[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BKD3CGYBAC5VC3EW7KKKQD":3,"skill-same:01M7BKD3CGYBAC5VC3EW7KKKQD":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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BKD3CGYBAC5VC3EW7KKKQD","make-bot-ui",null,"Use when building a local page or dashboard whose fixed buttons start approved Codex CLI tasks, with optional tailnet-only access.","nahuelb\u002Fpstack-codex","nahuelb","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6378996?v=4","01M7BKBW6R13F440YA3DWXQ9GM","nes","01M7BKBW7A4FZ5STZT0CNXX3B6",1,"MIT","https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex\u002Fblob\u002Fmain\u002Fskills\u002Fmake-bot-ui\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: make-bot-ui\ndescription: Use when building a local page or dashboard whose fixed buttons start approved Codex CLI tasks, with optional tailnet-only access.\n---\n\n# Make a Codex task UI\n\nBuild a small local page whose buttons start fixed Codex tasks on the same computer. Keep the action map on the server. Do not let the browser supply a shell command, project path, model, flag, or free-form prompt.\n\nCodex scheduled tasks do not provide generic webhook ingress for local projects. Do not claim that a button wakes an existing desktop task. If the user needs an existing task to resume, stop and explain that this path is unsupported. Offer a scheduled task or a new bounded CLI run instead.\n\n## Confirm the action contract\n\nBefore writing code, agree on each button's:\n\n- stable action ID and label\n- fixed project directory\n- fixed prompt or prompt template with named, validated fields\n- allowed external effects\n- timeout and concurrency rule\n- success evidence shown in the UI\n\nReject actions that need secrets from the browser or accept arbitrary instructions. Keep credentials in the local process environment or an approved secret store. Never place credentials in HTML, JavaScript, URLs, logs, or committed files.\n\n## Build the local server\n\nServe the page from the same process that handles button requests. Bind to `127.0.0.1` by default.\n\nFor every request:\n\n1. Require `POST` and JSON.\n2. Enforce same-origin requests.\n3. Match one server-owned action ID.\n4. Validate every input against a narrow schema.\n5. Build the prompt from server-owned text.\n6. start `codex` with an argument array and no shell.\n7. Record the run ID, start time, exit status, and a redacted output summary.\n\nUse a bounded queue. Default to one active task. Reject duplicate action IDs while the same action is active. Set a timeout and terminate the child process if it expires.\n\nThe project directory must be an absolute path chosen during setup. Resolve it once and reject symlinks or paths outside the approved project roots.\n\n## Start Codex\n\nCheck that the `codex` executable exists before enabling buttons. Use `codex exec` for a new bounded run. Keep approval, sandbox, model, and reasoning settings at their configured defaults unless the user explicitly chose different values during setup.\n\nDo not add `--dangerously-bypass-approvals-and-sandbox`, `--full-auto`, or equivalent broad authority. Do not run a user-provided command through `sh`, `bash`, `zsh`, or another shell.\n\nIf a task needs external writes, encode the exact destination and effect in the fixed action contract. The button press authorizes only that declared action. It does not authorize new destinations or broader effects discovered during execution.\n\n## Optional tailnet access\n\nKeep localhost-only access unless the user asks for remote access. Prefer Tailscale Serve over binding the application to every network interface.\n\nIf Tailscale is already online, expose the localhost service only to the tailnet. Show the user the resulting tailnet URL. Do not install Tailscale or change its node configuration without explicit approval.\n\nDo not expose the service to the public internet. Do not use an unauthenticated public tunnel. Treat tailnet membership as transport control, not as authority to add arbitrary actions.\n\n## Verify it\n\nBefore calling the UI ready:\n\n1. Test an unknown action ID and expect rejection.\n2. Test malformed input and expect rejection.\n3. Confirm concurrent duplicate requests do not start two tasks.\n4. Run one harmless fixed action after the user approves the test.\n5. Confirm the UI reports the child exit status without exposing the full prompt or secrets.\n6. Confirm the repository contains no credentials or generated run logs.\n\nStop if the host lacks the Codex CLI, the project path cannot be fixed safely, or the requested action requires unsupported webhook delivery.\n","# Make a Codex task UI\n\nBuild a small local page whose buttons start fixed Codex tasks on the same computer. Keep the action map on the server. Do not let the browser supply a shell command, project path, model, flag, or free-form prompt.\n\nCodex scheduled tasks do not provide generic webhook ingress for local projects. Do not claim that a button wakes an existing desktop task. If the user needs an existing task to resume, stop and explain that this path is unsupported. Offer a scheduled task or a new bounded CLI run instead.