[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EJMYXZK2KD09XDSMHF2MJM":3,"skill-same:01M7EJMYXZK2KD09XDSMHF2MJM":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},"01M7EJMYXZK2KD09XDSMHF2MJM","setup",null,"Use when the user wants qsm on a machine or wants to change what is installed or asks what to add: set up qsm, install the plugins, which plugins do I have, reconfigure qsm, doctor says, fix my Claude Code install, which qsm tools are new on main, the bin farm is stale, add a plugin to this machine, nastav qsm, nainstaluj pluginy.","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-setup\u002Fskills\u002Fsetup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: setup\ndescription: \"Use when the user wants qsm on a machine or wants to change what is installed or asks what to add: set up qsm, install the plugins, which plugins do I have, reconfigure qsm, doctor says, fix my Claude Code install, which qsm tools are new on main, the bin farm is stale, add a plugin to this machine, nastav qsm, nainstaluj pluginy.\"\n---\n\n# Setup\n\nqsm-setup is the marketplace's proactive installer. A user who knows what they want names the verb;\none who does not gets a guided run that picks the arguments, asks for the go before anything is\nwritten, and ends by offering the usage review (the qsm-usage skills do the judging). Install\nchanges no file the user owns; only an activation writes into the Claude home, so each one waits\nfor its own answer.\n\n## Direct\n\nRun the verb the user named, read the per-plugin lines, report them.\n\n- `qsm-setup install --all`, `qsm-setup install \u003Cplugin...>`, or `qsm-setup install --profile\n  general`: exactly one of the three; dependency order is the tool's job.\n- `qsm-setup doctor [\u003Cplugin>] [--verbose]`: one line per installed plugin, orphans as warnings,\n  the built-binaries check, the activation state of each plugin, then the `claude ...` lines for\n  the Claude Code installation.\n- `qsm-setup activate \u003Cplugin> -- \u003Coptions>`: the activation step of one plugin, see Guided.\n- `qsm-setup relink [--check]`: completions regenerated, undeclared binaries and completions\n  pruned; `--check` writes nothing and exits 1 when stale.\n- `qsm-setup build-bins`: every plugin's own build step, then the record doctor compares against.\n- `qsm-setup tools [--fetch]`: the qsm binaries on `origin\u002Fmain` against this machine, verbs added\n  and removed. Without `--fetch` it says how old main is and stays offline.\n\n## Guided\n\n1. Ask which plugins, with the general profile as the recommended answer: general, everything, or\n   a named list. `qsm-setup install --all --dry-run` lists every plugin and what its installer\n   would do. qsm-builder is not in the general profile and installs at project scope inside the\n   marketplace checkout only, so offer it only there.\n2. Get the go, then run one install call and read every status line. `suggested` means the\n   installer left a command for the user; `blocked` means a requirement failed first;\n   `missing-prereq` names a tool to install by hand.\n3. Then the activations, one question each, `--dry-run` first, then the user's choice, because an\n   activation writes into the Claude home. Doctor shows which plugins are activated.\n   - qsm-setup: `qsm-setup activate qsm-setup -- --instructions \u003Creplace|overwrite|skip>`. Replace\n     is the default: the plugin is the source of the instructions, and the activation rewrites only\n     its own marked area in every file it writes (CLAUDE.md, the rules, the output style), keeping\n     everything outside the markers, where text specific to this device lives. Overwrite rewrites\n     the whole file and runs only when the person asks for it.\n   - qsm-memory, when installed: \"Use the qsm session archive as the one memory? Claude Code's own\n     memory is then turned off (`autoMemoryEnabled: false`) and its transcripts are kept for good\n     (`cleanupPeriodDays: 36500`; the default deletes them after 30 days); the MCP is already\n     connected by the plugin.\" Yes: `qsm-setup activate qsm-memory -- --memory qsm`. No:\n     `--memory claude`, which records the choice and leaves Claude Code's own retention in force:\n     it deletes transcripts after 30 days and qsm-memory packs nothing.\n4. Run doctor and report PASS \u002F FAIL \u002F SKIP per plugin, the `claude ...