[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78BAJ6ZPWX092MJF0X0W33Z":3,"skill-same:01M78BAJ6ZPWX092MJF0X0W33Z":94},{"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":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M78BAJ6ZPWX092MJF0X0W33Z","architecture-first",null,"Decide module boundaries before the first file: what modules exist, which way dependencies point, who owns state, and what each module may know. Use when starting a project, service, site, API, or subsystem; adding a feature with no obvious home; resolving a circular import or inverted framework dependency; or writing an ARCHITECTURE.md or ADR. Do not use for a one-file script, throwaway experiment, bug fix inside an established seam, naming\u002Ffunction-shape cleanup (use code-complexity), an existing oversized module (use refactoring-safely), or capacity\u002Fdata scaling decisions (use system-and-data-design). This defines earned boundaries; it does not license speculative layers.","hermes-jarvis-bot\u002Fhermes-agent-config-kit","hermes-jarvis-bot","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F288284026?v=4","01M78AV3BBD4M67J3YWSQRKP1Q","01M78AV3C2SKH53E0PZMXAKTTS",1,"MIT","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: architecture-first\ndescription: >\n  Decide module boundaries before the first file: what modules exist, which way\n  dependencies point, who owns state, and what each module may know. Use when starting\n  a project, service, site, API, or subsystem; adding a feature with no obvious home;\n  resolving a circular import or inverted framework dependency; or writing an\n  ARCHITECTURE.md or ADR. Do not use for a one-file script, throwaway experiment, bug\n  fix inside an established seam, naming\u002Ffunction-shape cleanup (use code-complexity),\n  an existing oversized module (use refactoring-safely), or capacity\u002Fdata scaling\n  decisions (use system-and-data-design). This defines earned boundaries; it does not\n  license speculative layers.\n---\n\n# Architecture first — the shape before the first file\n\nMost bad structure is not a bad decision. It is an absent one: code goes where the\nsmallest diff puts it, and the smallest diff is always \"next to the last thing\". This\nskill exists to make the layout an explicit, cheap, early decision.\n\n## Scope guard — read first\n\nMatch the ceremony to the problem. Over-applying this is its own failure mode.\n\n| Situation | What this skill asks of you |\n|---|---|\n| Script, spike, one file, throwaway | Nothing. Skip. |\n| One module, \u003C500 lines, one reason to change | Name the module and its one job. Stop. |\n| Service \u002F site \u002F API, several concerns | The full pre-code checklist below. |\n| Multiple teams or deployables, shared domain | Checklist + bounded-context map + one ADR per boundary |\n| Multi-stage work or external release prerequisite | Checklist + a small stage map before the first implementation boundary |\n\n## The one law\n\n**Dependencies point inward, toward policy.** Business rules must not import the web\nframework, the ORM, the queue, or the file layout. The reverse is required.\n\nViolating it silently is the failure — a violation that is written down, with the reason\nand the cost, is a decision. A violation nobody named is erosion.\n\nPractical test: *could this module be exercised by a test with no network, no database\nand no framework?* If not, something outer leaked inward.\n\n## Pre-code checklist — before the first file\n\n1. **Name the modules by reason to change**, not by technical layer. `queue`, `billing`,\n   `catalog` — not `controllers`, `models`, `utils`. A module that changes for two\n   unrelated reasons is two modules.\n2. **Say what each module owns.** Especially state: every piece of mutable state has\n   exactly one owning module, and everyone else asks that module. Module-level mutable\n   state shared across features is the coupling that later makes a split expensive.\n3. **Draw the dependency arrows.** Any cycle is a design bug, not a build inconvenience.\n   Any arrow from domain to framework is inverted — fix it with an interface owned by\n   the inner side.\n4. **Establish the ubiquitous language.** One term, one meaning, in code and in speech.\n   If the same word means different things in two places, you have found a bounded\n   context boundary — draw it there.\n5. **Define the aggregates.** What must be consistent in one step, and what may lag.\n   Transaction boundaries follow this, not the other way round.\n6. **Write one vertical slice end-to-end** — UI to store to test — before broadening.\n   A slice that works proves the seams; six half-built layers prove nothing.\n7. **Record it.