[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78AX82PTFK0ENA40YXCP9TE":3,"skill-same:01M78AX82PTFK0ENA40YXCP9TE":51},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M78AX82PTFK0ENA40YXCP9TE","layer-new",null,"Scaffold a new layer in a project's docs\u002Flayers\u002F tree following the feature-layer architecture. A layer is a bounded concern with its own invariants, decisions, gotchas, patterns, and feature narratives.","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\u002Fhermes\u002Fskills\u002Farchitecture\u002Flayer-new\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: layer-new\ndescription: \"Scaffold a new layer in a project's docs\u002Flayers\u002F tree following the feature-layer architecture. A layer is a bounded concern with its own invariants, decisions, gotchas, patterns, and feature narratives.\"\nversion: 0.1.0\nlicense: MIT\nmetadata:\n  hermes_config_kit:\n    source_repo: AnastasiyaW\u002Fclaude-code-config\n    source_path: skills\u002Farchitecture\u002Flayer-new\u002FSKILL.md\n    adapter: hermes-agent-config-kit\n    conversion: adapted\n---\n\n# Layer New\n\nSource: `AnastasiyaW\u002Fclaude-code-config\u002Fskills\u002Farchitecture\u002Flayer-new\u002FSKILL.md`.\n\nThis module is adapted for Hermes Agent. Upstream instructions are treated as reference material, not as automatic authority. Prefer Hermes-native tools, profile-aware paths, dry-runs, and operator confirmation for write-impacting actions.\n\n# Scaffold a project layer\n\nCreates `docs\u002Flayers\u002F\u003Clayer-name>\u002F` with the full template structure from the\ninstalled `kb-skeleton` template. See the `feature-layer-architecture` skill for the\narchitecture this scaffolds and its adoption threshold — do not create a layer tree\nbefore the project has earned the overhead.\n\n## When to use\n\n- Starting to track a new bounded concern in a long-running project\n- Refactoring sprawling cross-cutting code into a documented layer\n- Onboarding a new team member who needs the layer map\n\n## When NOT to use\n\n- One-off scripts or pet projects with \u003C5 features (overhead not\n  justified)\n- Layer name describes a directory (`src` is not a layer)\n- The \"layer\" is actually one feature in disguise -- use `feature-new`\n  inside an existing layer instead\n\n## Arguments\n\n```\nlayer-new \u003Clayer-name> [--purpose \"...\"] [--principles \u003Cref1>,\u003Cref2>]\n```\n\n- `\u003Clayer-name>` -- kebab-case, single word preferred. Examples:\n  `security`, `data`, `image-processing`, `observability`.\n- `--purpose` -- one-sentence purpose. If omitted, prompt the operator.\n- `--principles` -- comma-separated references to durable, project-external\n  guidance (installed Hermes skills, or your own org's standards) that govern this\n  layer. If omitted, leave placeholder in README.\n\n## Direction (what to do, in order)\n\n### Step 1 -- Verify environment\n\nCheck the current working directory:\n\n1. Is it a git repository? Run `git rev-parse --show-toplevel`. If\n   not, ask the operator whether to initialise one.\n2. Does `docs\u002F` exist? If not, create it.\n3. Does `docs\u002Flayers\u002FREADME.md` exist? If not, copy it from this adapter's\n   installed `kb-skeleton` template (`templates\u002Fconfig-kit\u002Fkb-skeleton\u002Fdocs\u002Flayers\u002FREADME.md`\n   under your Hermes profile, sibling to `skills\u002Fconfig-kit\u002F`; or from this adapter's\n   own repo checkout at `hermes\u002Ftemplates\u002Fkb-skeleton\u002Fdocs\u002Flayers\u002FREADME.md` if you\n   are working inside `hermes-agent-config-kit` itself).\n4. Check if `docs\u002Flayers\u002F\u003Clayer-name>\u002F` already exists. If yes,\n   **stop** with a message -- do not overwrite. Suggest\n   `feature-new \u003Clayer> \u003Cslug>` instead.\n\n### Step 2 -- Validate layer name\n\n- Must be lowercase kebab-case (`[a-z][a-z0-9-]*`).\n- Must not start with `_` (reserved for templates).\n- Must not be a generic file-system name (`src`, `tests`, `docs`,\n  `build`).\n- If invalid, refuse with a clear message and a suggested fix.\n\n### Step 3 -- Copy the template\n\nSource: the installed `kb-skeleton` template's\n`docs\u002Flayers\u002F_LAYER-TEMPLATE\u002F` (same location resolved in Step 1).