[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EJH6JBD76CF7A9ECTW8SC8":3,"skill-same:01M7EJH6JBD76CF7A9ECTW8SC8":44},{"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":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7EJH6JBD76CF7A9ECTW8SC8","grounded-research",null,"Use when a topic already sized as deep needs several answers from several sources and an evidence base somebody will come back to. Triggers: deep dive into X, research this properly, investigate and document Y, build an evidence base for Z, run the research passes. Decomposes, queries the notebook in three passes, closes gaps with external research, and hands the findings on. Not the notebook itself (source-notebook), not note writing (vault-note), not sizing the ask.","qsmark-labs\u002Fqsm-marketplace","qsmark-labs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F348383745?v=4","01M7EJDK5MKZ67A7JBGC3ZB1RP","QSM-LABS","01M7EJDK6649PCGA2ENGFMFA7E",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-knowledge\u002Fskills\u002Fgrounded-research\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: grounded-research\ndescription: \"Use when a topic already sized as deep needs several answers from several sources and an evidence base somebody will come back to. Triggers: deep dive into X, research this properly, investigate and document Y, build an evidence base for Z, run the research passes. Decomposes, queries the notebook in three passes, closes gaps with external research, and hands the findings on. Not the notebook itself (source-notebook), not note writing (vault-note), not sizing the ask.\"\n---\n\n# Grounded research\n\nOne question at a time is cheap; several questions over several sources, ending in an evidence\nbase that outlives the session, drifts unless someone holds the method. This flow is that method\nfor the person who will come back to the result: the notebook holds the sources, the vault holds\nthe conclusions, and this is the passage between them. It writes no vault note and does not size\nthe ask. Where no web is available, the research plan, the questions and the sources they need,\nis the part that counts.\n\nIt starts from a topic already sized as deep, with a destination and an idea of what a good answer\nlooks like. If that is missing, send it back to be sized and say why in one line, because an\nunsized deep research produces material for hours and never a conclusion nobody agreed on.\n\n## Decompose first\n\nWrite three to five sub-questions, each falsifiable on its own, before the first query: \"when does\nthe strangler pattern fail\" is one, \"tell me about migration\" is a subject. Add the two people\nskip: where do the sources disagree (a topic with no disagreement is settled or under-sourced, and\nonly asking tells which) and what do the sources not cover (the notebook can only see its own\ncorpus, so it answers this honestly).\n\n## Three passes on the notebook\n\nAsk inline, because each answer comes back small and cited; `source-notebook` owns the verbs and\nfailure modes.\n\n1. **Broad.** One query per sub-question. Read the citations, not only the prose.\n2. **Sharp.** Follow what the broad pass surfaced; the finding usually lives here.\n3. **Adversarial.** Turn the strongest claim into a question that could kill it. A claim that\n   survives is worth writing down, and one that does not saved a wrong note.\n\n## A gap is a dispatch\n\nWhen a pass returns thin citations, or the notebook says its corpus does not cover a sub-question,\nresearch that one gap on the web, add what comes back good to the notebook, and\nonly then continue the passes. Continuing earlier builds the rest of the research on the hole you\njust found, and feeding the notebook is what makes the next session faster.\n\nKeep one findings file, appended as you go, each finding with its citation, and keep in context\nonly what the next question needs. Then give the file to the `synthesis-pass` worker (output\nshape and destination with it) and each draft it returns to `vault-note`.\n\n## Where no web or notebook is reachable\n\nThe plan is the deliverable, so write it so someone with access can run it: per sub-question, what\nyou would search or ask and why, which source kinds answer it (the spec, the paper, the maintainer,\nthe postmortem before the blog post about it), and how each claim will be grounded (a locator, not\na summary). Name the gaps you could not close and say so, because an answer from memory dressed as\nresearch is the failure this flow exists to prevent.\n\n## Done when\n\nEvery load-bearing claim cites a source, not a summary of one. Contradictions stay written down as\nopen questions, never averaged into a middle nobody's sources support. The gap sub-question was\nasked and answered, and sources found outside the notebook are now in it.