[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72VZQHRQN1SP7Y59R2P38V5":3,"skill-same:01M72VZQHRQN1SP7Y59R2P38V5":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M72VZQHRQN1SP7Y59R2P38V5","comet-hotfix",null,"Use the Classic preset to repair a localized defect. Use when the user explicitly invokes \u002Fcomet-hotfix, selects hotfix, or resumes workflow: hotfix.","rpamis\u002Fcomet","rpamis","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F153429891?v=4","01M72VXBR7EQYMM7KN8C19244V","01M72VXBRYC06QG0ZH0JBGV09V",3298,"MIT","https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fcomet-hotfix\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: comet-hotfix\ndescription: 'Use the Classic preset to repair a localized defect. Use when the user explicitly invokes \u002Fcomet-hotfix, selects hotfix, or resumes workflow: hotfix.'\n---\n\n# Comet Preset: Hotfix\n\nBefore starting or resuming, read and follow `comet-classic\u002Freference\u002Fclassic-layout.md`. All OpenSpec CLI calls must use the adapter, and all paths must use the bound `\u003Cclassic-*>` logical roots.\n\nA short defect-repair flow: open → build → root cause check → verify → archive. It skips brainstorming and a full implementation plan, and applies to repairing existing behavior without designing new features.\n\n**All applicability conditions must hold:**\n\n1. Repair an existing feature without adding a feature.\n2. No interface changes or architectural redesign.\n3. The scope is predictable. File counts are advisory and do not automatically require escalation; follow Preset scope in the SDK methods reference.\n\n**Escalation:** If the changes listed in Preset scope arise, the user decides whether to switch to the full `\u002Fcomet-classic` workflow.\n\nOn first entering a phase, handing off to a new Agent, or recovering context, read and follow [Task context and artifact language](..\u002Fcomet-classic\u002Freference\u002Fscripts.md#task-context-and-artifact-language). Prefer the current continuation or claimed Action's `contextRequest`; do not fetch it again during uninterrupted work in the same phase.\n\nPersonal memory stores reusable user information. Never save task summaries, progress, command output, or test results.\n\n## SDK Run path\n\nFirst read and follow [ordinary commands and checks](..\u002Fcomet\u002Freference\u002Fplatform-execution.md). New and old Runs use platform tools for ordinary commands and submit actual check reports to the original Run. Automatic upgrades do not restore old check executors. Phase preparation, user choices, task completion, and acceptance requirements remain effective.\n\nOn first entering the current SDK phase, changing Agent, or recovering context, read [Phase entry and recovery](..\u002Fcomet-classic\u002Freference\u002Fsdk-methods.md#phase-entry-and-recovery) and its current phase section. Reuse applicable instructions already in this session. Follow the current phase below; `nextAction.kind` recovery routing applies only to old responses without a continuation mode.\n\nWhen starting or resuming, reuse valid `agent.continuation` \u002F `data.nextAction` and the bound change, workspace, phase, and Run revision. Route by known `data.runtimeFormat`. Run `comet state next \u003Cchange-name> --json` only for a cold resume, external state change, or missing information. Follow this section for `sdk`; the SDK methods reference still governs applicability, reproduction and root cause checks, escalation, and file-count authorization. Submit state and evidence through the commands below. For `nextAction.kind: reconcile`, run `comet state check \u003Cchange-name> \u003Cphase> --recover --json` to inspect the original Action. Do not repeat implementation, checks, or Archive while its result is unknown.\n\n1. For a new change, choose isolation through [Workspace selection](..\u002Fcomet-classic\u002Freference\u002Fworkspace.md). Run `comet classic workspace prepare \u003Cname> --isolation \u003Cselected-isolation> --json` and enter the returned `projectRoot`. Create the OpenSpec base directories through [Entry and artifacts](..\u002Fcomet-classic\u002Freference\u002Fsdk-methods.md#entry-and-artifacts), run `comet state init \u003Cname> hotfix --isolation \u003Cselected-isolation>`, then `comet state select \u003Cname>` to bind Hook routing. Follow Entry and artifacts to create the concise OpenSpec artifacts. Preview with `comet guard \u003Cchange-name> open --json` and retain `data.approvalHash`. Present the Open artifacts and scope to the user. After explicit approval, run `comet guard \u003Cchange-name> open --apply --approval-hash \u003CapprovalHash>`. Changed artifacts require a fresh preview and approval; do not reuse an old hash. Open finishes only when the Run enters Build. New changes use `comet-state.yaml`; historical changes retain their original filename.