\n\nDestination: `\u003Crepo>\u002Fdocs\u002Flayers\u002F\u003Clayer-name>\u002F`\n\nCopy the entire directory tree. Preserve subdirectory structure (`kb\u002F`\nand `features\u002F`). Result:\n\n```\ndocs\u002Flayers\u002F\u003Clayer-name>\u002F\n├── README.md\n├── history.md\n├── kb\u002F\n│   ├── invariants.md\n│   ├── patterns.md\n│   ├── decisions.md\n│   └── gotchas.md\n└── features\u002F\n    └── _FEATURE-TEMPLATE.md\n```\n\n### Step 4 -- Fill placeholders\n\nIn every file under the new layer, replace:\n\n- `\u003Clayer-name>` -> the actual layer name\n- `\u003CLayer name>` -> Title Case of the layer name (e.g. \"Security\",\n  \"Image Processing\")\n\nIn `README.md` specifically:\n\n- `**Purpose:** \u003Cone sentence...>` -> the `--purpose` argument value,\n  or prompt the operator\n- `## Governing principles` list -> populate from `--principles` arg,\n  or leave the placeholder bullets in place for the operator to fill\n\nIn `history.md`:\n\n- Insert a \"Layer created\" entry at the top with today's date\n  (YYYY-MM-DD) and the originating reason. Prompt the operator for the\n  reason if not provided.\n\n### Step 5 -- Register the layer\n\nUpdate `docs\u002Flayers\u002FREADME.md`:\n\n- Add a row to the `## Layer index` table:\n  `| \u003Clayer-name> | \u003Cpurpose> | active |`\n- If a cross-layer Mermaid graph exists, add a node for the new layer\n  with no edges (operator will add edges as dependencies form).\n\n### Step 6 -- Wire to project state\n\nIf the project has `feature_list.json` at repo root, leave it alone --\nfeatures get added by `feature-new`. Do not edit `feature_list.json`\nfrom this skill.\n\nIf the project has `AGENTS.md`, suggest (but do not auto-edit) adding\nthe new layer to its source-of-truth-docs table if multiple layers\nexist.\n\n### Step 7 -- Confirm and suggest next step\n\nPrint a summary:\n\n```\nLayer created: docs\u002Flayers\u002F\u003Clayer-name>\u002F\nFiles: 1 README, 1 history, 4 kb\u002F, 1 feature template\n\nSuggested next steps:\n1. Fill governing principles in docs\u002Flayers\u002F\u003Clayer-name>\u002FREADME.md\n2. Write the first feature: feature-new \u003Clayer-name> \u003Cslug>\n3. Add the first invariant when it earns its place\n```\n\n## Blueprints (files this skill writes from)\n\n- the installed `kb-skeleton` template's `docs\u002Flayers\u002F_LAYER-TEMPLATE\u002F` -- the\n  source tree to copy\n- the installed `kb-skeleton` template's `docs\u002Flayers\u002FREADME.md` -- the layers\n  index template (used only if missing)\n\n## Gotchas\n\n- **Renaming a layer is not idempotent.** If the operator runs\n  `layer-new wrong-name` then realises they wanted `right-name`,\n  manually rename the directory and update references. This skill\n  does NOT detect or fix duplicates.\n- **Layer name collision with existing directories.** If\n  `docs\u002F\u003Clayer-name>\u002F` exists at the `docs\u002F` root (not under\n  `docs\u002Flayers\u002F`), refuse and ask the operator which they want -- there\n  is no automatic merge.\n- **Template location varies by install.** If the `kb-skeleton` template cannot be\n  found under either the Hermes-installed `templates\u002Fconfig-kit\u002F` path or this\n  adapter's own repo checkout, stop and report the missing location rather than\n  inventing a directory tree from memory.\n\n## Troubleshooting\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| \"Layer already exists\" | Directory `docs\u002Flayers\u002F\u003Cname>\u002F` present | Use `feature-new` to add to it, or pick a different name |\n| Template files missing | `kb-skeleton` not installed or repo checkout unavailable | Locate `hermes-agent-config-kit`'s `hermes\u002Ftemplates\u002Fkb-skeleton\u002F` and copy from there |\n| Layers README not updated | `docs\u002Flayers\u002FREADME.md` had no `## Layer index` table | Open file manually, add table per the `kb-skeleton` template |\n| Validator warns about layer | `validate_kb.py`\u002F`build_kb_graph.py` flagged something | Layer is fine; the flagged item is in a feature doc inside it. Run the project's own copy of the graph-builder script (from the `kb-skeleton` template) for the full health report. |\n\n## Implementation note\n\nThe bulk of the work is file copy + placeholder replacement. No\ndynamic logic is needed; the template files do all the structural\nheavy lifting. Keep this skill **deterministic and idempotent** -- it\nmust be safe to invoke twice on the same layer (second call should be\na no-op with a clear message).