\n\n## Red flags\n\n- When the passes are about to start without written sub-questions, write them, because nobody can\n  say when it is finished.\n- When one pass is about to stand as the answer, run the adversarial one, because otherwise you\n  hold an impression, not a finding.\n- When a gap was researched and the result is not in the notebook, add it, because the next pass\n  cannot cite it.\n- When findings sit in the conversation, move them to the file, because material in context\n  crowds out the reasoning that turns it into a conclusion.\n\n## Say it in the reply\n\nWhat was concluded, in the words a reader would use; what stayed open and whether the sources\ndisagree or none covered it; where the findings file, the notebook, and the notes are. Not the\nfindings themselves, because pasting them back buries the conclusion.\n","# Grounded research\n\nOne question at a time is cheap; several questions over several sources, ending in an evidence\nbase that outlives the session, drifts unless someone holds the method. This flow is that method\nfor the person who will come back to the result: the notebook holds the sources, the vault holds\nthe conclusions, and this is the passage between them. It writes no vault note and does not size\nthe ask. Where no web is available, the research plan, the questions and the sources they need,\nis the part that counts.\n\nIt starts from a topic already sized as deep, with a destination and an idea of what a good answer\nlooks like. If that is missing, send it back to be sized and say why in one line, because an\nunsized deep research produces material for hours and never a conclusion nobody agreed on.\n\n## Decompose first\n\nWrite three to five sub-questions, each falsifiable on its own, before the first query: \"when does\nthe strangler pattern fail\" is one, \"tell me about migration\" is a subject. Add the two people\nskip: where do the sources disagree (a topic with no disagreement is settled or under-sourced, and\nonly asking tells which) and what do the sources not cover (the notebook can only see its own\ncorpus, so it answers this honestly).\n\n## Three passes on the notebook\n\nAsk inline, because each answer comes back small and cited; `source-notebook` owns the verbs and\nfailure modes.\n\n1. **Broad.** One query per sub-question. Read the citations, not only the prose.\n2. **Sharp.** Follow what the broad pass surfaced; the finding usually lives here.\n3. **Adversarial.** Turn the strongest claim into a question that could kill it. A claim that\n   survives is worth writing down, and one that does not saved a wrong note.\n\n## A gap is a dispatch\n\nWhen a pass returns thin citations, or the notebook says its corpus does not cover a sub-question,\nresearch that one gap on the web, add what comes back good to the notebook, and\nonly then continue the passes. Continuing earlier builds the rest of the research on the hole you\njust found, and feeding the notebook is what makes the next session faster.\n\nKeep one findings file, appended as you go, each finding with its citation, and keep in context\nonly what the next question needs. Then give the file to the `synthesis-pass` worker (output\nshape and destination with it) and each draft it returns to `vault-note`.\n\n## Where no web or notebook is reachable\n\nThe plan is the deliverable, so write it so someone with access can run it: per sub-question, what\nyou would search or ask and why, which source kinds answer it (the spec, the paper, the maintainer,\nthe postmortem before the blog post about it), and how each claim will be grounded (a locator, not\na summary). Name the gaps you could not close and say so, because an answer from memory dressed as\nresearch is the failure this flow exists to prevent.\n\n## Done when\n\nEvery load-bearing claim cites a source, not a summary of one. Contradictions stay written down as\nopen questions, never averaged into a middle nobody's sources support. The gap sub-question was\nasked and answered, and sources found outside the notebook are now in it.\n\n## Red flags\n\n- When the passes are about to start without written sub-questions, write them, because nobody can\n  say when it is finished.\n- When one pass is about to stand as the answer, run the adversarial one, because otherwise you\n  hold an impression, not a finding.\n- When a gap was researched and the result is not in the notebook, add it, because the next pass\n  cannot cite it.\n- When findings sit in the conversation, move them to the file, because material in context\n  crowds out the reasoning that turns it into a conclusion.\n\n## Say it in the reply\n\nWhat was concluded, in the words a reader would use; what stayed open and whether the sources\ndisagree or none covered it; where the findings file, the notebook, and the notes are. Not the\nfindings themselves, because pasting them back buries the conclusion.