[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJD43JSGQSXDDH0RV72HYC":3,"skill-same:01M6MJD43JSGQSXDDH0RV72HYC":67},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6MJD43JSGQSXDDH0RV72HYC","maestro-frontier",null,"Maestro Frontier local multi-CLI fusion engine - compose or choose a read-only model panel, inspect the catalog, arm, disarm, or run it","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1566,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmbanderas\u002Fmaestro\u002Fcodex-skills\u002Fmaestro-frontier\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"frontier","maestro frontier","maestro","local","inspect","read-only","it","multi","panel","fusion","cli","compose","only","catalog","read","choose","model","engine","run","2026-11-10 10:12:30",false,"---\nname: maestro-frontier\ndescription: Maestro Frontier local multi-CLI fusion engine - compose or choose a read-only model panel, inspect the catalog, arm, disarm, or run it\nlicense: MIT\n---\n\nDrive the **Maestro Frontier** engine: a local multi-CLI fusion engine where a\nparallel panel feeds a judge and grounded synthesis. When a user asks to\ncompose or choose a model panel, route the request to `frontier compose` after\nconsulting `frontier catalog`; never guess a model or preset ID.\n\nWhen the trusted Maestro Codex plugin hook is installed, arming a non-`off`\nmode makes normal later Codex prompts auto-run through Frontier. `run` remains\nan advanced, manual one-off. Do not edit Frontier state files by hand.\n\n## Command launcher\n\nUse `maestro` when it is on `PATH`. If it is not, and this skill is loaded from\nthe Maestro Codex plugin, locate the plugin root by walking up from this\n`SKILL.md` until `.codex-plugin\u002Fplugin.json` is present, then run:\n\n```bash\nnode \"\u003Cmaestro-plugin-root>\u002Fbin\u002Fmaestro.cjs\" frontier ...\n```\n\nIn the examples below, `maestro frontier ...` means either the bare command or\nthat plugin-root launcher.\n\n## Catalog and compose a panel\n\nUse project scope from the repository root for state-changing commands:\n\n```bash\nmaestro frontier catalog\nmaestro frontier catalog --json\nmaestro frontier compose --models \u003Cmodel>,\u003Cmodel> --dry-run --scope codex-project\nmaestro frontier compose --models \u003Cmodel>,\u003Cmodel> --judge \u003Cmodel> --synth \u003Cmodel> --effort \u003Clevel> --scope codex-project\nmaestro frontier compose --models \u003Cmodel>,\u003Cmodel> --save \u003Cname> --scope codex-project\nmaestro frontier effort \u003Cauto|low|medium|high|xhigh|max|ultra> --scope codex-project\n```\n\n`frontier catalog` is the source of truth for models, presets, aliases,\nreadiness, and required configuration. `compose` accepts one to eight\ncomma-separated models. Judge and synth default to the first panel model.\n`--dry-run` changes nothing; a non-dry run saves and arms the resolved custom\nfusion panel. `--effort` persists one validated level across panel, judge, and\nsynth stages for selected effort-aware Claude and Codex models. `effort auto`\nreturns the armed panel to provider defaults.\n\n## Modes, inspection, and saved presets\n\n```bash\nmaestro frontier mode off --scope codex-project\nmaestro frontier mode single --model \u003Cmodel> --scope codex-project\nmaestro frontier mode fusion --preset \u003Cpreset> --scope codex-project\nmaestro frontier mode fusion --preset custom --models \u003Cmodel>,\u003Cmodel> --scope codex-project\nmaestro frontier status --scope codex-project\nmaestro frontier roster\nmaestro frontier preset save \u003Cname> --models \u003Cmodel>,\u003Cmodel> --judge \u003Cmodel> --synth \u003Cmodel> --scope codex-project\nmaestro frontier preset list --scope codex-project\nmaestro frontier preset delete \u003Cname> --scope codex-project\n```\n\nUse `catalog` before selecting any model or preset. `roster` reports only\nreadiness and configuration names, never secret or configured model values.\n\n## Current models, overrides, and release gate\n\n`opus` pins Claude Opus 5.5 (`claude-opus-5-5`), `fable` pins Fable 5.1\n(`claude-fable-5-1`), `sonnet-5` keeps Sonnet 5 (`claude-sonnet-5`), and\n`haiku` adds Haiku 4.5 (`claude-haiku-4-5-20251001`). Claude Code v2.1.280+\nis required for Opus 5.5; v2.1.257+ is required for Fable 5.1.\nOpus, Fable, and Sonnet support `low`, `medium`, `high`, `xhigh`, and `max`;\nHaiku has no effort flag.\nCodex selectors include `astra` (`gpt-6-astra`), `sol` (`gpt-6-sol`),\n`terra` (`gpt-5.6-terra`), and `luna` (`gpt-6-luna`), plus `auto-review` and\nthe retained GPT-5.5, GPT-5.4, GPT-5.4 Mini, and GPT-5.3 Codex Spark selectors.