[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75RCWAPRCP42JBTYBH3PH3K":3,"skill-same:01M75RCWAPRCP42JBTYBH3PH3K":44},{"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":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M75RCWAPRCP42JBTYBH3PH3K","thermos",null,"Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug\u002Fsecurity and code-quality branch audits.","TheDarkSkyXD\u002FSuperDevAgents","TheDarkSkyXD","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34119991?v=4","01M75491CAR2M915CJW2NKRTE7","01M75R09ATEWYMSRKW981X1EPY",1,"MIT","https:\u002F\u002Fgithub.com\u002FTheDarkSkyXD\u002FSuperDevAgents\u002Fblob\u002Fmain\u002Fplugins\u002Fsuperdev\u002Fskills\u002Fthermos\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: thermos\ndescription: \"Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug\u002Fsecurity and code-quality branch audits.\"\n---\n\n# Thermos\n\nOn Codex, read the [platform mapping](..\u002Fsuperdev-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fsuperdev-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\n\nOn Muse, read the [platform mapping](..\u002Fsuperdev-mode\u002Freferences\u002Fmuse-tools.md), including its per-skill notes, before following this skill.\n\nRead [the portable runtime contract](..\u002Fsuperdev-mode\u002Freferences\u002Fportable-runtime.md) before following this workflow.\n\nRun the two thermo review passes as async background subagents in parallel, then synthesize their results.\n\n## Workflow\n\n1. Determine the review scope from the user request, PR, current branch, or relevant changed files.\n2. Gather the diff and any file\u002Fcontext excerpts needed for reviewers to evaluate the change without guessing.\n3. Launch both subagents in the same message with `run_in_background: true`:\n   - `subagent_type: \"superdev:thermo-nuclear-review-subagent\"` for bugs, breakages, security, devex regressions, feature-flag leaks, and other branch-audit risks.\n   - `subagent_type: \"superdev:thermo-nuclear-code-quality-review-subagent\"` for maintainability, structure, file-size growth, spaghetti, abstractions, and codebase-health risks.\n\n   Set `model` on both to the `thermos reviewers` line in `superdev-models.md`, or to the default in [Models](#models) if the sheet or that line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If the `Agent` tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. Pick each subagent's reasoning level for the job, per the Subagents section of the **superdev-mode** skill.\n4. Pass each subagent the same scoped diff\u002Ffile context and ask it to return prioritized findings with file references and evidence.\n5. After both finish, synthesize the results with findings first, deduplicated across reviewers. Weight overlapping findings more heavily, resolve disagreements with your own judgment, and keep summaries brief.\n\nIf individual background summaries are already visible to the user, do not restate them wholesale. Surface the unified verdict, the highest-signal findings, and any remaining uncertainty.\n\n## Models\n\nRole defaults, stamped from `plugins\u002Fsuperdev\u002Fmodels.json` (edit there, rerun `tools\u002Fgenerate.mjs`). A matching role line in the `superdev-models.md` override sheet overrides each at runtime; `\u002Fsetup-superdev` writes it and lists its path per runtime.\n\n- thermos reviewers: `opus`\n\n## Reasoning effort\n\nA role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. On Claude Code, `session` sets no effort. On other runtimes, follow the platform mapping for `session`. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. Pass the level as the dispatch's effort field and keep the `subagent_type` you would otherwise use. That is `effort` on the Claude Code `Agent` call and `reasoning_effort` on Codex's `spawn_agent`. On Muse it is `effort` on a Workflow child; a `subagent_spawn` dispatch keeps the session's effort.\n","# Thermos\n\nOn Codex, read the [platform mapping](..\u002Fsuperdev-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fsuperdev-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\n\nOn Muse, read the [platform mapping](..\u002Fsuperdev-mode\u002Freferences\u002Fmuse-tools.md), including its per-skill notes, before following this skill.\n\nRead [the portable runtime contract](..\u002Fsuperdev-mode\u002Freferences\u002Fportable-runtime.md) before following this workflow.\n\nRun the two thermo review passes as async background subagents in parallel, then synthesize their results.\n\n## Workflow\n\n1. Determine the review scope from the user request, PR, current branch, or relevant changed files.\n2. Gather the diff and any file\u002Fcontext excerpts needed for reviewers to evaluate the change without guessing.