[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MQ8HAP3FMSD84Y320NCZZ":3,"skill-same:01M74MQ8HAP3FMSD84Y320NCZZ":63},{"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},"01M74MQ8HAP3FMSD84Y320NCZZ","okf-repo-organizer",null,"Organize a repository, folder, or knowledge corpus into generic Open Knowledge Format (OKF) bundles. Use when you are asked to convert or normalize repo files and folders to OKF, add OKF index\u002Flog\u002Fconcept frontmatter, choose bundle boundaries, migrate idea\u002Fproject\u002Fdoc folders into OKF-style structure, or validate generic OKF conformance.","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\u002Fokf-repo-organizer\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: okf-repo-organizer\ndescription: Organize a repository, folder, or knowledge corpus into generic Open Knowledge Format (OKF) bundles. Use when you are asked to convert or normalize repo files and folders to OKF, add OKF index\u002Flog\u002Fconcept frontmatter, choose bundle boundaries, migrate idea\u002Fproject\u002Fdoc folders into OKF-style structure, or validate generic OKF conformance.\n---\n\n# OKF Repo Organizer\n\n## Overview\n\nUse this skill to make an existing repo or folder easier for humans and agents to traverse as OKF. Keep the skill generic: OKF is markdown plus YAML frontmatter, not a domain-specific taxonomy.\n\n## Reference\n\nRead `references\u002FSPEC.md` from this skill before changing files. Treat it as the only OKF format reference. Do not assume the target repository contains an `okf\u002F` directory or its own copy of the spec.\n\nDo not invent stricter required fields than the spec. For generic OKF conformance, every non-reserved `.md` concept document needs parseable YAML frontmatter with a non-empty `type`. `title`, `description`, `resource`, `tags`, and `timestamp` are recommended, not mandatory.\n\nAdd frontmatter minimally and let content drive it. Always include `type`; add a recommended field only when it carries information the document body and the file's location do not already make obvious. Prefer the smallest frontmatter that satisfies OKF over a complete one.\n\n## Workflow\n\n1. Establish scope and bundle boundaries.\n   - Use the path the user names. If none is named, inspect the repo and choose the smallest sensible scope.\n   - Prefer treating knowledge-oriented folders as OKF bundles. Do not force a whole software repo to be one OKF bundle unless the user asks for that or the repo is already markdown-first.\n   - A nested folder can be its own bundle when it has independent context, for example an `ideas\u002Fidea_example\u002F` folder with its own `index.md`, `log.md`, and concept files.\n\n2. Inventory before editing.\n   - Use `rg --files` to inspect Markdown, source, asset, generated, and vendor paths.\n   - Preserve user content and existing frontmatter keys. Move or rename files only when it improves OKF traversal and does not break obvious project conventions.\n   - Ignore generated and dependency folders such as `.git\u002F`, `node_modules\u002F`, `.venv\u002F`, `dist\u002F`, and `build\u002F` unless the user explicitly wants them modeled.\n\n3. Organize the bundle.\n   - Add or update `index.md` at the bundle root and important subdirectories for progressive disclosure. Keep index files as plain Markdown; only a bundle-root `index.md` may use frontmatter, and only for `okf_version`.\n   - Add or update `log.md` when the folder needs chronological history. Use `## YYYY-MM-DD` date headings, newest first.\n   - For each non-reserved `.md` concept file, add or normalize frontmatter. Only `type` is required; add the other keys only when they earn their place:\n\n```markdown\n---\ntype: \u003Cself-explanatory type>        # required\ntitle: \u003Chuman-readable title>        # recommended\ndescription: \u003Cone-sentence summary>   # recommended\ntags: [optional, tags]                # optional\n# add resource, timestamp, or other keys only when they carry non-redundant information\n---\n```\n\n   - Keep frontmatter minimal and content-driven. Do not add a field that merely duplicates the body or the file's position. For example, omit `timestamp` on a chronological, newest-first log whose top `## YYYY-MM-DD` heading already states the last-change date, and omit `created` when the oldest in-body entry already states it.\n   - Keep `type` short and descriptive, such as `Idea`, `Project`, `Template`, `Reference`, `Runbook`, `Dataset`, `Note`, or `Decision`. Do not create a central type registry.\n   - Leave code, data, images, PDFs, and other non-Markdown assets in normal project locations. When useful, create a concept `.md` that describes or links to the asset instead of modifying the asset.