\n2. When `hotfix.build.execute` is pending, resume Build in the same change, workspace, and Run. Do not initialize again or repeat Open. Follow Preset scope to reproduce the defect, preserve failure evidence, complete tasks, and check the root cause. For a material escalation signal, or a file-count limit without valid authorization, first run `comet state propose-escalation \u003Cchange-name> --reason \"\u003Creason>\"`. Present the reason and the effects of continuing hotfix or upgrading to full; retain `data.wait.proposalHash`. After the user chooses, run `comet state decide-escalation \u003Cchange-name> --proposal-hash \u003CproposalHash> --choice \u003Ccontinue|upgrade>`. `continue` still requires the reference's scope, risk, and ruling conditions. `upgrade` enters full Design in the same Run and workspace; immediately follow the entry to load comet-design. Resume a pending Wait with its original proposal; do not repropose or choose for the user.\n3. Once all tasks, necessary checks, and reviews are complete and the preset still applies, run `comet state complete-build \u003Cchange-name> --session \u003Cbuilder-execution-ref> --checks \u003Cchecks-json-file>` to submit actual results. This adds no user decision. Runtime validates tasks, configuration, workspace, and reports before entering Verify. On failure or uncertainty, inspect the original task through the returned current Action without repeating execution.\n4. When the Run enters Verify, **Immediately execute:** Use the Skill tool to load the comet-verify skill. Skipping this step is prohibited. Its SDK path completes the report, actual checks, and acceptance. When the Run enters Archive, **Immediately execute:** Use the Skill tool to load the comet-archive skill. Skipping this step is prohibited. Archive and delivery still require current user authorization. Claim completion only when the current successful result shows a completed Run; read `state next --json` if completion state is missing.\n\nAfter each advance, use that result's `agent.continuation` \u002F `data.nextAction`. Do not repeat next, select, or check while state is valid and complete; read again only on a cold resume, after external state changes, or for missing information. Resolve `decision`, `evidence`, or `reconcile` within the current Run; execute the corresponding step only for `action`.\n\nUse the actual `--session \u003Cbuilder-execution-ref>` for SDK Build; do not repeat it when already supplied.\n\n## Compat path\n\nThe remaining original Runtime steps apply only to `runtimeFormat: compat`. Read [Compat operations](reference\u002Fcompat.md) and continue its current phase. SDK does not load that reference.\n\n## Optional change walkthrough\n\nAt Build completion and before presenting Verify results, check the project `.comet\u002Fconfig.yaml` field `change_walkthrough` (enabled by default; only explicit `false` disables it). When enabled, read and execute [Change walkthrough](..\u002Fcomet\u002Freference\u002Fchange-walkthrough.md), use the shared template to generate or update the same `walkthrough.html`, and provide an opening link. When disabled, skip extra explanation, detailed instructions and rendering; retain the existing summary. Archive preserves existing pages with the materials and links to their actual archived location; it does not generate missing pages, add confirmation or rerun code checks for page updates.\n","# Comet Preset: Hotfix\n\nBefore starting or resuming, read and follow `comet-classic\u002Freference\u002Fclassic-layout.md`. All OpenSpec CLI calls must use the adapter, and all paths must use the bound `\u003Cclassic-*>` logical roots.\n\nA short defect-repair flow: open → build → root cause check → verify → archive. It skips brainstorming and a full implementation plan, and applies to repairing existing behavior without designing new features.\n\n**All applicability conditions must hold:**\n\n1. Repair an existing feature without adding a feature.\n2. No interface changes or architectural redesign.\n3. The scope is predictable. File counts are advisory and do not automatically require escalation; follow Preset scope in the SDK methods reference.