[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78BCHDTS2MXKV5NA7SC6H28":3,"skill-same:01M78BCHDTS2MXKV5NA7SC6H28":50},{"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},"01M78BCHDTS2MXKV5NA7SC6H28","repo-map",null,"Ranked symbol map of a codebase within a token budget — a compact \"what matters in this repo\" before reading files. Use when starting work in an unfamiliar\u002Flarge codebase, before a refactor or deep-review fan-out, when you need JIT context instead of dumping whole files, or asked \"give me a map of this repo \u002F where are the important functions \u002F what's the structure\". Zero-dependency (stdlib only); Aider-inspired regex extraction and PageRank ranking, not a tree-sitter parser. Do NOT use to find correctness\u002Fsecurity defects in a change or to audit a diff; use deep-review for that (this only ranks and lists symbols, it does not evaluate code quality).","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\u002Frepo-map\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: repo-map\ndescription: Ranked symbol map of a codebase within a token budget — a compact \"what matters in this repo\" before reading files. Use when starting work in an unfamiliar\u002Flarge codebase, before a refactor or deep-review fan-out, when you need JIT context instead of dumping whole files, or asked \"give me a map of this repo \u002F where are the important functions \u002F what's the structure\". Zero-dependency (stdlib only); Aider-inspired regex extraction and PageRank ranking, not a tree-sitter parser. Do NOT use to find correctness\u002Fsecurity defects in a change or to audit a diff; use deep-review for that (this only ranks and lists symbols, it does not evaluate code quality).\n---\n\n# repo-map\n\nProduces a **ranked list of the structurally-important symbol definitions** in a\ncodebase, capped to a token budget. The point: instead of dumping whole files\n(wasteful, blows the context window), get a cheap \"skeleton\" of the repo —\nthe functions\u002Fclasses everything else depends on — and read full files only\nwhere it matters.\n\nThis is our zero-dependency port of [Aider's repo-map](https:\u002F\u002Faider.chat\u002Fdocs\u002Frepomap.html).\n\n## When to use\n\n- **Onboarding** to an unfamiliar or large codebase — get the lay of the land first.\n- **Before a refactor \u002F `deep-review` \u002F `workflow-orchestration` fan-out** — feed each\n  subagent the map so it knows the important entry points without re-scanning.\n- **JIT context** (principle 07 \u002F `practice_context_engineering`) — load the map, not the files.\n- Anytime the instinct is \"let me read 20 files to understand this\" → run this first.\n\n## Usage\n\n```bash\npython \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Frepo_map.py\" [ROOT] [--budget-tokens N] [--top N] [--json] [--no-signature] [--max-files N]\n```\n\n- `ROOT` — repo root (default: cwd). If it's a git repo, only **tracked files** are\n  scanned (honors `.gitignore`); otherwise a filtered directory walk is used.\n- `--budget-tokens` (default 1024) — stop emitting once ~this many tokens are used\n  (≈4 chars\u002Ftoken heuristic). Use 256–512 for a quick orientation, 2048+ for depth.\n- `--top N` — hard cap on symbols before the budget applies.\n- `--json` — machine-readable output (for piping into a workflow \u002F another agent).\n- `--no-signature` — emit `path:line: name` instead of the full signature line.\n\nJSON distinguishes `symbols_extracted_total` (before `--top`),\n`symbols_ranked_after_top` (after that cap), and `symbols_emitted` (after the\ntoken budget). The legacy `symbols_total` key retains its post-`--top` meaning\nfor compatibility. None is a semantic coverage guarantee: extraction is regex-based\nand `--max-files` can limit input. Never diagnose parser coverage from a capped map.\n\n### Typical recipes\n\n```bash\n# Quick orientation in a new repo\npython \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Frepo_map.py\" . --budget-tokens 512\n\n# Feed a fan-out: JSON map of the most important 40 symbols\npython \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Frepo_map.py\" \u002Fpath\u002Fto\u002Frepo --top 40 --json > repo_map.json\n\n# Focus a subdirectory (a single layer\u002Fservice)\npython \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Frepo_map.py\" \u002Fpath\u002Fto\u002Frepo\u002Fservices\u002Fauth --budget-tokens 800\n```\n\n## How ranking works\n\n1. Extract definitions (functions\u002Fclasses\u002Ftypes) and identifier references per file\n   via per-language regexes (py\u002Fjs\u002Fts\u002Ftsx\u002Fgo\u002Frust\u002Fjava\u002Fruby\u002Fc\u002Fcpp\u002Fcsharp\u002Fphp\u002Fkotlin\u002Fswift).\n2. Build a directed graph: edge `F → D` when file `F` references an identifier\n   **defined** in file `D`. Rare identifiers (defined in few files) weigh more.