\n3. Launch both subagents in the same message with `run_in_background: true`:\n   - `subagent_type: \"superdev:thermo-nuclear-review-subagent\"` for bugs, breakages, security, devex regressions, feature-flag leaks, and other branch-audit risks.\n   - `subagent_type: \"superdev:thermo-nuclear-code-quality-review-subagent\"` for maintainability, structure, file-size growth, spaghetti, abstractions, and codebase-health risks.\n\n   Set `model` on both to the `thermos reviewers` line in `superdev-models.md`, or to the default in [Models](#models) if the sheet or that line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If the `Agent` tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. Pick each subagent's reasoning level for the job, per the Subagents section of the **superdev-mode** skill.\n4. Pass each subagent the same scoped diff\u002Ffile context and ask it to return prioritized findings with file references and evidence.\n5. After both finish, synthesize the results with findings first, deduplicated across reviewers. Weight overlapping findings more heavily, resolve disagreements with your own judgment, and keep summaries brief.\n\nIf individual background summaries are already visible to the user, do not restate them wholesale. Surface the unified verdict, the highest-signal findings, and any remaining uncertainty.\n\n## Models\n\nRole defaults, stamped from `plugins\u002Fsuperdev\u002Fmodels.json` (edit there, rerun `tools\u002Fgenerate.mjs`). A matching role line in the `superdev-models.md` override sheet overrides each at runtime; `\u002Fsetup-superdev` writes it and lists its path per runtime.\n\n- thermos reviewers: `opus`\n\n## Reasoning effort\n\nA role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. On Claude Code, `session` sets no effort. On other runtimes, follow the platform mapping for `session`. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. Pass the level as the dispatch's effort field and keep the `subagent_type` you would otherwise use. That is `effort` on the Claude Code `Agent` call and `reasoning_effort` on Codex's `spawn_agent`. On Muse it is `effort` on a Workflow child; a `subagent_spawn` dispatch keeps the session's effort.\n",{"name":5,"description":7},"main","5440d26a8d527a55c691e544ae0e4e23e89e7157","plugins\u002Fsuperdev\u002Fskills\u002Fthermos",0,"https:\u002F\u002Fgithub.com\u002FTheDarkSkyXD\u002FSuperDevAgents","https:\u002F\u002Fgithub.com\u002FTheDarkSkyXD","2026-11-12 09:54:48",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add TheDarkSkyXD\u002FSuperDevAgents --skill thermos",{"tool":36,"command":37},"bunx","bunx skills add TheDarkSkyXD\u002FSuperDevAgents --skill thermos",{"tool":39,"command":40},"pnpm","pnpm dlx skills add TheDarkSkyXD\u002FSuperDevAgents --skill thermos","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTheDarkSkyXD\u002FSuperDevAgents\u002Fblob\u002Fmain\u002Fplugins\u002Fsuperdev\u002Fskills\u002Fthermos\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M75RDJ9BA2E6J9NNCB1N7K56","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\u002FTheDarkSkyXD\u002FSuperDevAgents\u002Fblob\u002Fmain\u002Fplugins\u002Fsuperdev\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M75RDFHCYADBVWTXG3AAZC09","what-did-i-get-done","Summarize authored commits over a user-specified time period into a concise update","https:\u002F\u002Fgithub.com\u002FTheDarkSkyXD\u002FSuperDevAgents\u002Fblob\u002Fmain\u002Fplugins\u002Fsuperdev\u002Fskills\u002Fwhat-did-i-get-done\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M75RDDK5WRB8PJ8PN7N6EWNZ","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\u002FTheDarkSkyXD\u002FSuperDevAgents\u002Fblob\u002Fmain\u002Fplugins\u002Fsuperdev\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M75RD9SZ9223AT30NA53XJ44","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002FTheDarkSkyXD\u002FSuperDevAgents\u002Fblob\u002Fmain\u002Fplugins\u002Fsuperdev\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M75RD7H5QRBN7DDGHX76JE4J","universal-architecture","Apply responsibility-based architecture and enforce import boundaries. Use for code placement, architecture reviews, adapters, CLI entry points, platform sharing, and ESLint boundary rules.","https:\u002F\u002Fgithub.com\u002FTheDarkSkyXD\u002FSuperDevAgents\u002Fblob\u002Fmain\u002Fplugins\u002Fsuperdev\u002Fskills\u002Funiversal-architecture\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M75RD5G2WGMRJKS5F7R7EW6N","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002FTheDarkSkyXD\u002FSuperDevAgents\u002Fblob\u002Fmain\u002Fplugins\u002Fsuperdev\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[]]