[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EJDPC05WQDRGSFQ46ABFB5":3,"skill-same:01M7EJDPC05WQDRGSFQ46ABFB5":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},"01M7EJDPC05WQDRGSFQ46ABFB5","book-to-skill",null,"Use when a book, paper, or long document should become one self-contained skill, naming the book only as its source: turn this PDF or EPUB into a skill, extract the frameworks and rules from a document, build on-demand guidance from a book. Triggers: turn this book into a skill, make a skill from this PDF, extract the frameworks from this document, convert this EPUB, knihu na skill.","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-book-to-skill\u002Fskills\u002Fbook-to-skill\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: book-to-skill\ndescription: \"Use when a book, paper, or long document should become one self-contained skill, naming the book only as its source: turn this PDF or EPUB into a skill, extract the frameworks and rules from a document, build on-demand guidance from a book. Triggers: turn this book into a skill, make a skill from this PDF, extract the frameworks from this document, convert this EPUB, knihu na skill.\"\n---\n\n# Book to skill\n\nA book holds rules, ideas and abstractions the agent cannot carry into a session. This turns it\ninto ONE self-contained skill document: the summary, rules, ideas and abstractions as instructions\nthe agent can act on, in the author's own names. Once written, the document stands without the\nbook. It names the book once, as its source (\"we follow the X architecture, as AAA does\"), and\nnever a chapter or a page. It is not a book report or an index: a book is worth converting only\nwhen it changes how the agent works, so a book the model already knows by heart gets a short\ndocument or none. The binary `qsm-book-to-skill` does the mechanical stages; reading each chapter\nand deciding what the agent must keep is yours, because that is judgement.\n\n## The flow\n\n```bash\nqsm-book-to-skill validate \u003Cpath-or-directory-or-glob>... --work \u003Cdir>\nqsm-book-to-skill extract --work \u003Cdir>\nqsm-book-to-skill analyze --work \u003Cdir>\nqsm-book-to-skill draft --work \u003Cdir>\n#   fill every \u003Cdir>\u002Fdraft\u002Fchapters\u002FNN-*.md from its NN-*.source.md\nqsm-book-to-skill assemble --description \"\u003Cwhen to load it>\" --out \u003Cskills-dir> --work \u003Cdir>\nqsm-book-to-skill scan --work \u003Cdir>\n```\n\n`assemble` merges every filled chapter summary into one `SKILL.md`; the `.source.md` files and the\nchapter files stay in the work directory. Each stage reads the previous one's files, so a stage\nthat went wrong is re-run alone. Name `--work` for anything longer than one sitting, because\nwithout it the run lands in a temporary directory a later session cannot find. `qsm-book-to-skill\ndoctor` reports which optional converters are missing: PDF needs `pdftotext`, EPUB, DOCX and RTF\nneed `pandoc`, MOBI and AZW need `ebook-convert`. When one is missing say so and let the person\ndecide; do not convert the source to another format behind his back.\n\n## How to fill a chapter\n\n- Read the chapter's own `.source.md`, one chapter at a time, never the whole extracted text,\n  because a model summarising a chapter it can hold beats one summarising a book it cannot.\n- Write the rule or the framework, not where the book said it. No page numbers, no \"see chapter\",\n  no cross-references: the reader of the skill never holds the book beside it, and a reference is\n  a pointer to nothing. `scan` fails on a page or chapter reference.\n- Keep the author's exact names (\"the 5 Whys\", not \"asking why several times\"), because the name\n  is how the person recognises the idea later.\n- Write each rule with its reason and, where the book gives one, its edge case, because a rule\n  without a reason is applied too wide or not at all.\n- Delete a section the chapter has nothing for, because a section padded to look full teaches the\n  reader to skip the full ones.\n- Retitle a chapter heading that is only a chapter number or the book's own outline (\"Part 2:\n  Ch. 4\") to the idea it teaches, because the heading becomes a section of the document.\n- When `analyze` reports a chapter far larger than the rest, check the source before summarising\n  it: it is usually a boundary that was missed (a PDF whose headings extracted as body text comes\n  back as one chapter).\n\n## After assemble\n\nThe result is one document the agent loads whole, so read it once as the reader will, and cut.\n\n- Open it with the source line: the book and author named once, and the stance the person takes\n  from it, as one sentence. That is the only place the book appears.\n- Merge a rule two chapters repeat into one place, and drop the chapter order when the ideas read\n  better grouped by the decision they serve.\n- Keep it under 8 KB, 12 at the most. A book that needs more holds two subjects: build two\n  documents with two descriptions, because an oversized skill is skimmed.\n\n## Decisions\n\n- Ask once where the skill goes and pass it as `--out`, because the destination depends on which\n  agent loads it and a guess lands where nothing looks. `QSM_SKILLS_DIR` also works.\n- Write `--description` as the trigger: when to use the skill and what the person would be saying\n  then. `assemble` refuses to run without one, because a description of the book instead of the\n  occasion means the skill never loads.\n- A source `validate` or `extract` could not read is named in the reply and the others go on; do\n  not restart the run for one file.\n- A placeholder left anywhere, or a failed scan, means the run is not done: fill it or delete the\n  section that holds it.\n\n## Red flags\n\n- When you are about to read the whole extracted text into context, run `analyze` and `draft`\n  instead, because a chapter at a time is what fits.\n- When a summary would fit any book on the subject, go back to the chapter and take its named\n  frameworks, because a generic summary changes nothing about how the agent works.\n- When you cannot point at a framework in the chapter's own text, drop it, because it is yours,\n  not the author's.