[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MQ4E6B23S63C06MZKP3CV":3,"skill-same:01M74MQ4E6B23S63C06MZKP3CV":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M74MQ4E6B23S63C06MZKP3CV","map-then-territory",null,"Map scattered ideas into a human-approved DAG of verifiable states, then drive fresh agents through it edge by edge. Use when the user has a destination or idea fragments but lacks the domain knowledge to identify or sequence the route; when revising a map bundle; when compiling approved edges into launch prompts; or when recording execution evidence, deviations, and human verification.","pengqianhan\u002FAI-Human-Research-OS","pengqianhan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4286531?v=4","01M74M3DT9HNZ6HPAK8TX69EX9","PengqianHan","01M74M3DTVSN2GXW0JH2W396FK",3,"MIT","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fmap-then-territory\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: map-then-territory\ndescription: Map scattered ideas into a human-approved DAG of verifiable states, then drive fresh agents through it edge by edge. Use when the user has a destination or idea fragments but lacks the domain knowledge to identify or sequence the route; when revising a map bundle; when compiling approved edges into launch prompts; or when recording execution evidence, deviations, and human verification.\n---\n\n# Map Then Territory\n\nTurn human intent into a map before changing the territory. The human owns the\nintent, values, directional choices, and final verification. The agent surveys\nthe unfamiliar domain, preserves the human's idea fragments, proposes the\nmissing points and lines, and executes approved lines. A point is ready only\nwhen the human can verify it without understanding the implementation.\n\n## Core model\n\n- **Idea fragment** — the human's original input, preserved verbatim until the\n  map records its disposition.\n- **Waypoint** — a verifiable state of the world, phrased as what is true rather\n  than work to perform. A\n  **directional** waypoint can redraw the route and requires an informed human\n  choice before execution; an **executive** waypoint allows any implementation\n  that passes its human-runnable acceptance check.\n- **Edge** — one clean agent session of action, with transition logic explaining\n  why it moves the territory from one waypoint to another.\n- **Map** — the human-approved Markdown and Mermaid DAG; its `index.md` is the\n  single source of route state.\n- **Territory** — the repository, documents, or environment changed by agents\n  traversing approved edges.\n\n## Branches\n\n- **Mapping ideas or revising a route** → read\n  [references\u002Fmap-schema.md](references\u002Fmap-schema.md) before editing.\n- **Compiling an edge prompt** → read\n  [references\u002Fedge-prompt-assembly.md](references\u002Fedge-prompt-assembly.md)\n  before assembling.\n- **Traversing an edge or writing back its result** → read\n  [references\u002Fexecution-loop.md](references\u002Fexecution-loop.md) before changing\n  territory or route state.\n\nFor an existing bundle, enter at the requested branch and treat completed\nearlier steps as repository evidence. Treat each branch as one session arc:\nmapping ends with an approved map, compilation ends with ready prompts, and\ntraversal ends with one edge's write-back or one human verdict.\n\n## Map\n\n### 1. Capture intent and survey the territory\n\nEstablish the territory, known start, desired destination, and every idea\nfragment the human supplies. Preserve each fragment verbatim in the idea ledger\nbefore interpreting it. Treat the destination as provisional until the human\nconfirms that it describes success. Survey the relevant code, documents, and\nprior art; answer from territory evidence before asking the human. Use\n`grilling` one question at a time for intent, preferences, or directional\nambiguity that evidence cannot resolve.\n\nComplete when the draft map names the territory, start, and destination; every\nsupplied fragment has a stable ledger row; and the evidence needed to propose a\nroute is gathered or its absence is explicit.\n\n### 2. Draw and approve the route\n\nConvert the idea ledger and survey evidence into a trunk route. Propose the\nmissing waypoints as well as the edges between them, including both when the\nhuman supplies only fragments. Give every ledger row a disposition to the\ndestination, one or more waypoint or edge IDs, or a human-approved out-of-scope\nrationale.\n\nFor each directional waypoint, present two or three contrasting options with\nreal trade-offs and a recommended default, then resolve them one at a time with\n`grilling`. When the human lacks the concepts needed to choose, teach from\nterritory evidence in `tutorials\u002F` via `human-cognition-cache` before asking.\n\nComplete when every idea has a final disposition; every waypoint has a state,\nhuman-runnable acceptance check, type, and status; every edge has an action and\ntransition logic; every in-scope waypoint lies on a coherent route; the DAG\ncontains a complete start-to-destination trunk; and the human approves the\nroute. Record approval as bundle status `approved`, then end the mapping arc.