[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79W4H86F4MF7GG2KA7DY845":3,"skill-same:01M79W4H86F4MF7GG2KA7DY845":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M79W4H86F4MF7GG2KA7DY845","fluttairbar",null,"Check the AI command-line tools on this device (Claude Code, Codex, OpenCode, Pi, Cursor Agent, Grok Build, fx, Ori, ZCode) for their installed and newest versions and safe updates, and how much of the Claude, Codex and Cursor subscriptions signed in here is used, which agent skills, hooks and instructions file each coding agent has, and whether conversation history is kept on two devices, with fluttAIrbar's command line `fluttairbar-cli`. Use when asked whether AI tools are up to date, how much usage or limit is left, when a limit resets, before updating an AI command-line tool, or which skills an agent has.","mmdmcy\u002FfluttAIrbar","mmdmcy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F112551618?v=4","01M79VZK60MN4F3KP7YQ49FBPF","01M79VZK6V57RCY60WD8G2FA0H",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmmdmcy\u002FfluttAIrbar\u002Fblob\u002Fmain\u002Fskills\u002Ffluttairbar\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: fluttairbar\ndescription: Check the AI command-line tools on this device (Claude Code, Codex, OpenCode, Pi, Cursor Agent, Grok Build, fx, Ori, ZCode) for their installed and newest versions and safe updates, and how much of the Claude, Codex and Cursor subscriptions signed in here is used, which agent skills, hooks and instructions file each coding agent has, and whether conversation history is kept on two devices, with fluttAIrbar's command line `fluttairbar-cli`. Use when asked whether AI tools are up to date, how much usage or limit is left, when a limit resets, before updating an AI command-line tool, or which skills an agent has.\n---\n\n# fluttAIrbar\n\n`fluttairbar-cli` reads what is installed and signed in on this device. It\nnever prints tokens, emails or account ids and never rewrites a credentials\nfile.\n\n## AI command-line tools\n\n```bash\nfluttairbar-cli harnesses --json            # every tool it knows\nfluttairbar-cli harnesses --json --only codex,claude\n```\n\nOne object per tool: `id`, `name`, `installed`, `currentVersion`,\n`latestVersion`, `updateAvailable`, `ageGateSatisfied`, `updateSource`\n(`npm`, `githubRelease` or `officialChannel`), `checkError`, and `configs`\n(each tool's config files, sensitive ones shown as present only).\n\n- `updateAvailable` with `ageGateSatisfied: false` means the release is\n  newer than 14 days: fluttAIrbar holds npm and GitHub releases back until\n  then. Say so; do not install it another way.\n- `officialChannel` tools (Claude Code's native install, Grok Build) update\n  through their own updater.\n\n## Usage limits\n\n```bash\nfluttairbar-cli usage --json\n```\n\n`{\"schema\":\"fluttairbar.usage.v1\",\"providers\":[...]}`, one provider each for\n`codex`, `claude` and `cursor`: `state` (`ok`, `signed-out`, `expired`,\n`stale`, `paused`, `error`), `detail` (what to do, in a sentence), `plan`, and\n`windows`, each with `label` (\"5 hours\", \"7 days\"), `used_percent` and\n`resets_at` (ISO 8601, UTC). Report the percentages and when they reset in\nthe user's local time. `stale` or `expired` means the user should run that\ntool once to renew its session; never renew it yourself.\n\n## Updating (ask first)\n\n```bash\nfluttairbar-cli harnesses --update --only codex   # one tool\nfluttairbar-cli harnesses --update                # every verified update\nfluttairbar-cli harnesses --sync-codex-daemon     # Codex CLI to its daemon's version\n```\n\nThese install software: ask the user before running them, and run them\nonly for tools the scan showed as ready. Exit 1 means an update failed; the\noutput says which.