-codex\u002Fskills\u002Fcreate-subagent","https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo","https:\u002F\u002Fgithub.com\u002Fodellsallis93","SWE: Applied \u002F Agentic AI, Full-stack Web Dev, Mobile, Design | Computer Vision | Automation | Events | Music","2026-11-11 07:05:03",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add odellsallis93\u002Fskills-repo --skill create-subagent",{"tool":37,"command":38},"bunx","bunx skills add odellsallis93\u002Fskills-repo --skill create-subagent",{"tool":40,"command":41},"pnpm","pnpm dlx skills add odellsallis93\u002Fskills-repo --skill create-subagent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo\u002Fblob\u002Fmain\u002Fplugins\u002Fodell-codex\u002Fskills\u002Fcreate-subagent\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",149,"https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo\u002Fblob\u002Fmain\u002Fplugins\u002Fodell-codex\u002Fskills\u002Fcreate-subagent\u002Fagents\u002Fopenai.yaml",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7DF09PNHXECAA9M9472985Z","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo\u002Fblob\u002Fmain\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7DF06BVP31PP8PB9WQBG6NR","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo\u002Fblob\u002Fmain\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7DF03EM39HHEET1C44R50F7","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo\u002Fblob\u002Fmain\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7DF00MVBHP5P88V3A8FR3AW","triage","Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.","https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7DEZWFJTR2K5SGCVE1MQRTZ","to-tickets","Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).","https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo\u002Fblob\u002Fmain\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7DEZSYEBMNAGE02BCYWKMHT","to-spec","Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.","https:\u002F\u002Fgithub.com\u002Fodellsallis93\u002Fskills-repo\u002Fblob\u002Fmain\u002Fskills\u002Fto-spec\u002FSKILL.md",[],[]]