\n\n## Territory\n\n### 3. Compile ready edges\n\nFor the requested approved edge—or each currently reachable edge when the user\nrequests a batch—assemble a provenance-annotated prompt with\n`writing-great-prompt` according to\n[references\u002Fedge-prompt-assembly.md](references\u002Fedge-prompt-assembly.md).\n\nComplete when every requested edge has a prompt under `prompts\u002F` that a fresh\nsession can execute without the authoring conversation, and each prompt is\n`ready` after any required human review. End the compilation arc before\nterritory execution.\n\n### 4. Traverse, verify, and learn\n\nRun one edge through [references\u002Fexecution-loop.md](references\u002Fexecution-loop.md).\nLet the executing agent self-verify and write evidence; reserve `verified` for\nthe human's acceptance run. Pre-teach directional choices and offer executive\nexplanation after delivery on demand; record delivered cognition growth through\n`human-cognition-cache`.\n\nComplete the execution arc when the selected edge reaches `done` and its target\nis `delivered`, or when it returns to `ready` with the blocker or deviation\nrecorded. Complete a human-verdict arc when the verdict, resulting statuses, and\ncalibration entry agree. Repeat through fresh sessions until the destination is\n`verified` or the map is explicitly `paused` or `abandoned` with its record.\n\n## Boundaries\n\n- Write map, tutorial, and prompt prose in the human's working language; keep\n  field names and statuses in English for stable tooling.\n- Keep dead waypoints, deviations, and post-mortems: map history is cognition\n  history.\n- Before publishing a bundle, warn that tutorials and post-mortems can expose\n  the human's cognition state.\n\n_Original, Pengqian Han. Inspired by Thariq Shihipar's \"A Field Guide to Claude\nFable 5: Finding Your Unknowns\" (the map–territory framing)._\n","# Map Then Territory\n\nTurn human intent into a map before changing the territory. The human owns the\nintent, values, directional choices, and final verification. The agent surveys\nthe unfamiliar domain, preserves the human's idea fragments, proposes the\nmissing points and lines, and executes approved lines. A point is ready only\nwhen the human can verify it without understanding the implementation.\n\n## Core model\n\n- **Idea fragment** — the human's original input, preserved verbatim until the\n  map records its disposition.\n- **Waypoint** — a verifiable state of the world, phrased as what is true rather\n  than work to perform. A\n  **directional** waypoint can redraw the route and requires an informed human\n  choice before execution; an **executive** waypoint allows any implementation\n  that passes its human-runnable acceptance check.\n- **Edge** — one clean agent session of action, with transition logic explaining\n  why it moves the territory from one waypoint to another.\n- **Map** — the human-approved Markdown and Mermaid DAG; its `index.md` is the\n  single source of route state.\n- **Territory** — the repository, documents, or environment changed by agents\n  traversing approved edges.\n\n## Branches\n\n- **Mapping ideas or revising a route** → read\n  [references\u002Fmap-schema.md](references\u002Fmap-schema.md) before editing.\n- **Compiling an edge prompt** → read\n  [references\u002Fedge-prompt-assembly.md](references\u002Fedge-prompt-assembly.md)\n  before assembling.\n- **Traversing an edge or writing back its result** → read\n  [references\u002Fexecution-loop.md](references\u002Fexecution-loop.md) before changing\n  territory or route state.\n\nFor an existing bundle, enter at the requested branch and treat completed\nearlier steps as repository evidence. Treat each branch as one session arc:\nmapping ends with an approved map, compilation ends with ready prompts, and\ntraversal ends with one edge's write-back or one human verdict.\n\n## Map\n\n### 1. Capture intent and survey the territory\n\nEstablish the territory, known start, desired destination, and every idea\nfragment the human supplies. Preserve each fragment verbatim in the idea ledger\nbefore interpreting it. Treat the destination as provisional until the human\nconfirms that it describes success. Survey the relevant code, documents, and\nprior art; answer from territory evidence before asking the human. Use\n`grilling` one question at a time for intent, preferences, or directional\nambiguity that evidence cannot resolve.\n\nComplete when the draft map names the territory, start, and destination; every\nsupplied fragment has a stable ledger row; and the evidence needed to propose a\nroute is gathered or its absence is explicit.\n\n### 2. Draw and approve the route\n\nConvert the idea ledger and survey evidence into a trunk route. Propose the\nmissing waypoints as well as the edges between them, including both when the\nhuman supplies only fragments. Give every ledger row a disposition to the\ndestination, one or more waypoint or edge IDs, or a human-approved out-of-scope\nrationale.\n\nFor each directional waypoint, present two or three contrasting options with\nreal trade-offs and a recommended default, then resolve them one at a time with\n`grilling`. When the human lacks the concepts needed to choose, teach from\nterritory evidence in `tutorials\u002F` via `human-cognition-cache` before asking.