\n\n## Agent skills, hooks, shared instructions, quiz, conversation history\n\n```bash\nfluttairbar-cli skills --json               # skills per agent, and their instructions file\nfluttairbar-cli skills install --all -n     # what linking would do; nothing changes\nfluttairbar-cli hooks --json                # hooks per agent: installed, missing, different, no hooks\nfluttairbar-cli hooks install --all -n      # what adding them would do; nothing changes\nfluttairbar-cli conversations --json        # history kept here, last copies, `behind`\n```\n\n`skills` lists per skill and agent `linked`, `via DIR`, `copy`, `off` or\n`missing`, and for each agent whether its instructions file is `linked` to\nthe shared one. `conversations` shows `behind`: directions of the copy that\nkeep failing, with days, and `excluded`: per entry of `exclude` in\nconversations.toml, how many projects it keeps off the other device\n(never packed or copied; copies made before stay). `hooks` lists each declared hook's `state` for\nits agent; an agent without hook settings is `no hooks`, never guessed.\n`install`, `add`, `remove`, `on`, `off` (skills and hooks) and\n`conversations copy` change files: run them with `-n` first, show the plan,\nand add `-y` only when the user said so. Conversation history is never\ndeleted or pruned; `quiz` uses the agents' subscriptions, so run it only when\nasked.\n\n## Not installed?\n\nFrom a checkout of https:\u002F\u002Fgithub.com\u002Fmmdmcy\u002FfluttAIrbar on Linux:\n`tool\u002Finstall_linux.sh` (the tray app and `fluttairbar-cli`), or only the\ncommand line with `flutter pub get` and then `dart compile exe\ntool\u002Ffluttairbar_cli.dart -o ~\u002F.local\u002Fbin\u002Ffluttairbar-cli`. Both need the\nFlutter SDK; the compiled `fluttairbar-cli` does not, so it can be copied to\na machine without it.\n","# fluttAIrbar\n\n`fluttairbar-cli` reads what is installed and signed in on this device. It\nnever prints tokens, emails or account ids and never rewrites a credentials\nfile.\n\n## AI command-line tools\n\n```bash\nfluttairbar-cli harnesses --json            # every tool it knows\nfluttairbar-cli harnesses --json --only codex,claude\n```\n\nOne object per tool: `id`, `name`, `installed`, `currentVersion`,\n`latestVersion`, `updateAvailable`, `ageGateSatisfied`, `updateSource`\n(`npm`, `githubRelease` or `officialChannel`), `checkError`, and `configs`\n(each tool's config files, sensitive ones shown as present only).\n\n- `updateAvailable` with `ageGateSatisfied: false` means the release is\n  newer than 14 days: fluttAIrbar holds npm and GitHub releases back until\n  then. Say so; do not install it another way.\n- `officialChannel` tools (Claude Code's native install, Grok Build) update\n  through their own updater.\n\n## Usage limits\n\n```bash\nfluttairbar-cli usage --json\n```\n\n`{\"schema\":\"fluttairbar.usage.v1\",\"providers\":[...]}`, one provider each for\n`codex`, `claude` and `cursor`: `state` (`ok`, `signed-out`, `expired`,\n`stale`, `paused`, `error`), `detail` (what to do, in a sentence), `plan`, and\n`windows`, each with `label` (\"5 hours\", \"7 days\"), `used_percent` and\n`resets_at` (ISO 8601, UTC). Report the percentages and when they reset in\nthe user's local time. `stale` or `expired` means the user should run that\ntool once to renew its session; never renew it yourself.\n\n## Updating (ask first)\n\n```bash\nfluttairbar-cli harnesses --update --only codex   # one tool\nfluttairbar-cli harnesses --update                # every verified update\nfluttairbar-cli harnesses --sync-codex-daemon     # Codex CLI to its daemon's version\n```\n\nThese install software: ask the user before running them, and run them\nonly for tools the scan showed as ready. Exit 1 means an update failed; the\noutput says which.