[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ABMQHCX2PJ1P1T0B8PH9B0":3,"skill-same:01M7ABMQHCX2PJ1P1T0B8PH9B0":46},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7ABMQHCX2PJ1P1T0B8PH9B0","research",null,"Research a question in primary sources. Use when it needs sources, not the user — how a library behaves, what a spec requires, where something lives in this repo. Not for user decisions (grilling) or failures to reproduce (diagnose).","j0hanz\u002Fj0hanz-marketplace","j0hanz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F159924955?v=4","01M7ABFK415CKHXYV9GZRJ16T7","Linus Johansson","01M7ABFK52FCPP2PNBH1YR7ZPA",0,"MIT","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Fresearch\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: research\ndescription: Research a question in primary sources. Use when it needs sources, not the user — how a library behaves, what a spec requires, where something lives in this repo. Not for user decisions (grilling) or failures to reproduce (diagnose).\n---\n\nDispatch a background agent (Claude Code: Agent tool, `subagent_type: \"general-purpose\"`, `run_in_background: true`; Copilot: `task`, `agent_type: \"general-purpose\"`, `mode: \"background\"`). Two source modes share one template: **web** (fetch and search outside the repo) or **directory** (read this working directory). A question spanning both is two dispatches, not one agent handed both source blocks.\n\nFill the template and pass it as the agent's prompt. Drop a whole tag when the run has nothing to put in it, and inside `\u003Csources>` keep only the mode you picked — an agent handed both picks its own.\n\n```text\n\u003Cquestion>\n{the one thing to find out, concrete enough to be answered wrong}\n\u003C\u002Fquestion>\n\n\u003Csources>\nWeb mode — primary only: official docs, source code, specs, first-party APIs;\ntrace any secondary write-up back to the primary that owns the claim.\n{pinned repos, domains, or version numbers, if any}\n\nDirectory mode — this working directory only: source, tests, config, fixtures,\nand what the manifest scripts and `--help` actually print. Read the code that\nowns the behavior; treat comments, READMEs, and docs as pointers to that code.\n{paths, symbols, or directories to start from, if any}\n\u003C\u002Fsources>\n\n\u003Cscope>\n{what is already known and needs no re-reading}\n{what is out of bounds}\n\u003C\u002Fscope>\n\n\u003Coutput>\nYour final message is the whole deliverable — a single, self-contained report.\nOpen every source listed above; name the ones you opened and the ones you did\nnot, with why. Cite every fact with a link to the source that owns it (web) or\nas `path:line` (directory), and quote the shortest excerpt that carries it.\nWhere a version or date is the answer, name the exact identifier; where a\nconvention is the answer, name one exemplar file to imitate. Where sources\ncontradict each other, report both rather than picking one. The deliverable is\nthe answer to the question asked.\n\u003C\u002Foutput>\n```\n\nCheck the report when it returns — the agent's report reaches you, not the user. A report that misses the `\u003Cquestion>` as asked, or carries a fact without a citation, goes back once: re-dispatch with the gap named in `\u003Cscope>`. Under [frontier](..\u002Ffrontier\u002FSKILL.md), its operations' reopen rule replaces that re-dispatch.\n\n**Done when** the findings are relayed, every fact in them is cited or — only after the one re-dispatch — marked **unverified**, and the relay says whether the `\u003Cquestion>` as asked is answered.\n","Dispatch a background agent (Claude Code: Agent tool, `subagent_type: \"general-purpose\"`, `run_in_background: true`; Copilot: `task`, `agent_type: \"general-purpose\"`, `mode: \"background\"`). Two source modes share one template: **web** (fetch and search outside the repo) or **directory** (read this working directory). A question spanning both is two dispatches, not one agent handed both source blocks.\n\nFill the template and pass it as the agent's prompt. Drop a whole tag when the run has nothing to put in it, and inside `\u003Csources>` keep only the mode you picked — an agent handed both picks its own.