[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78B4REVB12JSZ50C4G4XX56":3,"skill-same:01M78B4REVB12JSZ50C4G4XX56":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},"01M78B4REVB12JSZ50C4G4XX56","rlm-context-as-program",null,"Plan bounded analysis of an artefact too large for one context window through metadata-first chunking, per-chunk evidence, synthesis, and explicit cost limits without activating recursive execution or delegation.","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\u002Frlm-context-as-program\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rlm-context-as-program\ndescription: \"Plan bounded analysis of an artefact too large for one context window through metadata-first chunking, per-chunk evidence, synthesis, and explicit cost limits without activating recursive execution or delegation.\"\nversion: 0.1.0\nlicense: MIT\nmetadata:\n  hermes_config_kit:\n    source_repo: AnastasiyaW\u002Fclaude-code-config\n    source_path: rules\u002Frlm-context-as-program.md\n    adapter: hermes-agent-config-kit\n    conversion: adapted\n---\n\n# Rlm Context As Program\n\nSource: `AnastasiyaW\u002Fclaude-code-config\u002Frules\u002Frlm-context-as-program.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# RLM Context as a Program\n\nUse this module when a log, dataset listing, transcript, JSONL stream, or other\nartefact is too large to inspect safely in one context window. Treat the artefact\nas bounded input to a review protocol rather than pasting it wholesale into a\nprompt. This is planning guidance only: it does not run code, create a routine,\ndispatch agents, or authorise additional model usage.\n\n## Decision boundary\n\nUse ordinary single-pass inspection when the relevant material fits comfortably\nin context and can be checked directly. Consider this pattern only when the\nartefact is too large, evidence near the end would otherwise be lost, or a\none-off question does not justify building retrieval infrastructure.\n\nDo not use it where deterministic latency or cost is the primary requirement,\nwhere the source cannot be partitioned without breaking its meaning, or where a\nsmall targeted read answers the question.\n\n## Bounded analysis protocol\n\n1. **Inspect metadata first.** Record source provenance, size, format, line or\n   record count, relevant schema, the question to answer, and any access or\n   privacy constraints. Read only a small representative sample before selecting\n   ranges.\n2. **Plan partitions.** Choose non-overlapping chunks with stable offsets or\n   identifiers. State coverage, ordering, focus terms, and how malformed or\n   missing records will be reported. Do not silently discard tail ranges.\n3. **Collect per-chunk evidence.** Use approved read-only inspection interfaces\n   to extract only evidence relevant to the stated question. Preserve source\n   references sufficient for a later reviewer to reproduce the observation.\n4. **Synthesize conservatively.** Combine evidence only after checking coverage,\n   contradictions, duplicates, and gaps. Distinguish observations, inference,\n   unresolved areas, and recommendations.\n5. **Verify proportionately.** For a consequential conclusion, sample findings\n   from independent ranges or ask a fresh reviewer to check the synthesis against\n   the cited evidence.\n\n## Cost and safety controls\n\n- Set a maximum number of chunks, concurrency, time, result size, and provider\n  budget before any fan-out. More partitions can multiply token usage.\n- Keep large-input analysis opt-in. A discovered large file is not authority to\n  spend budget or broaden an approved task.\n- Stop and report BLOCKED when access, source integrity, scope, budget, or\n  evidence is insufficient. Never claim complete coverage after a partial pass.\n- Keep sensitive content and access credentials out of prompts and retained\n  evidence unless their use is explicitly authorised and necessary.\n- Treat any executable helper for partitioning or recursion as a separate,\n  reviewed routine. This module does not install or invoke one.\n\n## Relationship to existing modules\n\nUse `agent-harness-design` for a broader sandboxed connector design,\n`workflow-orchestration` for a reviewable multi-stage protocol,\n`multi-agent-task-decomposition` for dependency and ownership boundaries,\n`billing-spend-controls` for spend limits, and `proof-verify` for independent\nacceptance evidence.