** One page: modules, ownership, data flow, external systems. Plus one\n   short ADR per decision that was genuinely a choice (context, options, decision,\n   consequences). Both live in git, next to the code.\n8. **Name the promotion boundaries.** When one verified result becomes the input to\n   another stage, name its contract, inputs, output, and invalidation keys before\n   implementation. A missing signer, VM, account, or remote service is a future\n   `BLOCKED` stage, not a reason to keep reopening already-proven code.\n\n## Stage contracts - when proof becomes an input\n\nFor multi-stage work, architecture includes delivery boundaries as well as module\nboundaries. Keep these states separate:\n\n- `VERIFIED`: the scoped behavior passed at one exact revision.\n- `SEALED`: the verified scope has an immutable receipt and may be consumed by a\n  following stage.\n- `BLOCKED`: a named external prerequisite is absent; upstream proof remains valid.\n- `SUPERSEDED`: a contract, source, or input digest changed, so a successor must be\n  verified instead of editing history.\n\nThe stage map is deliberately smaller than a release plan. For each boundary, name\nthe owning scope, frozen contract, inputs, output, and what invalidates it. Use the\nmachine-readable ledger only when there is a real hand-off between stages:\n`..\u002Fproof-verify\u002Freferences\u002Fproven-stage-contracts.md`. Do not add it to a one-file\nchange merely because the word \"stage\" exists.\n\n## Review checklist — once code exists\n\n- Does any inner module import an outer one? Name it or fix it.\n- Is there module-level mutable state touched by more than one feature?\n- Does one file hold routes\u002Fhandlers for more than one reason to change?\n- Are there two names for the same concept, or one name for two?\n- Can each module's tests run without the framework?\n- Does the ARCHITECTURE.md still describe what is actually there?\n\n## Fast decision table\n\n| Question | Default answer |\n|---|---|\n| Layer folders or feature folders? | Feature (vertical slices). Layer folders scatter one change across four directories. |\n| Where does validation live? | Input shape at the edge; business rules inside. Never only at the edge. |\n| Interface for a single implementation? | No — until a second caller or a test double actually needs it. |\n| Microservices? | Not yet. Modular monolith with real boundaries first; extract when a module needs its own deploy or scaling. |\n| Where does the ORM model live? | Outer. The domain object is not the row. |\n| Shared \"utils\" module? | A smell. Utils is where things go when nobody decided; name the reason instead. |\n\n## References — load on demand\n\n- `references\u002Fclean-architecture\u002Fboundaries-and-layers.md` — boundaries, Humble Object\n- `references\u002Fclean-architecture\u002Fsolid-and-components.md` — SOLID applied correctly, REP\u002FCCP\u002FCRP, ADP\u002FSDP\u002FSAP\n- `references\u002Fclean-architecture\u002Fdetails-and-code-organization.md` — DB\u002Fweb\u002Fframeworks as details\n- `references\u002Fclean-architecture\u002Fpython-implementation.md` — entities, use cases, repositories, wiring\n- `references\u002Fdomain-driven-design\u002Fbounded-contexts.md` — context mapping\n- `references\u002Fdomain-driven-design\u002Fubiquitous-language.md` — one term, one meaning\n- `references\u002Fdomain-driven-design\u002Fbuilding-blocks.md` — entities, value objects, aggregates\n- `references\u002Fdomain-driven-design\u002Fdomain-events.md`, `repositories-factories.md`, `strategic-design.md`\n- `*-original.md` — the source skills' own framework prose, kept verbatim\n\n## Gotchas\n\n- **\"We'll structure it later.\"** Later costs more per caller, and callers only grow. The\n  cheapest moment is before the first file; the second cheapest is now.\n- **Ceremony as architecture.** Four layers around a CRUD endpoint is not architecture,\n  it is cost. The scope guard above exists to stop this.\n- **Folders instead of boundaries.** Moving files without changing who imports whom\n  changes nothing. The arrows are the architecture; folders only display it.\n- **The domain importing the framework \"just for a type\".** That is the whole violation,\n  arriving politely.\n\n## Troubleshooting\n\n| Symptom | Cause | Fix |\n|---|---|---|\n| Circular import | Two modules both own part of one concept | Extract the shared concept into a third module both depend on |\n| One change touches six files across four folders | Layer folders, not feature folders | Re-cut by feature; keep the change local |\n| Tests need a live database to assert a rule | Rule lives outside the domain | Move the rule inward, inject the store |\n| Nobody can say which module owns X | Nobody decided | Decide now, write it in ARCHITECTURE.md, move the state |\n","# Architecture first — the shape before the first file\n\nMost bad structure is not a bad decision. It is an absent one: code goes where the\nsmallest diff puts it, and the smallest diff is always \"next to the last thing\". This\nskill exists to make the layout an explicit, cheap, early decision.