\n   - Prefer bundle-relative Markdown links that begin with `\u002F` when links should survive file moves. Relative links are fine for local neighbors.\n   - For repeatable project workflows, keep templates and instances semantically distinct. A useful generic pattern is `projects-folder\u002Ftemplates\u002F\u003CTemplateName>\u002F` for reusable templates and `projects-folder\u002F\u003CProjectName>\u002F` for instantiated projects.\n\n4. Validate.\n   - Run bundled scripts from this skill's root directory, using paths relative to the directory that contains this `SKILL.md`. Pass the bundle root as an absolute path when the target repo is not the current working directory.\n   - Run the bundled validator on every OKF bundle root you changed. Prefer `uv run` so the script can install its declared Python dependency from the inline PEP 723 metadata:\n\n```bash\nuv run scripts\u002Fvalidate_okf_bundle.py \u002Fabsolute\u002Fpath\u002Fto\u002Fbundle-root\n```\n\n   - If `uv` is unavailable and the environment already has Python 3.11+ plus PyYAML, run it directly:\n\n```bash\npython scripts\u002Fvalidate_okf_bundle.py \u002Fabsolute\u002Fpath\u002Fto\u002Fbundle-root\n```\n\n   - If an OKF reference implementation is available and you want to reuse its parser, pass it explicitly. This is optional; the validator also works with PyYAML when the reference implementation is unavailable.\n\n```bash\nuv run scripts\u002Fvalidate_okf_bundle.py \u002Fabsolute\u002Fpath\u002Fto\u002Fbundle-root --okf-src \u002Fpath\u002Fto\u002Fokf\u002Fsrc\n```\n\n   - The validator reuses `enrichment_agent.bundle.document.OKFDocument.parse` from `okf\u002Fsrc` when available, then applies the generic conformance rules from this skill's bundled `references\u002FSPEC.md`. It does not call the stricter enrichment-agent document validator because that validator requires recommended fields that generic OKF does not require.\n\n5. Finish with a concise report.\n   - List the bundle root(s), important files changed, and validator result.\n   - If validation fails, fix the OKF format issues before finishing unless the user explicitly asks you to stop.\n   - Call out deliberate non-OKF areas, such as source-only directories or a top-level README kept outside the selected bundle.\n","# OKF Repo Organizer\n\n## Overview\n\nUse this skill to make an existing repo or folder easier for humans and agents to traverse as OKF. Keep the skill generic: OKF is markdown plus YAML frontmatter, not a domain-specific taxonomy.\n\n## Reference\n\nRead `references\u002FSPEC.md` from this skill before changing files. Treat it as the only OKF format reference. Do not assume the target repository contains an `okf\u002F` directory or its own copy of the spec.\n\nDo not invent stricter required fields than the spec. For generic OKF conformance, every non-reserved `.md` concept document needs parseable YAML frontmatter with a non-empty `type`. `title`, `description`, `resource`, `tags`, and `timestamp` are recommended, not mandatory.\n\nAdd frontmatter minimally and let content drive it. Always include `type`; add a recommended field only when it carries information the document body and the file's location do not already make obvious. Prefer the smallest frontmatter that satisfies OKF over a complete one.\n\n## Workflow\n\n1. Establish scope and bundle boundaries.\n   - Use the path the user names. If none is named, inspect the repo and choose the smallest sensible scope.\n   - Prefer treating knowledge-oriented folders as OKF bundles. Do not force a whole software repo to be one OKF bundle unless the user asks for that or the repo is already markdown-first.\n   - A nested folder can be its own bundle when it has independent context, for example an `ideas\u002Fidea_example\u002F` folder with its own `index.md`, `log.md`, and concept files.\n\n2. Inventory before editing.\n   - Use `rg --files` to inspect Markdown, source, asset, generated, and vendor paths.\n   - Preserve user content and existing frontmatter keys. Move or rename files only when it improves OKF traversal and does not break obvious project conventions.\n   - Ignore generated and dependency folders such as `.git\u002F`, `node_modules\u002F`, `.venv\u002F`, `dist\u002F`, and `build\u002F` unless the user explicitly wants them modeled.\n\n3. Organize the bundle.\n   - Add or update `index.md` at the bundle root and important subdirectories for progressive disclosure. Keep index files as plain Markdown; only a bundle-root `index.md` may use frontmatter, and only for `okf_version`.