\n3. Run **PageRank** over the file graph → structurally-central files float up\n   (shared utilities, core models, base classes).\n4. Symbol score = `pagerank(def_file) × (1 + total_refs) × rarity`. Emit highest\n   first until the token budget is hit.\n\nSo the map surfaces the code **everything else leans on**, not just the first files\nalphabetically.\n\n## Gotchas\n\n- **Regex extraction, not tree-sitter.** Fidelity is good for ranking but not a\n  parser. Exotic syntax, heavy macros, or unusual formatting can miss\u002Fmisattribute a\n  def. This is a deliberate trade for zero-install + runs-anywhere. To upgrade\n  fidelity, replace `extract()` with `tree-sitter-language-pack` tags — the graph\u002F\n  PageRank stages stay identical. (Don't install tree-sitter casually: it trips the\n  7-day supply-chain gate; gate it like any fresh dep.)\n- **Token count is a heuristic** (`chars\u002F4`), not a real tokenizer. Treat the budget\n  as approximate; it errs slightly high on code with many short tokens.\n- **Same name in many files** (e.g. `get`, `handle`) ranks each def site separately —\n  expected, since each is a distinct definition. Use `--top` to trim noise.\n- **Non-git dirs** fall back to a denylist walk (`node_modules`, `dist`, `venv`, …).\n  If your build output lives somewhere unusual, it may get scanned — point ROOT at the\n  source dir instead.\n- **Generated code** (protobuf, `src\u002Fgen\u002F`) can dominate ranks because it's referenced\n  everywhere. Point ROOT at hand-written source, or filter after the fact.\n\n## Troubleshooting\n\n| Symptom | Cause | Fix |\n|---|---|---|\n| `0 files scanned` | ROOT has no recognized source extensions, or all gitignored | Check `git ls-files`; point ROOT at the source subdir |\n| A key function is missing | Regex didn't match its signature style | Lower `--budget-tokens` pressure (raise budget) or accept the limitation; verify by `grep` |\n| `--top 12` appears to find only 12 definitions | Post-cap count confused with extraction | Inspect `symbols_extracted_total`; remove caps before investigating actual extraction misses |\n| Map dominated by one vendored file | A `vendor\u002F`\u002Fgenerated tree got scanned (non-git mode) | Run inside the git repo, or point ROOT at hand-written source |\n| Wrong\u002Fold map | File moved; map is a point-in-time snapshot | Re-run — it's cheap and stateless |\n\n## Verification\n\n`scripts\u002Frepo_map.py` is stdlib-only and was verified to run on real trees (it\ncorrectly ranks shared-utility files to the top via PageRank). Re-run on any repo to\nconfirm; there is no state to corrupt.\n","# repo-map\n\nProduces a **ranked list of the structurally-important symbol definitions** in a\ncodebase, capped to a token budget. The point: instead of dumping whole files\n(wasteful, blows the context window), get a cheap \"skeleton\" of the repo —\nthe functions\u002Fclasses everything else depends on — and read full files only\nwhere it matters.\n\nThis is our zero-dependency port of [Aider's repo-map](https:\u002F\u002Faider.chat\u002Fdocs\u002Frepomap.html).\n\n## When to use\n\n- **Onboarding** to an unfamiliar or large codebase — get the lay of the land first.\n- **Before a refactor \u002F `deep-review` \u002F `workflow-orchestration` fan-out** — feed each\n  subagent the map so it knows the important entry points without re-scanning.\n- **JIT context** (principle 07 \u002F `practice_context_engineering`) — load the map, not the files.\n- Anytime the instinct is \"let me read 20 files to understand this\" → run this first.\n\n## Usage\n\n```bash\npython \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Frepo_map.py\" [ROOT] [--budget-tokens N] [--top N] [--json] [--no-signature] [--max-files N]\n```\n\n- `ROOT` — repo root (default: cwd). If it's a git repo, only **tracked files** are\n  scanned (honors `.gitignore`); otherwise a filtered directory walk is used.\n- `--budget-tokens` (default 1024) — stop emitting once ~this many tokens are used\n  (≈4 chars\u002Ftoken heuristic). Use 256–512 for a quick orientation, 2048+ for depth.\n- `--top N` — hard cap on symbols before the budget applies.\n- `--json` — machine-readable output (for piping into a workflow \u002F another agent).\n- `--no-signature` — emit `path:line: name` instead of the full signature line.\n\nJSON distinguishes `symbols_extracted_total` (before `--top`),\n`symbols_ranked_after_top` (after that cap), and `symbols_emitted` (after the\ntoken budget). The legacy `symbols_total` key retains its post-`--top` meaning\nfor compatibility. None is a semantic coverage guarantee: extraction is regex-based\nand `--max-files` can limit input. Never diagnose parser coverage from a capped map.