\n\n## Scope guard — read first\n\nMatch the ceremony to the problem. Over-applying this is its own failure mode.\n\n| Situation | What this skill asks of you |\n|---|---|\n| Script, spike, one file, throwaway | Nothing. Skip. |\n| One module, \u003C500 lines, one reason to change | Name the module and its one job. Stop. |\n| Service \u002F site \u002F API, several concerns | The full pre-code checklist below. |\n| Multiple teams or deployables, shared domain | Checklist + bounded-context map + one ADR per boundary |\n| Multi-stage work or external release prerequisite | Checklist + a small stage map before the first implementation boundary |\n\n## The one law\n\n**Dependencies point inward, toward policy.** Business rules must not import the web\nframework, the ORM, the queue, or the file layout. The reverse is required.\n\nViolating it silently is the failure — a violation that is written down, with the reason\nand the cost, is a decision. A violation nobody named is erosion.\n\nPractical test: *could this module be exercised by a test with no network, no database\nand no framework?* If not, something outer leaked inward.\n\n## Pre-code checklist — before the first file\n\n1. **Name the modules by reason to change**, not by technical layer. `queue`, `billing`,\n   `catalog` — not `controllers`, `models`, `utils`. A module that changes for two\n   unrelated reasons is two modules.\n2. **Say what each module owns.** Especially state: every piece of mutable state has\n   exactly one owning module, and everyone else asks that module. Module-level mutable\n   state shared across features is the coupling that later makes a split expensive.\n3. **Draw the dependency arrows.** Any cycle is a design bug, not a build inconvenience.\n   Any arrow from domain to framework is inverted — fix it with an interface owned by\n   the inner side.\n4. **Establish the ubiquitous language.** One term, one meaning, in code and in speech.\n   If the same word means different things in two places, you have found a bounded\n   context boundary — draw it there.\n5. **Define the aggregates.** What must be consistent in one step, and what may lag.\n   Transaction boundaries follow this, not the other way round.\n6. **Write one vertical slice end-to-end** — UI to store to test — before broadening.\n   A slice that works proves the seams; six half-built layers prove nothing.\n7. **Record it.** One page: modules, ownership, data flow, external systems. Plus one\n   short ADR per decision that was genuinely a choice (context, options, decision,\n   consequences). Both live in git, next to the code.\n8. **Name the promotion boundaries.** When one verified result becomes the input to\n   another stage, name its contract, inputs, output, and invalidation keys before\n   implementation. A missing signer, VM, account, or remote service is a future\n   `BLOCKED` stage, not a reason to keep reopening already-proven code.\n\n## Stage contracts - when proof becomes an input\n\nFor multi-stage work, architecture includes delivery boundaries as well as module\nboundaries. Keep these states separate:\n\n- `VERIFIED`: the scoped behavior passed at one exact revision.\n- `SEALED`: the verified scope has an immutable receipt and may be consumed by a\n  following stage.\n- `BLOCKED`: a named external prerequisite is absent; upstream proof remains valid.\n- `SUPERSEDED`: a contract, source, or input digest changed, so a successor must be\n  verified instead of editing history.\n\nThe stage map is deliberately smaller than a release plan. For each boundary, name\nthe owning scope, frozen contract, inputs, output, and what invalidates it. Use the\nmachine-readable ledger only when there is a real hand-off between stages:\n`..\u002Fproof-verify\u002Freferences\u002Fproven-stage-contracts.md`. Do not add it to a one-file\nchange merely because the word \"stage\" exists.\n\n## Review checklist — once code exists\n\n- Does any inner module import an outer one? Name it or fix it.\n- Is there module-level mutable state touched by more than one feature?\n- Does one file hold routes\u002Fhandlers for more than one reason to change?\n- Are there two names for the same concept, or one name for two?\n- Can each module's tests run without the framework?\n- Does the ARCHITECTURE.md still describe what is actually there?