\nGPT-6 models support `low`, `medium`, `high`, `xhigh`, and `max` in Maestro’s\nUI, without `none` or `ultra`. Earlier explicit selectors and third-party\nadapters remain available.\nUse `frontier catalog` for exact aliases and supported effort levels.\n`MAESTRO_FRONTIER_MODEL_TERRA`, `MAESTRO_FRONTIER_MODEL_LUNA`, and\n`MAESTRO_FRONTIER_MODEL_SOL` remain optional model-ID overrides. Codex Desktop\n\u002F IDE sessions read those overrides from `~\u002F.codex\u002F.env`; restart the app and\nopen a new thread after changing it.\n\nBefore releasing Codex catalog changes, probe every first-party Codex selector:\n\n```bash\nnode frontier\u002Fsmoke.cjs\n```\n\nThis explicit release gate invokes those selectors through the normal\nread-only dispatch path.\n\n## Normal and debug use\n\nAfter mode is non-`off`, use ordinary Codex prompts; the trusted hook supplies\nthe Frontier result. Turn it off or run one manual prompt with:\n\n```bash\nmaestro frontier mode off --scope codex-project\nmaestro frontier run \"\u003Cprompt>\" --scope codex-project\n```\n\nAll panel, judge, and synthesizer subprocesses are one-shot and read-only:\nthey return text only and never edit the workspace, commit, or run autonomous\nloops. On `ERROR [\u003Creason>]: \u003Cdetail>`, relay the reason.\n\n## Indicator instruction\n\n\u003C!-- INDICATOR INSTRUCTION - apply every turn while this skill is active -->\n\nBefore composing your first reply each turn, run:\n\n```bash\nmaestro frontier status --scope codex-project\n```\n\nParse the returned JSON `mode` field:\n\n- If `mode` is not `off`, make the **first line** of your reply exactly:\n  `Maestro Frontier ON (\u003Clabel>)`\n  where `\u003Clabel>` is `single - \u003Cmodel>` or `fusion - \u003Cpreset>`; for a custom\n  preset use `fusion - custom (\u003Cmodel1>, \u003Cmodel2>, ...)`.\n- If `mode` is `off`, output no indicator line.\n\n\u003C!-- END INDICATOR INSTRUCTION -->\n","Drive the **Maestro Frontier** engine: a local multi-CLI fusion engine where a\nparallel panel feeds a judge and grounded synthesis. When a user asks to\ncompose or choose a model panel, route the request to `frontier compose` after\nconsulting `frontier catalog`; never guess a model or preset ID.\n\nWhen the trusted Maestro Codex plugin hook is installed, arming a non-`off`\nmode makes normal later Codex prompts auto-run through Frontier. `run` remains\nan advanced, manual one-off. Do not edit Frontier state files by hand.\n\n## Command launcher\n\nUse `maestro` when it is on `PATH`. If it is not, and this skill is loaded from\nthe Maestro Codex plugin, locate the plugin root by walking up from this\n`SKILL.md` until `.codex-plugin\u002Fplugin.json` is present, then run:\n\n```bash\nnode \"\u003Cmaestro-plugin-root>\u002Fbin\u002Fmaestro.cjs\" frontier ...\n```\n\nIn the examples below, `maestro frontier ...` means either the bare command or\nthat plugin-root launcher.\n\n## Catalog and compose a panel\n\nUse project scope from the repository root for state-changing commands:\n\n```bash\nmaestro frontier catalog\nmaestro frontier catalog --json\nmaestro frontier compose --models \u003Cmodel>,\u003Cmodel> --dry-run --scope codex-project\nmaestro frontier compose --models \u003Cmodel>,\u003Cmodel> --judge \u003Cmodel> --synth \u003Cmodel> --effort \u003Clevel> --scope codex-project\nmaestro frontier compose --models \u003Cmodel>,\u003Cmodel> --save \u003Cname> --scope codex-project\nmaestro frontier effort \u003Cauto|low|medium|high|xhigh|max|ultra> --scope codex-project\n```\n\n`frontier catalog` is the source of truth for models, presets, aliases,\nreadiness, and required configuration. `compose` accepts one to eight\ncomma-separated models. Judge and synth default to the first panel model.\n`--dry-run` changes nothing; a non-dry run saves and arms the resolved custom\nfusion panel. `--effort` persists one validated level across panel, judge, and\nsynth stages for selected effort-aware Claude and Codex models. `effort auto`\nreturns the armed panel to provider defaults.\n\n## Modes, inspection, and saved presets\n\n```bash\nmaestro frontier mode off --scope codex-project\nmaestro frontier mode single --model \u003Cmodel> --scope codex-project\nmaestro frontier mode fusion --preset \u003Cpreset> --scope codex-project\nmaestro frontier mode fusion --preset custom --models \u003Cmodel>,\u003Cmodel> --scope codex-project\nmaestro frontier status --scope codex-project\nmaestro frontier roster\nmaestro frontier preset save \u003Cname> --models \u003Cmodel>,\u003Cmodel> --judge \u003Cmodel> --synth \u003Cmodel> --scope codex-project\nmaestro frontier preset list --scope codex-project\nmaestro frontier preset delete \u003Cname> --scope codex-project\n```\n\nUse `catalog` before selecting any model or preset. `roster` reports only\nreadiness and configuration names, never secret or configured model values.