\n\n### Typical recipes\n\n```bash\n# Quick orientation in a new repo\npython \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Frepo_map.py\" . --budget-tokens 512\n\n# Feed a fan-out: JSON map of the most important 40 symbols\npython \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Frepo_map.py\" \u002Fpath\u002Fto\u002Frepo --top 40 --json > repo_map.json\n\n# Focus a subdirectory (a single layer\u002Fservice)\npython \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Frepo_map.py\" \u002Fpath\u002Fto\u002Frepo\u002Fservices\u002Fauth --budget-tokens 800\n```\n\n## How ranking works\n\n1. Extract definitions (functions\u002Fclasses\u002Ftypes) and identifier references per file\n   via per-language regexes (py\u002Fjs\u002Fts\u002Ftsx\u002Fgo\u002Frust\u002Fjava\u002Fruby\u002Fc\u002Fcpp\u002Fcsharp\u002Fphp\u002Fkotlin\u002Fswift).\n2. Build a directed graph: edge `F → D` when file `F` references an identifier\n   **defined** in file `D`. Rare identifiers (defined in few files) weigh more.\n3. Run **PageRank** over the file graph → structurally-central files float up\n   (shared utilities, core models, base classes).\n4. Symbol score = `pagerank(def_file) × (1 + total_refs) × rarity`. Emit highest\n   first until the token budget is hit.\n\nSo the map surfaces the code **everything else leans on**, not just the first files\nalphabetically.\n\n## Gotchas\n\n- **Regex extraction, not tree-sitter.** Fidelity is good for ranking but not a\n  parser. Exotic syntax, heavy macros, or unusual formatting can miss\u002Fmisattribute a\n  def. This is a deliberate trade for zero-install + runs-anywhere. To upgrade\n  fidelity, replace `extract()` with `tree-sitter-language-pack` tags — the graph\u002F\n  PageRank stages stay identical. (Don't install tree-sitter casually: it trips the\n  7-day supply-chain gate; gate it like any fresh dep.)\n- **Token count is a heuristic** (`chars\u002F4`), not a real tokenizer. Treat the budget\n  as approximate; it errs slightly high on code with many short tokens.\n- **Same name in many files** (e.g. `get`, `handle`) ranks each def site separately —\n  expected, since each is a distinct definition. Use `--top` to trim noise.\n- **Non-git dirs** fall back to a denylist walk (`node_modules`, `dist`, `venv`, …).\n  If your build output lives somewhere unusual, it may get scanned — point ROOT at the\n  source dir instead.\n- **Generated code** (protobuf, `src\u002Fgen\u002F`) can dominate ranks because it's referenced\n  everywhere. Point ROOT at hand-written source, or filter after the fact.\n\n## Troubleshooting\n\n| Symptom | Cause | Fix |\n|---|---|---|\n| `0 files scanned` | ROOT has no recognized source extensions, or all gitignored | Check `git ls-files`; point ROOT at the source subdir |\n| A key function is missing | Regex didn't match its signature style | Lower `--budget-tokens` pressure (raise budget) or accept the limitation; verify by `grep` |\n| `--top 12` appears to find only 12 definitions | Post-cap count confused with extraction | Inspect `symbols_extracted_total`; remove caps before investigating actual extraction misses |\n| Map dominated by one vendored file | A `vendor\u002F`\u002Fgenerated tree got scanned (non-git mode) | Run inside the git repo, or point ROOT at hand-written source |\n| Wrong\u002Fold map | File moved; map is a point-in-time snapshot | Re-run — it's cheap and stateless |\n\n## Verification\n\n`scripts\u002Frepo_map.py` is stdlib-only and was verified to run on real trees (it\ncorrectly ranks shared-utility files to the top via PageRank). Re-run on any repo to\nconfirm; there is no state to corrupt.\n",{"name":5,"description":7},"main","acf75aba86a23da299be8c69732af3e9b12433cb","upstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Frepo-map",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 repo-map",{"tool":36,"command":37},"bunx","bunx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill repo-map",{"tool":39,"command":40},"pnpm","pnpm dlx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill repo-map","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\u002Frepo-map\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Frepo_map.py","SCRIPT","脚本",14024,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fdevelopment\u002Frepo-map\u002Fscripts\u002Frepo_map.py",[51,57,64,71,78,85],{"skillNo":52,"name":53,"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":54,"categories":55,"keywords":56,"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":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},"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":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},"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":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},"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":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},"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":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},"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",[],[]]