\n\n## Fast decision table\n\n| Question | Default answer |\n|---|---|\n| Layer folders or feature folders? | Feature (vertical slices). Layer folders scatter one change across four directories. |\n| Where does validation live? | Input shape at the edge; business rules inside. Never only at the edge. |\n| Interface for a single implementation? | No — until a second caller or a test double actually needs it. |\n| Microservices? | Not yet. Modular monolith with real boundaries first; extract when a module needs its own deploy or scaling. |\n| Where does the ORM model live? | Outer. The domain object is not the row. |\n| Shared \"utils\" module? | A smell. Utils is where things go when nobody decided; name the reason instead. |\n\n## References — load on demand\n\n- `references\u002Fclean-architecture\u002Fboundaries-and-layers.md` — boundaries, Humble Object\n- `references\u002Fclean-architecture\u002Fsolid-and-components.md` — SOLID applied correctly, REP\u002FCCP\u002FCRP, ADP\u002FSDP\u002FSAP\n- `references\u002Fclean-architecture\u002Fdetails-and-code-organization.md` — DB\u002Fweb\u002Fframeworks as details\n- `references\u002Fclean-architecture\u002Fpython-implementation.md` — entities, use cases, repositories, wiring\n- `references\u002Fdomain-driven-design\u002Fbounded-contexts.md` — context mapping\n- `references\u002Fdomain-driven-design\u002Fubiquitous-language.md` — one term, one meaning\n- `references\u002Fdomain-driven-design\u002Fbuilding-blocks.md` — entities, value objects, aggregates\n- `references\u002Fdomain-driven-design\u002Fdomain-events.md`, `repositories-factories.md`, `strategic-design.md`\n- `*-original.md` — the source skills' own framework prose, kept verbatim\n\n## Gotchas\n\n- **\"We'll structure it later.\"** Later costs more per caller, and callers only grow. The\n  cheapest moment is before the first file; the second cheapest is now.\n- **Ceremony as architecture.** Four layers around a CRUD endpoint is not architecture,\n  it is cost. The scope guard above exists to stop this.\n- **Folders instead of boundaries.** Moving files without changing who imports whom\n  changes nothing. The arrows are the architecture; folders only display it.\n- **The domain importing the framework \"just for a type\".** That is the whole violation,\n  arriving politely.\n\n## Troubleshooting\n\n| Symptom | Cause | Fix |\n|---|---|---|\n| Circular import | Two modules both own part of one concept | Extract the shared concept into a third module both depend on |\n| One change touches six files across four folders | Layer folders, not feature folders | Re-cut by feature; keep the change local |\n| Tests need a live database to assert a rule | Rule lives outside the domain | Move the rule inward, inject the store |\n| Nobody can say which module owns X | Nobody decided | Decide now, write it in ARCHITECTURE.md, move the state |\n",{"name":5,"description":7},"main","07d02526f424fc814f8350d6b0b728e81576603d","upstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first",0,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot","2026-11-14 18:25:27",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill architecture-first",{"tool":36,"command":37},"bunx","bunx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill architecture-first",{"tool":39,"command":40},"pnpm","pnpm dlx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill architecture-first","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002FSKILL.md",true,[44,50,54,58,62,66,70,74,78,82,86,90],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"references\u002Fclean-architecture-original.md","REFERENCE","参考文档",13599,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fclean-architecture-original.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fclean-architecture\u002Fboundaries-and-layers.md",54534,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fclean-architecture\u002Fboundaries-and-layers.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fclean-architecture\u002Fdetails-and-code-organization.md",46032,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fclean-architecture\u002Fdetails-and-code-organization.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fclean-architecture\u002Fpython-implementation.md",69709,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fclean-architecture\u002Fpython-implementation.md",{"path":63,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fclean-architecture\u002Fsolid-and-components.md",47861,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fclean-architecture\u002Fsolid-and-components.md",{"path":67,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fdomain-driven-design-original.md",19122,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fdomain-driven-design-original.md",{"path":71,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fdomain-driven-design\u002Fbounded-contexts.md",13416,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