\n\n## Confirm the action contract\n\nBefore writing code, agree on each button's:\n\n- stable action ID and label\n- fixed project directory\n- fixed prompt or prompt template with named, validated fields\n- allowed external effects\n- timeout and concurrency rule\n- success evidence shown in the UI\n\nReject actions that need secrets from the browser or accept arbitrary instructions. Keep credentials in the local process environment or an approved secret store. Never place credentials in HTML, JavaScript, URLs, logs, or committed files.\n\n## Build the local server\n\nServe the page from the same process that handles button requests. Bind to `127.0.0.1` by default.\n\nFor every request:\n\n1. Require `POST` and JSON.\n2. Enforce same-origin requests.\n3. Match one server-owned action ID.\n4. Validate every input against a narrow schema.\n5. Build the prompt from server-owned text.\n6. start `codex` with an argument array and no shell.\n7. Record the run ID, start time, exit status, and a redacted output summary.\n\nUse a bounded queue. Default to one active task. Reject duplicate action IDs while the same action is active. Set a timeout and terminate the child process if it expires.\n\nThe project directory must be an absolute path chosen during setup. Resolve it once and reject symlinks or paths outside the approved project roots.\n\n## Start Codex\n\nCheck that the `codex` executable exists before enabling buttons. Use `codex exec` for a new bounded run. Keep approval, sandbox, model, and reasoning settings at their configured defaults unless the user explicitly chose different values during setup.\n\nDo not add `--dangerously-bypass-approvals-and-sandbox`, `--full-auto`, or equivalent broad authority. Do not run a user-provided command through `sh`, `bash`, `zsh`, or another shell.\n\nIf a task needs external writes, encode the exact destination and effect in the fixed action contract. The button press authorizes only that declared action. It does not authorize new destinations or broader effects discovered during execution.\n\n## Optional tailnet access\n\nKeep localhost-only access unless the user asks for remote access. Prefer Tailscale Serve over binding the application to every network interface.\n\nIf Tailscale is already online, expose the localhost service only to the tailnet. Show the user the resulting tailnet URL. Do not install Tailscale or change its node configuration without explicit approval.\n\nDo not expose the service to the public internet. Do not use an unauthenticated public tunnel. Treat tailnet membership as transport control, not as authority to add arbitrary actions.\n\n## Verify it\n\nBefore calling the UI ready:\n\n1. Test an unknown action ID and expect rejection.\n2. Test malformed input and expect rejection.\n3. Confirm concurrent duplicate requests do not start two tasks.\n4. Run one harmless fixed action after the user approves the test.\n5. Confirm the UI reports the child exit status without exposing the full prompt or secrets.\n6. Confirm the repository contains no credentials or generated run logs.\n\nStop if the host lacks the Codex CLI, the project path cannot be fixed safely, or the requested action requires unsupported webhook delivery.\n",{"name":5,"description":7},"main","121c6fb0c47135a02ef927f76da76a3dbf176ff1","skills\u002Fmake-bot-ui",0,"https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex","https:\u002F\u002Fgithub.com\u002Fnahuelb","2026-09-28 19:04:18",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add nahuelb\u002Fpstack-codex --skill make-bot-ui",{"tool":37,"command":38},"bunx","bunx skills add nahuelb\u002Fpstack-codex --skill make-bot-ui",{"tool":40,"command":41},"pnpm","pnpm dlx skills add nahuelb\u002Fpstack-codex --skill make-bot-ui","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex\u002Fblob\u002Fmain\u002Fskills\u002Fmake-bot-ui\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",238,"https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex\u002Fblob\u002Fmain\u002Fskills\u002Fmake-bot-ui\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},"01M7BKFMNX7P2VNKW0G2AJ4TW4","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\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},"01M7BKFKCNQG7PNG4B6PTVXN1C","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex\u002Fblob\u002Fmain\u002Fskills\u002Funslop\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},"01M7BKFJ10QEAY0FNGG2AFJJ69","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex\u002Fblob\u002Fmain\u002Fskills\u002Ftypescript-best-practices\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},"01M7BKFEZPV6987Y9B3K3A3T84","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for $technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-writing\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},"01M7BKFCQ2ZV1WP6B57WEKFYGK","teach","Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.","https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex\u002Fblob\u002Fmain\u002Fskills\u002Fteach\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},"01M7BKFAGESR7AAYR2F2MZ0YTE","tdd","Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.","https:\u002F\u002Fgithub.com\u002Fnahuelb\u002Fpstack-codex\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]