\n   - Add or update `log.md` when the folder needs chronological history. Use `## YYYY-MM-DD` date headings, newest first.\n   - For each non-reserved `.md` concept file, add or normalize frontmatter. Only `type` is required; add the other keys only when they earn their place:\n\n```markdown\n---\ntype: \u003Cself-explanatory type>        # required\ntitle: \u003Chuman-readable title>        # recommended\ndescription: \u003Cone-sentence summary>   # recommended\ntags: [optional, tags]                # optional\n# add resource, timestamp, or other keys only when they carry non-redundant information\n---\n```\n\n   - Keep frontmatter minimal and content-driven. Do not add a field that merely duplicates the body or the file's position. For example, omit `timestamp` on a chronological, newest-first log whose top `## YYYY-MM-DD` heading already states the last-change date, and omit `created` when the oldest in-body entry already states it.\n   - Keep `type` short and descriptive, such as `Idea`, `Project`, `Template`, `Reference`, `Runbook`, `Dataset`, `Note`, or `Decision`. Do not create a central type registry.\n   - Leave code, data, images, PDFs, and other non-Markdown assets in normal project locations. When useful, create a concept `.md` that describes or links to the asset instead of modifying the asset.\n   - Prefer bundle-relative Markdown links that begin with `\u002F` when links should survive file moves. Relative links are fine for local neighbors.\n   - For repeatable project workflows, keep templates and instances semantically distinct. A useful generic pattern is `projects-folder\u002Ftemplates\u002F\u003CTemplateName>\u002F` for reusable templates and `projects-folder\u002F\u003CProjectName>\u002F` for instantiated projects.\n\n4. Validate.\n   - Run bundled scripts from this skill's root directory, using paths relative to the directory that contains this `SKILL.md`. Pass the bundle root as an absolute path when the target repo is not the current working directory.\n   - Run the bundled validator on every OKF bundle root you changed. Prefer `uv run` so the script can install its declared Python dependency from the inline PEP 723 metadata:\n\n```bash\nuv run scripts\u002Fvalidate_okf_bundle.py \u002Fabsolute\u002Fpath\u002Fto\u002Fbundle-root\n```\n\n   - If `uv` is unavailable and the environment already has Python 3.11+ plus PyYAML, run it directly:\n\n```bash\npython scripts\u002Fvalidate_okf_bundle.py \u002Fabsolute\u002Fpath\u002Fto\u002Fbundle-root\n```\n\n   - If an OKF reference implementation is available and you want to reuse its parser, pass it explicitly. This is optional; the validator also works with PyYAML when the reference implementation is unavailable.\n\n```bash\nuv run scripts\u002Fvalidate_okf_bundle.py \u002Fabsolute\u002Fpath\u002Fto\u002Fbundle-root --okf-src \u002Fpath\u002Fto\u002Fokf\u002Fsrc\n```\n\n   - The validator reuses `enrichment_agent.bundle.document.OKFDocument.parse` from `okf\u002Fsrc` when available, then applies the generic conformance rules from this skill's bundled `references\u002FSPEC.md`. It does not call the stricter enrichment-agent document validator because that validator requires recommended fields that generic OKF does not require.\n\n5. Finish with a concise report.\n   - List the bundle root(s), important files changed, and validator result.\n   - If validation fails, fix the OKF format issues before finishing unless the user explicitly asks you to stop.\n   - Call out deliberate non-OKF areas, such as source-only directories or a top-level README kept outside the selected bundle.\n",{"name":5,"description":7},"main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fopen-paper-skills\u002Fokf-repo-organizer",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 okf-repo-organizer",{"tool":39,"command":40},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill okf-repo-organizer",{"tool":42,"command":43},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill okf-repo-organizer","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\u002Fokf-repo-organizer\u002FSKILL.md",true,[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",233,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fokf-repo-organizer\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002FSPEC.md",15046,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fokf-repo-organizer\u002Freferences\u002FSPEC.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fvalidate_okf_bundle.py","SCRIPT","脚本",9842,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fokf-repo-organizer\u002Fscripts\u002Fvalidate_okf_bundle.py",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]