\n\n**Escalation:** If the changes listed in Preset scope arise, the user decides whether to switch to the full `\u002Fcomet-classic` workflow.\n\nOn first entering a phase, handing off to a new Agent, or recovering context, read and follow [Task context and artifact language](..\u002Fcomet-classic\u002Freference\u002Fscripts.md#task-context-and-artifact-language). Prefer the current continuation or claimed Action's `contextRequest`; do not fetch it again during uninterrupted work in the same phase.\n\nPersonal memory stores reusable user information. Never save task summaries, progress, command output, or test results.\n\n## SDK Run path\n\nFirst read and follow [ordinary commands and checks](..\u002Fcomet\u002Freference\u002Fplatform-execution.md). New and old Runs use platform tools for ordinary commands and submit actual check reports to the original Run. Automatic upgrades do not restore old check executors. Phase preparation, user choices, task completion, and acceptance requirements remain effective.\n\nOn first entering the current SDK phase, changing Agent, or recovering context, read [Phase entry and recovery](..\u002Fcomet-classic\u002Freference\u002Fsdk-methods.md#phase-entry-and-recovery) and its current phase section. Reuse applicable instructions already in this session. Follow the current phase below; `nextAction.kind` recovery routing applies only to old responses without a continuation mode.\n\nWhen starting or resuming, reuse valid `agent.continuation` \u002F `data.nextAction` and the bound change, workspace, phase, and Run revision. Route by known `data.runtimeFormat`. Run `comet state next \u003Cchange-name> --json` only for a cold resume, external state change, or missing information. Follow this section for `sdk`; the SDK methods reference still governs applicability, reproduction and root cause checks, escalation, and file-count authorization. Submit state and evidence through the commands below. For `nextAction.kind: reconcile`, run `comet state check \u003Cchange-name> \u003Cphase> --recover --json` to inspect the original Action. Do not repeat implementation, checks, or Archive while its result is unknown.\n\n1. For a new change, choose isolation through [Workspace selection](..\u002Fcomet-classic\u002Freference\u002Fworkspace.md). Run `comet classic workspace prepare \u003Cname> --isolation \u003Cselected-isolation> --json` and enter the returned `projectRoot`. Create the OpenSpec base directories through [Entry and artifacts](..\u002Fcomet-classic\u002Freference\u002Fsdk-methods.md#entry-and-artifacts), run `comet state init \u003Cname> hotfix --isolation \u003Cselected-isolation>`, then `comet state select \u003Cname>` to bind Hook routing. Follow Entry and artifacts to create the concise OpenSpec artifacts. Preview with `comet guard \u003Cchange-name> open --json` and retain `data.approvalHash`. Present the Open artifacts and scope to the user. After explicit approval, run `comet guard \u003Cchange-name> open --apply --approval-hash \u003CapprovalHash>`. Changed artifacts require a fresh preview and approval; do not reuse an old hash. Open finishes only when the Run enters Build. New changes use `comet-state.yaml`; historical changes retain their original filename.\n2. When `hotfix.build.execute` is pending, resume Build in the same change, workspace, and Run. Do not initialize again or repeat Open. Follow Preset scope to reproduce the defect, preserve failure evidence, complete tasks, and check the root cause. For a material escalation signal, or a file-count limit without valid authorization, first run `comet state propose-escalation \u003Cchange-name> --reason \"\u003Creason>\"`. Present the reason and the effects of continuing hotfix or upgrading to full; retain `data.wait.proposalHash`. After the user chooses, run `comet state decide-escalation \u003Cchange-name> --proposal-hash \u003CproposalHash> --choice \u003Ccontinue|upgrade>`. `continue` still requires the reference's scope, risk, and ruling conditions. `upgrade` enters full Design in the same Run and workspace; immediately follow the entry to load comet-design. Resume a pending Wait with its original proposal; do not repropose or choose for the user.\n3. Once all tasks, necessary checks, and reviews are complete and the preset still applies, run `comet state complete-build \u003Cchange-name> --session \u003Cbuilder-execution-ref> --checks \u003Cchecks-json-file>` to submit actual results. This adds no user decision. Runtime validates tasks, configuration, workspace, and reports before entering Verify. On failure or uncertainty, inspect the original task through the returned current Action without repeating execution.