\n\nComplete when every idea has a final disposition; every waypoint has a state,\nhuman-runnable acceptance check, type, and status; every edge has an action and\ntransition logic; every in-scope waypoint lies on a coherent route; the DAG\ncontains a complete start-to-destination trunk; and the human approves the\nroute. Record approval as bundle status `approved`, then end the mapping arc.\n\n## Territory\n\n### 3. Compile ready edges\n\nFor the requested approved edge—or each currently reachable edge when the user\nrequests a batch—assemble a provenance-annotated prompt with\n`writing-great-prompt` according to\n[references\u002Fedge-prompt-assembly.md](references\u002Fedge-prompt-assembly.md).\n\nComplete when every requested edge has a prompt under `prompts\u002F` that a fresh\nsession can execute without the authoring conversation, and each prompt is\n`ready` after any required human review. End the compilation arc before\nterritory execution.\n\n### 4. Traverse, verify, and learn\n\nRun one edge through [references\u002Fexecution-loop.md](references\u002Fexecution-loop.md).\nLet the executing agent self-verify and write evidence; reserve `verified` for\nthe human's acceptance run. Pre-teach directional choices and offer executive\nexplanation after delivery on demand; record delivered cognition growth through\n`human-cognition-cache`.\n\nComplete the execution arc when the selected edge reaches `done` and its target\nis `delivered`, or when it returns to `ready` with the blocker or deviation\nrecorded. Complete a human-verdict arc when the verdict, resulting statuses, and\ncalibration entry agree. Repeat through fresh sessions until the destination is\n`verified` or the map is explicitly `paused` or `abandoned` with its record.\n\n## Boundaries\n\n- Write map, tutorial, and prompt prose in the human's working language; keep\n  field names and statuses in English for stable tooling.\n- Keep dead waypoints, deviations, and post-mortems: map history is cognition\n  history.\n- Before publishing a bundle, warn that tutorials and post-mortems can expose\n  the human's cognition state.\n\n_Original, Pengqian Han. Inspired by Thariq Shihipar's \"A Field Guide to Claude\nFable 5: Finding Your Unknowns\" (the map–territory framing)._\n",{"name":5,"description":7},"main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fopen-paper-skills\u002Fmap-then-territory",0,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS","https:\u002F\u002Fpengqianhan.github.io\u002FAI-Human-Research-OS\u002F","https:\u002F\u002Fgithub.com\u002Fpengqianhan","Ph.D. candidate of The University of Auckland, New Zealand","2026-11-14 18:08:16",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill map-then-territory",{"tool":39,"command":40},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill map-then-territory",{"tool":42,"command":43},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill map-then-territory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fmap-then-territory\u002FSKILL.md",true,[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fedge-prompt-assembly.md","REFERENCE","参考文档",3450,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fmap-then-territory\u002Freferences\u002Fedge-prompt-assembly.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fexecution-loop.md",3168,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fmap-then-territory\u002Freferences\u002Fexecution-loop.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fmap-schema.md",5751,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fmap-then-territory\u002Freferences\u002Fmap-schema.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"templates\u002Fedge-prompt.md",1866,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fmap-then-territory\u002Ftemplates\u002Fedge-prompt.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"templates\u002Fmap-index.md",1716,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fmap-then-territory\u002Ftemplates\u002Fmap-index.md",[70,77,84,91,98,105],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M74MWYTHT498SVMN823896T7","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M74MWWVCFZ8HQS8840F1V1FT","uv","Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fuv\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M74MWRH5BTSWZ2C5PCTD5FV9","uniprot-database","Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funiprot_database\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M74MWN1D3ER9F1FZPWH8HQC1","unibind-database","Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED\u002FFASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funibind_database\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M74MWHHB5QZY3NR2FYA1EK4N","ucsc-conservation-and-tfbs","Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fucsc_conservation_and_tfbs\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M74MWERYHSY87P21FDMVE6BA","string-database","Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fstring_database\u002FSKILL.md",[],[]]