` lines and the summary\n   line. A FAIL is a finding for the user, not something to retry.\n5. End with the usage review offer, the one walkthrough setup hands off to.\n   - doctor shows qsm-usage is not installed: say that a review session needs qsm-usage and give\n     `qsm-setup install qsm-usage`.\n   - it is installed: ask through the ask tool whether to start the usage review now. On yes load\n     the qsm-usage `usage` skill and the rest is its work. On no say the phrase that starts it\n     later: \"review my Claude Code usage\".\n\nWrite nothing and start nothing until the person says yes to that one.\n\n## Claude Code health\n\nDoctor's `claude ...` lines only report. Each FAIL names its fix; show the line and the exact fix,\nask once per fix, apply it after the yes, never a batch \"fix all\". Then run doctor again.\n\n- Removals (`claude installs`): run the command the line names.\n- PATH (`claude path`): add the line to the shell profile the user names.\n- A file that does not parse (`claude config`): read only the lines around the named line and\n  column and fix the JSON there.\n- One key (`installMethod`): read and write that key alone, `jq '.installMethod' ~\u002F.claude.json`.\n  Settings files and `.claude.json` hold tokens and paths, so never `cat` one or print its content\n  in the reply; name the file, the key and the position.\n- Agents and skills: add the missing `description:` line, rename one of the shared `name:` values,\n  or fix the frontmatter YAML at the named lines, showing the user the change.\n- Version (`claude version`): `claude update`.\n\n## Red flags\n\n- When the run is about to end after doctor with no usage review offer made, make it, because the\n  person otherwise never learns the review exists.\n- When it is a first setup, show a dry run before the install, because the user has not seen what\n  gets written.\n- When you want `--all` and plugin names in one call, pick one, because the tool refuses both.\n- When you are about to choose overwrite, ask first and name the text outside the markers it would\n  delete, because that text is specific to this device and lives nowhere else.\n- When a status is `suggested`, report it as not installed, because the user still has a command\n  to run.\n\n## Say it in the reply\n\nAfter install, one line per plugin, `name: status: detail`, nothing summarised away. After doctor,\nthe summary line plus every FAIL with its exit code and remedy.\n","# Setup\n\nqsm-setup is the marketplace's proactive installer. A user who knows what they want names the verb;\none who does not gets a guided run that picks the arguments, asks for the go before anything is\nwritten, and ends by offering the usage review (the qsm-usage skills do the judging). Install\nchanges no file the user owns; only an activation writes into the Claude home, so each one waits\nfor its own answer.\n\n## Direct\n\nRun the verb the user named, read the per-plugin lines, report them.\n\n- `qsm-setup install --all`, `qsm-setup install \u003Cplugin...>`, or `qsm-setup install --profile\n  general`: exactly one of the three; dependency order is the tool's job.\n- `qsm-setup doctor [\u003Cplugin>] [--verbose]`: one line per installed plugin, orphans as warnings,\n  the built-binaries check, the activation state of each plugin, then the `claude ...` lines for\n  the Claude Code installation.\n- `qsm-setup activate \u003Cplugin> -- \u003Coptions>`: the activation step of one plugin, see Guided.\n- `qsm-setup relink [--check]`: completions regenerated, undeclared binaries and completions\n  pruned; `--check` writes nothing and exits 1 when stale.\n- `qsm-setup build-bins`: every plugin's own build step, then the record doctor compares against.\n- `qsm-setup tools [--fetch]`: the qsm binaries on `origin\u002Fmain` against this machine, verbs added\n  and removed. Without `--fetch` it says how old main is and stays offline.\n\n## Guided\n\n1. Ask which plugins, with the general profile as the recommended answer: general, everything, or\n   a named list. `qsm-setup install --all --dry-run` lists every plugin and what its installer\n   would do. qsm-builder is not in the general profile and installs at project scope inside the\n   marketplace checkout only, so offer it only there.\n2. Get the go, then run one install call and read every status line. `suggested` means the\n   installer left a command for the user; `blocked` means a requirement failed first;\n   `missing-prereq` names a tool to install by hand.