\n4. When the Run enters Verify, **Immediately execute:** Use the Skill tool to load the comet-verify skill. Skipping this step is prohibited. Its SDK path completes the report, actual checks, and acceptance. When the Run enters Archive, **Immediately execute:** Use the Skill tool to load the comet-archive skill. Skipping this step is prohibited. Archive and delivery still require current user authorization. Claim completion only when the current successful result shows a completed Run; read `state next --json` if completion state is missing.\n\nAfter each advance, use that result's `agent.continuation` \u002F `data.nextAction`. Do not repeat next, select, or check while state is valid and complete; read again only on a cold resume, after external state changes, or for missing information. Resolve `decision`, `evidence`, or `reconcile` within the current Run; execute the corresponding step only for `action`.\n\nUse the actual `--session \u003Cbuilder-execution-ref>` for SDK Build; do not repeat it when already supplied.\n\n## Compat path\n\nThe remaining original Runtime steps apply only to `runtimeFormat: compat`. Read [Compat operations](reference\u002Fcompat.md) and continue its current phase. SDK does not load that reference.\n\n## Optional change walkthrough\n\nAt Build completion and before presenting Verify results, check the project `.comet\u002Fconfig.yaml` field `change_walkthrough` (enabled by default; only explicit `false` disables it). When enabled, read and execute [Change walkthrough](..\u002Fcomet\u002Freference\u002Fchange-walkthrough.md), use the shared template to generate or update the same `walkthrough.html`, and provide an opening link. When disabled, skip extra explanation, detailed instructions and rendering; retain the existing summary. Archive preserves existing pages with the materials and links to their actual archived location; it does not generate missing pages, add confirmation or rerun code checks for page updates.\n",{"name":5,"description":7},"master","9b2c15a8cbb321ae4e36d48849676e14d90eba24","assets\u002Fskills\u002Fcomet-hotfix",314,"https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet","https:\u002F\u002Fdocs.comet.rpamis.com","https:\u002F\u002Fgithub.com\u002Frpamis","More Efficient, Easier to Use, and Less Annoying","2026-11-15 00:26:58",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add rpamis\u002Fcomet --skill comet-hotfix",{"tool":38,"command":39},"bunx","bunx skills add rpamis\u002Fcomet --skill comet-hotfix",{"tool":41,"command":42},"pnpm","pnpm dlx skills add rpamis\u002Fcomet --skill comet-hotfix","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fcomet-hotfix\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",169,"https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fcomet-hotfix\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"reference\u002Fcompat.md",20255,"https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Fassets\u002Fskills\u002Fcomet-hotfix\u002Freference\u002Fcompat.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M72W3K6F0C2FKZ8DHABM49R7","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Feval\u002Flocal\u002Fskills\u002Fbenchmarks\u002Fdependency\u002Fsuperpowers\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M72W3HCPQ3GVMACX61QJTD4B","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Feval\u002Flocal\u002Fskills\u002Fbenchmarks\u002Fdependency\u002Fsuperpowers\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M72W3F8EVD3EK4NXJG40P84K","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Feval\u002Flocal\u002Fskills\u002Fbenchmarks\u002Fdependency\u002Fsuperpowers\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M72W3CA9YM0Y6CSXXTNCV1CA","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Feval\u002Flocal\u002Fskills\u002Fbenchmarks\u002Fdependency\u002Fsuperpowers\u002Fusing-git-worktrees\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M72W3AEH0F548GTPRNYRR3H3","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Feval\u002Flocal\u002Fskills\u002Fbenchmarks\u002Fdependency\u002Fsuperpowers\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M72W38EN8NEKX1YN4W9G19Y2","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002Frpamis\u002Fcomet\u002Fblob\u002Fmaster\u002Feval\u002Flocal\u002Fskills\u002Fbenchmarks\u002Fdependency\u002Fsuperpowers\u002Fsystematic-debugging\u002FSKILL.md",[],[]]