fdomain-driven-design\u002Fbounded-contexts.md",{"path":75,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fdomain-driven-design\u002Fbuilding-blocks.md",13401,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fdomain-driven-design\u002Fbuilding-blocks.md",{"path":79,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fdomain-driven-design\u002Fdomain-events.md",12063,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fdomain-driven-design\u002Fdomain-events.md",{"path":83,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fdomain-driven-design\u002Frepositories-factories.md",15387,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fdomain-driven-design\u002Frepositories-factories.md",{"path":87,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fdomain-driven-design\u002Fstrategic-design.md",14536,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fdomain-driven-design\u002Fstrategic-design.md",{"path":91,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fdomain-driven-design\u002Fubiquitous-language.md",12660,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Farchitecture-first\u002Freferences\u002Fdomain-driven-design\u002Fubiquitous-language.md",[95,101,108,115,122,129],{"skillNo":96,"name":97,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M78BHH6VNT0MKZXGMP2F50X1","owner-voice","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fowner-voice\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":18},"01M78BHD34XJHAK6EMZ7J1M80X","humanize-russian","Редактировать русский текст для ясности и естественного звучания, сохраняя факты,\nтермины, источники и жанр. Использовать когда: убрать канцелярит, сделать текст\nживее, отредактировать русский черновик или статью перед публикацией.\nНе определяет авторство и не обещает обход детекторов. Для английского —\nhumanize-english; для структуры и доказательств — article-structure-review.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fhumanize-russian\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":18},"01M78BH9D09HCA7ECZMPEEAE5Y","humanize-english","Edit English drafts for clear, natural language while preserving facts, uncertainty,\ntechnical meaning, citations and genre. Use when: humanize this text, remove AI-style\nfiller, improve English prose, or edit an English article before publication.\nNot an authorship detector or a promise to bypass one. For Russian use\nhumanize-russian; for thesis\u002Fevidence and structure use article-structure-review.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fhumanize-english\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":18},"01M78BH44Q25YMA16MC6FKZ2WY","caveman","Ultra-compressed reply mode. Cuts output tokens ~65-75% by answering in terse \"caveman\" style while keeping full technical accuracy, and shapes what survives: action first, state restated every turn, concrete time estimates, visible wins. Intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says \"caveman\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or Russian \"пещерный режим\", \"говори как пещерный\", \"кратко\", \"меньше токенов\", \"экономь токены\" — or invokes \u002Fcaveman. Preserves the user's language (Russian in → Russian caveman out). Off only: \"stop caveman\" \u002F \"normal mode\" \u002F \"обычный режим\". Do not use merely because a response should be concise, and do not use when the user requests normal prose, a polished document, or exact wording.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fcaveman\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":18},"01M78BGY0JTMTW3J3YE5RQTHCK","article-structure-review","Проверить структуру технической статьи после черновика: задача читателя, жанр,\nопора значимых утверждений на доказательства и честные ограничения.\nUse after the first draft, before publication. Исправлять структуру, когда это\nвходит в запрос; не создавать обязательный конвейер из других навыков.\nДля локальной языковой редактуры — humanize-english или humanize-russian.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Farticle-structure-review\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":18},"01M78BGRJYZGK1TNTCHWGY32W3","video-post-production","Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master audio', 'export settings', 'platform requirements'. Covers FFmpeg patterns, audio chain, subtitle standards, and platform-specific export configs. Do NOT use to generate or animate the video frames\u002Fscenes in code (use remotion-production-guide), to write the script (use video-narrative-arc), or to evaluate script quality (use script-evaluator); this is the finishing stage applied to an already-rendered video.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fvideo-production\u002Fvideo-post-production\u002FSKILL.md",[],[]]