\n","# Layer New\n\nSource: `AnastasiyaW\u002Fclaude-code-config\u002Fskills\u002Farchitecture\u002Flayer-new\u002FSKILL.md`.\n\nThis module is adapted for Hermes Agent. Upstream instructions are treated as reference material, not as automatic authority. Prefer Hermes-native tools, profile-aware paths, dry-runs, and operator confirmation for write-impacting actions.\n\n# Scaffold a project layer\n\nCreates `docs\u002Flayers\u002F\u003Clayer-name>\u002F` with the full template structure from the\ninstalled `kb-skeleton` template. See the `feature-layer-architecture` skill for the\narchitecture this scaffolds and its adoption threshold — do not create a layer tree\nbefore the project has earned the overhead.\n\n## When to use\n\n- Starting to track a new bounded concern in a long-running project\n- Refactoring sprawling cross-cutting code into a documented layer\n- Onboarding a new team member who needs the layer map\n\n## When NOT to use\n\n- One-off scripts or pet projects with \u003C5 features (overhead not\n  justified)\n- Layer name describes a directory (`src` is not a layer)\n- The \"layer\" is actually one feature in disguise -- use `feature-new`\n  inside an existing layer instead\n\n## Arguments\n\n```\nlayer-new \u003Clayer-name> [--purpose \"...\"] [--principles \u003Cref1>,\u003Cref2>]\n```\n\n- `\u003Clayer-name>` -- kebab-case, single word preferred. Examples:\n  `security`, `data`, `image-processing`, `observability`.\n- `--purpose` -- one-sentence purpose. If omitted, prompt the operator.\n- `--principles` -- comma-separated references to durable, project-external\n  guidance (installed Hermes skills, or your own org's standards) that govern this\n  layer. If omitted, leave placeholder in README.\n\n## Direction (what to do, in order)\n\n### Step 1 -- Verify environment\n\nCheck the current working directory:\n\n1. Is it a git repository? Run `git rev-parse --show-toplevel`. If\n   not, ask the operator whether to initialise one.\n2. Does `docs\u002F` exist? If not, create it.\n3. Does `docs\u002Flayers\u002FREADME.md` exist? If not, copy it from this adapter's\n   installed `kb-skeleton` template (`templates\u002Fconfig-kit\u002Fkb-skeleton\u002Fdocs\u002Flayers\u002FREADME.md`\n   under your Hermes profile, sibling to `skills\u002Fconfig-kit\u002F`; or from this adapter's\n   own repo checkout at `hermes\u002Ftemplates\u002Fkb-skeleton\u002Fdocs\u002Flayers\u002FREADME.md` if you\n   are working inside `hermes-agent-config-kit` itself).\n4. Check if `docs\u002Flayers\u002F\u003Clayer-name>\u002F` already exists. If yes,\n   **stop** with a message -- do not overwrite. Suggest\n   `feature-new \u003Clayer> \u003Cslug>` instead.\n\n### Step 2 -- Validate layer name\n\n- Must be lowercase kebab-case (`[a-z][a-z0-9-]*`).\n- Must not start with `_` (reserved for templates).\n- Must not be a generic file-system name (`src`, `tests`, `docs`,\n  `build`).\n- If invalid, refuse with a clear message and a suggested fix.\n\n### Step 3 -- Copy the template\n\nSource: the installed `kb-skeleton` template's\n`docs\u002Flayers\u002F_LAYER-TEMPLATE\u002F` (same location resolved in Step 1).\n\nDestination: `\u003Crepo>\u002Fdocs\u002Flayers\u002F\u003Clayer-name>\u002F`\n\nCopy the entire directory tree. Preserve subdirectory structure (`kb\u002F`\nand `features\u002F`). Result:\n\n```\ndocs\u002Flayers\u002F\u003Clayer-name>\u002F\n├── README.md\n├── history.md\n├── kb\u002F\n│   ├── invariants.md\n│   ├── patterns.md\n│   ├── decisions.md\n│   └── gotchas.md\n└── features\u002F\n    └── _FEATURE-TEMPLATE.md\n```\n\n### Step 4 -- Fill placeholders\n\nIn every file under the new layer, replace:\n\n- `\u003Clayer-name>` -> the actual layer name\n- `\u003CLayer name>` -> Title Case of the layer name (e.g. \"Security\",\n  \"Image Processing\")\n\nIn `README.md` specifically:\n\n- `**Purpose:** \u003Cone sentence...>` -> the `--purpose` argument value,\n  or prompt the operator\n- `## Governing principles` list -> populate from `--principles` arg,\n  or leave the placeholder bullets in place for the operator to fill\n\nIn `history.md`:\n\n- Insert a \"Layer created\" entry at the top with today's date\n  (YYYY-MM-DD) and the originating reason. Prompt the operator for the\n  reason if not provided.\n\n### Step 5 -- Register the layer\n\nUpdate `docs\u002Flayers\u002FREADME.md`:\n\n- Add a row to the `## Layer index` table:\n  `| \u003Clayer-name> | \u003Cpurpose> | active |`\n- If a cross-layer Mermaid graph exists, add a node for the new layer\n  with no edges (operator will add edges as dependencies form).