\n\n## Agent skills, hooks, shared instructions, quiz, conversation history\n\n```bash\nfluttairbar-cli skills --json               # skills per agent, and their instructions file\nfluttairbar-cli skills install --all -n     # what linking would do; nothing changes\nfluttairbar-cli hooks --json                # hooks per agent: installed, missing, different, no hooks\nfluttairbar-cli hooks install --all -n      # what adding them would do; nothing changes\nfluttairbar-cli conversations --json        # history kept here, last copies, `behind`\n```\n\n`skills` lists per skill and agent `linked`, `via DIR`, `copy`, `off` or\n`missing`, and for each agent whether its instructions file is `linked` to\nthe shared one. `conversations` shows `behind`: directions of the copy that\nkeep failing, with days, and `excluded`: per entry of `exclude` in\nconversations.toml, how many projects it keeps off the other device\n(never packed or copied; copies made before stay). `hooks` lists each declared hook's `state` for\nits agent; an agent without hook settings is `no hooks`, never guessed.\n`install`, `add`, `remove`, `on`, `off` (skills and hooks) and\n`conversations copy` change files: run them with `-n` first, show the plan,\nand add `-y` only when the user said so. Conversation history is never\ndeleted or pruned; `quiz` uses the agents' subscriptions, so run it only when\nasked.\n\n## Not installed?\n\nFrom a checkout of https:\u002F\u002Fgithub.com\u002Fmmdmcy\u002FfluttAIrbar on Linux:\n`tool\u002Finstall_linux.sh` (the tray app and `fluttairbar-cli`), or only the\ncommand line with `flutter pub get` and then `dart compile exe\ntool\u002Ffluttairbar_cli.dart -o ~\u002F.local\u002Fbin\u002Ffluttairbar-cli`. Both need the\nFlutter SDK; the compiled `fluttairbar-cli` does not, so it can be copied to\na machine without it.\n",{"name":5,"description":7},"main","62406a19cdd26cd016c18f75c06eb6e5834810f7","skills\u002Ffluttairbar","https:\u002F\u002Fgithub.com\u002Fmmdmcy\u002FfluttAIrbar","https:\u002F\u002Fgithub.com\u002Fmmdmcy","katteke.com"," ☦️\r\nChristian first, AI & ML Engineer second. ","2026-11-14 03:46:08",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add mmdmcy\u002FfluttAIrbar --skill fluttairbar",{"tool":37,"command":38},"bunx","bunx skills add mmdmcy\u002FfluttAIrbar --skill fluttairbar",{"tool":40,"command":41},"pnpm","pnpm dlx skills add mmdmcy\u002FfluttAIrbar --skill fluttairbar","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmmdmcy\u002FfluttAIrbar\u002Fblob\u002Fmain\u002Fskills\u002Ffluttairbar\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M79W4BCJA4M08K3YDNPVYQZ6","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\u002Fmmdmcy\u002FfluttAIrbar\u002Fblob\u002Fmain\u002Fplugins\u002Fpstack\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M79W47SVY4YFGV9ZAMG5SDGM","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002Fmmdmcy\u002FfluttAIrbar\u002Fblob\u002Fmain\u002Fplugins\u002Fpstack\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M79W45NJX78RKV82X85E1HRP","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fmmdmcy\u002FfluttAIrbar\u002Fblob\u002Fmain\u002Fplugins\u002Fpstack\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M79W4117DRK5VK8W6B4TP14B","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\u002Fmmdmcy\u002FfluttAIrbar\u002Fblob\u002Fmain\u002Fplugins\u002Fpstack\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M79W3XJZMS2TTSQYV13G1DRX","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\u002Fmmdmcy\u002FfluttAIrbar\u002Fblob\u002Fmain\u002Fplugins\u002Fpstack\u002Fskills\u002Fteach\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M79W3TFNAQHSWY3A7J37TFAB","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\u002Fmmdmcy\u002FfluttAIrbar\u002Fblob\u002Fmain\u002Fplugins\u002Fpstack\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]