\n\n```text\n\u003Cquestion>\n{the one thing to find out, concrete enough to be answered wrong}\n\u003C\u002Fquestion>\n\n\u003Csources>\nWeb mode — primary only: official docs, source code, specs, first-party APIs;\ntrace any secondary write-up back to the primary that owns the claim.\n{pinned repos, domains, or version numbers, if any}\n\nDirectory mode — this working directory only: source, tests, config, fixtures,\nand what the manifest scripts and `--help` actually print. Read the code that\nowns the behavior; treat comments, READMEs, and docs as pointers to that code.\n{paths, symbols, or directories to start from, if any}\n\u003C\u002Fsources>\n\n\u003Cscope>\n{what is already known and needs no re-reading}\n{what is out of bounds}\n\u003C\u002Fscope>\n\n\u003Coutput>\nYour final message is the whole deliverable — a single, self-contained report.\nOpen every source listed above; name the ones you opened and the ones you did\nnot, with why. Cite every fact with a link to the source that owns it (web) or\nas `path:line` (directory), and quote the shortest excerpt that carries it.\nWhere a version or date is the answer, name the exact identifier; where a\nconvention is the answer, name one exemplar file to imitate. Where sources\ncontradict each other, report both rather than picking one. The deliverable is\nthe answer to the question asked.\n\u003C\u002Foutput>\n```\n\nCheck the report when it returns — the agent's report reaches you, not the user. A report that misses the `\u003Cquestion>` as asked, or carries a fact without a citation, goes back once: re-dispatch with the gap named in `\u003Cscope>`. Under [frontier](..\u002Ffrontier\u002FSKILL.md), its operations' reopen rule replaces that re-dispatch.\n\n**Done when** the findings are relayed, every fact in them is cited or — only after the one re-dispatch — marked **unverified**, and the relay says whether the `\u003Cquestion>` as asked is answered.\n",{"name":5,"description":7},"main","534498267dccbe415f22f31fceac9da6771c195f","plugins\u002Fworkbench\u002Fskills\u002Fresearch","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace","https:\u002F\u002Fj0hanz-marketplace.vercel.app","https:\u002F\u002Fgithub.com\u002Fj0hanz","linus-johansson-cv-d308be9b73e1.herokuapp.com","2026-11-15 02:42:07",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add j0hanz\u002Fj0hanz-marketplace --skill research",{"tool":38,"command":39},"bunx","bunx skills add j0hanz\u002Fj0hanz-marketplace --skill research",{"tool":41,"command":42},"pnpm","pnpm dlx skills add j0hanz\u002Fj0hanz-marketplace --skill research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Fresearch\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7ABP78JFYBMCXJ9GMETCYZM","unslop","Use when writing or editing prose a person will read, or when text sounds AI-generated.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwriteup\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7ABP52BNV7NRPNBR6PCNZWC","show-me","Use when asked to show, diagram, or walk through how code fits together or what a change does, or before explaining a multi-file flow in prose.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwriteup\u002Fskills\u002Fshow-me\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7ABP3EPN4KFB4HPJNMY31NR","pr","Use when writing or updating a pull request description, or before running `gh pr create`.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwriteup\u002Fskills\u002Fpr\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7ABP08MXTHPZYTG4HKEP7WQ","commit","Use when writing a commit message, or before running `git commit`.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwriteup\u002Fskills\u002Fcommit\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7ABNV9J7DN1AFRBGDBHVBY2","write-specs","Spec a feature's observable behavior. Use when asked for requirements, when a request says what the system should do but not how, or to capture what a built system already guarantees. Not for how to build it (write-plan).","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Fwrite-specs\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7ABNPK2GVG8EB3SSEAMK4FZ","write-skills","Write, fix, or audit a skill's frontmatter, trigger description, and body. Use when a skill is asked for, never fires, or fires at the wrong moment. Not for a hook (write-hooks) or the plugin manifest and catalog.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Fwrite-skills\u002FSKILL.md",[],[]]