\n\n## Reporting\n\nReport the source and question, metadata, partition plan, covered and excluded\nranges, budget boundary, evidence references, synthesis, verification result,\nand any remaining uncertainty or operator-confirmation point. The report must\nstate whether analysis was complete, partial, or blocked.\n","# Rlm Context As Program\n\nSource: `AnastasiyaW\u002Fclaude-code-config\u002Frules\u002Frlm-context-as-program.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# RLM Context as a Program\n\nUse this module when a log, dataset listing, transcript, JSONL stream, or other\nartefact is too large to inspect safely in one context window. Treat the artefact\nas bounded input to a review protocol rather than pasting it wholesale into a\nprompt. This is planning guidance only: it does not run code, create a routine,\ndispatch agents, or authorise additional model usage.\n\n## Decision boundary\n\nUse ordinary single-pass inspection when the relevant material fits comfortably\nin context and can be checked directly. Consider this pattern only when the\nartefact is too large, evidence near the end would otherwise be lost, or a\none-off question does not justify building retrieval infrastructure.\n\nDo not use it where deterministic latency or cost is the primary requirement,\nwhere the source cannot be partitioned without breaking its meaning, or where a\nsmall targeted read answers the question.\n\n## Bounded analysis protocol\n\n1. **Inspect metadata first.** Record source provenance, size, format, line or\n   record count, relevant schema, the question to answer, and any access or\n   privacy constraints. Read only a small representative sample before selecting\n   ranges.\n2. **Plan partitions.** Choose non-overlapping chunks with stable offsets or\n   identifiers. State coverage, ordering, focus terms, and how malformed or\n   missing records will be reported. Do not silently discard tail ranges.\n3. **Collect per-chunk evidence.** Use approved read-only inspection interfaces\n   to extract only evidence relevant to the stated question. Preserve source\n   references sufficient for a later reviewer to reproduce the observation.\n4. **Synthesize conservatively.** Combine evidence only after checking coverage,\n   contradictions, duplicates, and gaps. Distinguish observations, inference,\n   unresolved areas, and recommendations.\n5. **Verify proportionately.** For a consequential conclusion, sample findings\n   from independent ranges or ask a fresh reviewer to check the synthesis against\n   the cited evidence.\n\n## Cost and safety controls\n\n- Set a maximum number of chunks, concurrency, time, result size, and provider\n  budget before any fan-out. More partitions can multiply token usage.\n- Keep large-input analysis opt-in. A discovered large file is not authority to\n  spend budget or broaden an approved task.\n- Stop and report BLOCKED when access, source integrity, scope, budget, or\n  evidence is insufficient. Never claim complete coverage after a partial pass.\n- Keep sensitive content and access credentials out of prompts and retained\n  evidence unless their use is explicitly authorised and necessary.\n- Treat any executable helper for partitioning or recursion as a separate,\n  reviewed routine. This module does not install or invoke one.\n\n## Relationship to existing modules\n\nUse `agent-harness-design` for a broader sandboxed connector design,\n`workflow-orchestration` for a reviewable multi-stage protocol,\n`multi-agent-task-decomposition` for dependency and ownership boundaries,\n`billing-spend-controls` for spend limits, and `proof-verify` for independent\nacceptance evidence.\n\n## Reporting\n\nReport the source and question, metadata, partition plan, covered and excluded\nranges, budget boundary, evidence references, synthesis, verification result,\nand any remaining uncertainty or operator-confirmation point. The report must\nstate whether analysis was complete, partial, or blocked.\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","rules\u002Frlm-context-as-program.md","AnastasiyaW\u002Fclaude-code-config","main","07d02526f424fc814f8350d6b0b728e81576603d","hermes\u002Fskills\u002Frlm-context-as-program",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 rlm-context-as-program",{"tool":43,"command":44},"bunx","bunx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill rlm-context-as-program",{"tool":46,"command":47},"pnpm","pnpm dlx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill rlm-context-as-program","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fhermes\u002Fskills\u002Frlm-context-as-program\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",[],[]]