\n\n## Current models, overrides, and release gate\n\n`opus` pins Claude Opus 5.5 (`claude-opus-5-5`), `fable` pins Fable 5.1\n(`claude-fable-5-1`), `sonnet-5` keeps Sonnet 5 (`claude-sonnet-5`), and\n`haiku` adds Haiku 4.5 (`claude-haiku-4-5-20251001`). Claude Code v2.1.280+\nis required for Opus 5.5; v2.1.257+ is required for Fable 5.1.\nOpus, Fable, and Sonnet support `low`, `medium`, `high`, `xhigh`, and `max`;\nHaiku has no effort flag.\nCodex selectors include `astra` (`gpt-6-astra`), `sol` (`gpt-6-sol`),\n`terra` (`gpt-5.6-terra`), and `luna` (`gpt-6-luna`), plus `auto-review` and\nthe retained GPT-5.5, GPT-5.4, GPT-5.4 Mini, and GPT-5.3 Codex Spark selectors.\nGPT-6 models support `low`, `medium`, `high`, `xhigh`, and `max` in Maestro’s\nUI, without `none` or `ultra`. Earlier explicit selectors and third-party\nadapters remain available.\nUse `frontier catalog` for exact aliases and supported effort levels.\n`MAESTRO_FRONTIER_MODEL_TERRA`, `MAESTRO_FRONTIER_MODEL_LUNA`, and\n`MAESTRO_FRONTIER_MODEL_SOL` remain optional model-ID overrides. Codex Desktop\n\u002F IDE sessions read those overrides from `~\u002F.codex\u002F.env`; restart the app and\nopen a new thread after changing it.\n\nBefore releasing Codex catalog changes, probe every first-party Codex selector:\n\n```bash\nnode frontier\u002Fsmoke.cjs\n```\n\nThis explicit release gate invokes those selectors through the normal\nread-only dispatch path.\n\n## Normal and debug use\n\nAfter mode is non-`off`, use ordinary Codex prompts; the trusted hook supplies\nthe Frontier result. Turn it off or run one manual prompt with:\n\n```bash\nmaestro frontier mode off --scope codex-project\nmaestro frontier run \"\u003Cprompt>\" --scope codex-project\n```\n\nAll panel, judge, and synthesizer subprocesses are one-shot and read-only:\nthey return text only and never edit the workspace, commit, or run autonomous\nloops. On `ERROR [\u003Creason>]: \u003Cdetail>`, relay the reason.\n\n## Indicator instruction\n\n\u003C!-- INDICATOR INSTRUCTION - apply every turn while this skill is active -->\n\nBefore composing your first reply each turn, run:\n\n```bash\nmaestro frontier status --scope codex-project\n```\n\nParse the returned JSON `mode` field:\n\n- If `mode` is not `off`, make the **first line** of your reply exactly:\n  `Maestro Frontier ON (\u003Clabel>)`\n  where `\u003Clabel>` is `single - \u003Cmodel>` or `fusion - \u003Cpreset>`; for a custom\n  preset use `fusion - custom (\u003Cmodel1>, \u003Cmodel2>, ...)`.\n- If `mode` is `off`, output no indicator line.\n\n\u003C!-- END INDICATOR INSTRUCTION -->\n",{"name":5,"license":15,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fmbanderas\u002Fmaestro\u002Fcodex-skills\u002Fmaestro-frontier",483,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-13 02:16:32",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill maestro-frontier",{"tool":59,"command":60},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill maestro-frontier",{"tool":62,"command":63},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill maestro-frontier","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmbanderas\u002Fmaestro\u002Fcodex-skills\u002Fmaestro-frontier\u002FSKILL.md",true,[],[68,77,84,91,117,142],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":76},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":76},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":76},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":38},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,29,115,116],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","when","you","done","reviewer","io","change","merge","past",{"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":72,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":38},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[124,125,126,113,127,128,129,130,131,132,133,134,135,136,103,137,138,139,140,141],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":159,"publishedAt":38},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[148,153,156],{"categoryNo":149,"categoryName":150,"taxonomyType":151,"taxonomyTypeDesc":152},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":154,"categoryName":155,"taxonomyType":151,"taxonomyTypeDesc":152},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":157,"categoryName":158,"taxonomyType":151,"taxonomyTypeDesc":152},"01JBSEEDCAT000000000000010","后端与接口",[144,160,161,162,163,164,165,138,166,104,167,168,169,170,109,171,172,173,174,175],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]