\n\n### Step 6 -- Wire to project state\n\nIf the project has `feature_list.json` at repo root, leave it alone --\nfeatures get added by `feature-new`. Do not edit `feature_list.json`\nfrom this skill.\n\nIf the project has `AGENTS.md`, suggest (but do not auto-edit) adding\nthe new layer to its source-of-truth-docs table if multiple layers\nexist.\n\n### Step 7 -- Confirm and suggest next step\n\nPrint a summary:\n\n```\nLayer created: docs\u002Flayers\u002F\u003Clayer-name>\u002F\nFiles: 1 README, 1 history, 4 kb\u002F, 1 feature template\n\nSuggested next steps:\n1. Fill governing principles in docs\u002Flayers\u002F\u003Clayer-name>\u002FREADME.md\n2. Write the first feature: feature-new \u003Clayer-name> \u003Cslug>\n3. Add the first invariant when it earns its place\n```\n\n## Blueprints (files this skill writes from)\n\n- the installed `kb-skeleton` template's `docs\u002Flayers\u002F_LAYER-TEMPLATE\u002F` -- the\n  source tree to copy\n- the installed `kb-skeleton` template's `docs\u002Flayers\u002FREADME.md` -- the layers\n  index template (used only if missing)\n\n## Gotchas\n\n- **Renaming a layer is not idempotent.** If the operator runs\n  `layer-new wrong-name` then realises they wanted `right-name`,\n  manually rename the directory and update references. This skill\n  does NOT detect or fix duplicates.\n- **Layer name collision with existing directories.** If\n  `docs\u002F\u003Clayer-name>\u002F` exists at the `docs\u002F` root (not under\n  `docs\u002Flayers\u002F`), refuse and ask the operator which they want -- there\n  is no automatic merge.\n- **Template location varies by install.** If the `kb-skeleton` template cannot be\n  found under either the Hermes-installed `templates\u002Fconfig-kit\u002F` path or this\n  adapter's own repo checkout, stop and report the missing location rather than\n  inventing a directory tree from memory.\n\n## Troubleshooting\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| \"Layer already exists\" | Directory `docs\u002Flayers\u002F\u003Cname>\u002F` present | Use `feature-new` to add to it, or pick a different name |\n| Template files missing | `kb-skeleton` not installed or repo checkout unavailable | Locate `hermes-agent-config-kit`'s `hermes\u002Ftemplates\u002Fkb-skeleton\u002F` and copy from there |\n| Layers README not updated | `docs\u002Flayers\u002FREADME.md` had no `## Layer index` table | Open file manually, add table per the `kb-skeleton` template |\n| Validator warns about layer | `validate_kb.py`\u002F`build_kb_graph.py` flagged something | Layer is fine; the flagged item is in a feature doc inside it. Run the project's own copy of the graph-builder script (from the `kb-skeleton` template) for the full health report. |\n\n## Implementation note\n\nThe bulk of the work is file copy + placeholder replacement. No\ndynamic logic is needed; the template files do all the structural\nheavy lifting. Keep this skill **deterministic and idempotent** -- it\nmust be safe to invoke twice on the same layer (second call should be\na no-op with a clear message).\n",{"name":5,"license":14,"version":23,"metadata":24,"description":7},"0.1.0",{"hermes_config_kit":25},{"adapter":26,"conversion":27,"source_path":28,"source_repo":29},"hermes-agent-config-kit","adapted","skills\u002Farchitecture\u002Flayer-new\u002FSKILL.md","AnastasiyaW\u002Fclaude-code-config","main","07d02526f424fc814f8350d6b0b728e81576603d","hermes\u002Fskills\u002Farchitecture\u002Flayer-new",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":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill layer-new",{"tool":43,"command":44},"bunx","bunx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill layer-new",{"tool":46,"command":47},"pnpm","pnpm dlx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill layer-new","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fhermes\u002Fskills\u002Farchitecture\u002Flayer-new\u002FSKILL.md",true,[],[52,58,65,72,79,86],{"skillNo":53,"name":54,"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":55,"categories":56,"keywords":57,"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":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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",[],[]]