\n",{"name":5,"description":7},"main","c385fc50aadaee7296445e049153ce0560a9c80c","plugins\u002Fqsm-knowledge\u002Fskills\u002Fgrounded-research","https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace","https:\u002F\u002Fgithub.com\u002Fqsmark-labs","2026-11-13 18:31:51",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add qsmark-labs\u002Fqsm-marketplace --skill grounded-research",{"tool":36,"command":37},"bunx","bunx skills add qsmark-labs\u002Fqsm-marketplace --skill grounded-research",{"tool":39,"command":40},"pnpm","pnpm dlx skills add qsmark-labs\u002Fqsm-marketplace --skill grounded-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-knowledge\u002Fskills\u002Fgrounded-research\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7EJWPJ0B4E1P148MWQ3GMR8","worktrunk","Use when working with git worktrees or wt (worktrunk): creating, switching, merging or removing a branch workspace, configuring wt (project or personal config, workflow hooks around switch, commit and merge, commit-message generation, hook approvals), or a wt command that failed. Triggers: make a worktree for this branch, wt merge, wt remove, configure wt, .config\u002Fwt.toml, run tests before merge, install deps when a worktree is created, wt hook, wt switch does not cd, nastav wt, wt nefunguje.","https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-worktrunk\u002Fskills\u002Fworktrunk\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7EJWD4F683TF21N89JGWZB2","web-ladder","Use when a task needs something the internet holds: look something up, search the web, find which page answers a question, read a page, check a library's current docs, a page that needs a browser or shows a captcha. Runs one research loop: searxng search, keywords, cases, search again up to three times, Context7 for a library, Tavily when the keywords will not come, one page in a browser, the person on a wall. Triggers: look this up, search the web, find out online, read this page, check the docs, the page is blocked, captcha, najdi na webu, otevri tu stranku. A multi-round question goes to the qsm-web:web-research agent; one tool's commands are its own skill (searxng, browserbox, opensrc).","https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-web\u002Fskills\u002Fweb-ladder\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7EJW9G0K6AS5Z4H0B0K6NDB","searxng","Use when running a web search through the person's own SearXNG instance with qsm-web searxng: choosing a search profile or engines, the instance, time range or language, reading its JSON, a suspended engine. Triggers: search with searxng, qsm-web searxng, search profile, niche search, academic search, IT search, vyhledavaci profil, searxng is down, which engines. The research loop around it is the web-ladder skill.","https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-web\u002Fskills\u002Fsearxng\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7EJW40RD3DRBQVVCW6K7NMG","opensrc","Use when the source code of an open-source library or repository is needed on disk to read: the docs are silent, the behaviour must be checked in code, the version the project pins. Runs qsm-web opensrc get with a package spec or a repository address. Triggers: get the source of this package, clone this library, read the library's code, qsm-web opensrc, stahni zdrojak knihovny. Library docs are the Context7 skill; the research loop is the web-ladder skill.","https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-web\u002Fskills\u002Fopensrc\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7EJVZWD6J7W91G69GMBWBQS","browserbox","Use when one page needs a real browser through qsm-web browserbox: content built by script, a page that blocks plain fetching, a captcha to solve or hand to the person, a scripted sequence of clicks, a login the person is present for. Triggers: open it in a browser, the page is empty without JavaScript, captcha, take over the browser, run these steps on the page, log in to this site, browserbox. When to reach for a browser at all is the web-ladder skill.","https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-web\u002Fskills\u002Fbrowserbox\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7EJVSZC1E8ZGVE8KXVFPR9S","usage","Use when the user wants a review of how they use Claude Code, or setup hands over after a first install: review my Claude Code usage, audit my setup, what does my setup cost, where did my tokens go, clean up my Claude Code, usage report, zkontroluj moje pouzivani. One walkthrough of four stages (machine, work, habits, extensions), questions after each, then one plan. A question about one topic (which hooks are slow) goes to that topic's skill; this session's tokens alone is `\u002Fqsm-usage`.","https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-usage\u002Fskills\u002Fusage\u002FSKILL.md",[],[]]