\n3. Then the activations, one question each, `--dry-run` first, then the user's choice, because an\n   activation writes into the Claude home. Doctor shows which plugins are activated.\n   - qsm-setup: `qsm-setup activate qsm-setup -- --instructions \u003Creplace|overwrite|skip>`. Replace\n     is the default: the plugin is the source of the instructions, and the activation rewrites only\n     its own marked area in every file it writes (CLAUDE.md, the rules, the output style), keeping\n     everything outside the markers, where text specific to this device lives. Overwrite rewrites\n     the whole file and runs only when the person asks for it.\n   - qsm-memory, when installed: \"Use the qsm session archive as the one memory? Claude Code's own\n     memory is then turned off (`autoMemoryEnabled: false`) and its transcripts are kept for good\n     (`cleanupPeriodDays: 36500`; the default deletes them after 30 days); the MCP is already\n     connected by the plugin.\" Yes: `qsm-setup activate qsm-memory -- --memory qsm`. No:\n     `--memory claude`, which records the choice and leaves Claude Code's own retention in force:\n     it deletes transcripts after 30 days and qsm-memory packs nothing.\n4. Run doctor and report PASS \u002F FAIL \u002F SKIP per plugin, the `claude ...` lines and the summary\n   line. A FAIL is a finding for the user, not something to retry.\n5. End with the usage review offer, the one walkthrough setup hands off to.\n   - doctor shows qsm-usage is not installed: say that a review session needs qsm-usage and give\n     `qsm-setup install qsm-usage`.\n   - it is installed: ask through the ask tool whether to start the usage review now. On yes load\n     the qsm-usage `usage` skill and the rest is its work. On no say the phrase that starts it\n     later: \"review my Claude Code usage\".\n\nWrite nothing and start nothing until the person says yes to that one.\n\n## Claude Code health\n\nDoctor's `claude ...` lines only report. Each FAIL names its fix; show the line and the exact fix,\nask once per fix, apply it after the yes, never a batch \"fix all\". Then run doctor again.\n\n- Removals (`claude installs`): run the command the line names.\n- PATH (`claude path`): add the line to the shell profile the user names.\n- A file that does not parse (`claude config`): read only the lines around the named line and\n  column and fix the JSON there.\n- One key (`installMethod`): read and write that key alone, `jq '.installMethod' ~\u002F.claude.json`.\n  Settings files and `.claude.json` hold tokens and paths, so never `cat` one or print its content\n  in the reply; name the file, the key and the position.\n- Agents and skills: add the missing `description:` line, rename one of the shared `name:` values,\n  or fix the frontmatter YAML at the named lines, showing the user the change.\n- Version (`claude version`): `claude update`.\n\n## Red flags\n\n- When the run is about to end after doctor with no usage review offer made, make it, because the\n  person otherwise never learns the review exists.\n- When it is a first setup, show a dry run before the install, because the user has not seen what\n  gets written.\n- When you want `--all` and plugin names in one call, pick one, because the tool refuses both.\n- When you are about to choose overwrite, ask first and name the text outside the markers it would\n  delete, because that text is specific to this device and lives nowhere else.\n- When a status is `suggested`, report it as not installed, because the user still has a command\n  to run.\n\n## Say it in the reply\n\nAfter install, one line per plugin, `name: status: detail`, nothing summarised away. After doctor,\nthe summary line plus every FAIL with its exit code and remedy.\n",{"name":5,"description":7},"main","c385fc50aadaee7296445e049153ce0560a9c80c","plugins\u002Fqsm-setup\u002Fskills\u002Fsetup","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 setup",{"tool":36,"command":37},"bunx","bunx skills add qsmark-labs\u002Fqsm-marketplace --skill setup",{"tool":39,"command":40},"pnpm","pnpm dlx skills add qsmark-labs\u002Fqsm-marketplace --skill setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-setup\u002Fskills\u002Fsetup\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",[],[]]