\n- When you want to write the skill by hand because the binary is slower, run `assemble`, because\n  the scan is bound to what it builds.\n\n## Say it in the reply\n\nThe skill's location and slug, its size, any source that failed to extract with the reason, and\nthe scan result: clean, or each finding on a line. Last line: done, or the one thing still\nunfilled.\n","# Book to skill\n\nA book holds rules, ideas and abstractions the agent cannot carry into a session. This turns it\ninto ONE self-contained skill document: the summary, rules, ideas and abstractions as instructions\nthe agent can act on, in the author's own names. Once written, the document stands without the\nbook. It names the book once, as its source (\"we follow the X architecture, as AAA does\"), and\nnever a chapter or a page. It is not a book report or an index: a book is worth converting only\nwhen it changes how the agent works, so a book the model already knows by heart gets a short\ndocument or none. The binary `qsm-book-to-skill` does the mechanical stages; reading each chapter\nand deciding what the agent must keep is yours, because that is judgement.\n\n## The flow\n\n```bash\nqsm-book-to-skill validate \u003Cpath-or-directory-or-glob>... --work \u003Cdir>\nqsm-book-to-skill extract --work \u003Cdir>\nqsm-book-to-skill analyze --work \u003Cdir>\nqsm-book-to-skill draft --work \u003Cdir>\n#   fill every \u003Cdir>\u002Fdraft\u002Fchapters\u002FNN-*.md from its NN-*.source.md\nqsm-book-to-skill assemble --description \"\u003Cwhen to load it>\" --out \u003Cskills-dir> --work \u003Cdir>\nqsm-book-to-skill scan --work \u003Cdir>\n```\n\n`assemble` merges every filled chapter summary into one `SKILL.md`; the `.source.md` files and the\nchapter files stay in the work directory. Each stage reads the previous one's files, so a stage\nthat went wrong is re-run alone. Name `--work` for anything longer than one sitting, because\nwithout it the run lands in a temporary directory a later session cannot find. `qsm-book-to-skill\ndoctor` reports which optional converters are missing: PDF needs `pdftotext`, EPUB, DOCX and RTF\nneed `pandoc`, MOBI and AZW need `ebook-convert`. When one is missing say so and let the person\ndecide; do not convert the source to another format behind his back.\n\n## How to fill a chapter\n\n- Read the chapter's own `.source.md`, one chapter at a time, never the whole extracted text,\n  because a model summarising a chapter it can hold beats one summarising a book it cannot.\n- Write the rule or the framework, not where the book said it. No page numbers, no \"see chapter\",\n  no cross-references: the reader of the skill never holds the book beside it, and a reference is\n  a pointer to nothing. `scan` fails on a page or chapter reference.\n- Keep the author's exact names (\"the 5 Whys\", not \"asking why several times\"), because the name\n  is how the person recognises the idea later.\n- Write each rule with its reason and, where the book gives one, its edge case, because a rule\n  without a reason is applied too wide or not at all.\n- Delete a section the chapter has nothing for, because a section padded to look full teaches the\n  reader to skip the full ones.\n- Retitle a chapter heading that is only a chapter number or the book's own outline (\"Part 2:\n  Ch. 4\") to the idea it teaches, because the heading becomes a section of the document.\n- When `analyze` reports a chapter far larger than the rest, check the source before summarising\n  it: it is usually a boundary that was missed (a PDF whose headings extracted as body text comes\n  back as one chapter).\n\n## After assemble\n\nThe result is one document the agent loads whole, so read it once as the reader will, and cut.\n\n- Open it with the source line: the book and author named once, and the stance the person takes\n  from it, as one sentence. That is the only place the book appears.\n- Merge a rule two chapters repeat into one place, and drop the chapter order when the ideas read\n  better grouped by the decision they serve.\n- Keep it under 8 KB, 12 at the most. A book that needs more holds two subjects: build two\n  documents with two descriptions, because an oversized skill is skimmed.\n\n## Decisions\n\n- Ask once where the skill goes and pass it as `--out`, because the destination depends on which\n  agent loads it and a guess lands where nothing looks. `QSM_SKILLS_DIR` also works.\n- Write `--description` as the trigger: when to use the skill and what the person would be saying\n  then. `assemble` refuses to run without one, because a description of the book instead of the\n  occasion means the skill never loads.\n- A source `validate` or `extract` could not read is named in the reply and the others go on; do\n  not restart the run for one file.\n- A placeholder left anywhere, or a failed scan, means the run is not done: fill it or delete the\n  section that holds it.\n\n## Red flags\n\n- When you are about to read the whole extracted text into context, run `analyze` and `draft`\n  instead, because a chapter at a time is what fits.\n- When a summary would fit any book on the subject, go back to the chapter and take its named\n  frameworks, because a generic summary changes nothing about how the agent works.\n- When you cannot point at a framework in the chapter's own text, drop it, because it is yours,\n  not the author's.\n- When you want to write the skill by hand because the binary is slower, run `assemble`, because\n  the scan is bound to what it builds.\n\n## Say it in the reply\n\nThe skill's location and slug, its size, any source that failed to extract with the reason, and\nthe scan result: clean, or each finding on a line. Last line: done, or the one thing still\nunfilled.\n",{"name":5,"description":7},"main","c385fc50aadaee7296445e049153ce0560a9c80c","plugins\u002Fqsm-book-to-skill\u002Fskills\u002Fbook-to-skill","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 book-to-skill",{"tool":36,"command":37},"bunx","bunx skills add qsmark-labs\u002Fqsm-marketplace --skill book-to-skill",{"tool":39,"command":40},"pnpm","pnpm dlx skills add qsmark-labs\u002Fqsm-marketplace --skill book-to-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-book-to-skill\u002Fskills\u002Fbook-to-skill\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",[],[]]