[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EJVC2V6AFSBFJ68HKWNQE2":3,"skill-same:01M7EJVC2V6AFSBFJ68HKWNQE2":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},"01M7EJVC2V6AFSBFJ68HKWNQE2","permissions-tune",null,"Use when permission prompts get in the way: fewer permission prompts, pre-approve read-only commands, why was that denied, allowlist commands I keep approving, make auto mode my default, stop asking me for git log. Proposes auto mode as the default mode and exact allow rules for read-only calls that keep prompting, from transcript evidence.","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-usage\u002Fskills\u002Fpermissions-tune\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: permissions-tune\ndescription: \"Use when permission prompts get in the way: fewer permission prompts, pre-approve read-only commands, why was that denied, allowlist commands I keep approving, make auto mode my default, stop asking me for git log. Proposes auto mode as the default mode and exact allow rules for read-only calls that keep prompting, from transcript evidence.\"\n---\n\n# Permissions tune\n\nEvery prompt for a read-only command costs a decision that changes nothing. The built-in\n`\u002Ffewer-permission-prompts` writes wildcard rules into project settings; this skill writes exact\nrules for the observed calls into the local settings, because a wildcard also approves flags nobody\nsaw. Propose two things:\nauto mode as the default, and exact allow rules for read-only calls that keep prompting. Both\nwiden what runs unasked, so each is its own question naming every change. Shared reading and apply\nrules are in the `usage` skill. A prompt saves no tokens: `savingTokens` is 0, and `savingNote`\nsays the prompts removed (\"~9 prompts per session\").\n\n## 1. Auto mode\n\nRead `permissions.defaultMode` by key from user, project and local settings. Healthy: user says\n`\"auto\"` and nothing overrides it. A project value other than `\"auto\"` wins over the user's: say\nso. Skip with one line when managed policy sets `defaultMode` or any file has `disableAutoMode:\n\"disable\"`. Otherwise propose `\"permissions\": {\"defaultMode\": \"auto\"}` in `~\u002F.claude\u002Fsettings.json`\nonly, because `\"auto\"` in project settings is ignored. It applies to every project.\n\n## 2. Allow rules\n\nThe ledger records uses, not prompts, so read the ~50 newest transcripts.\n\n1. **Collect** `user` entries with `toolDenialKind` (`user-rejected`, `permission-rule`,\n   `automode-*`); `interrupted` and `cancelled` are aborts. Follow `tool_use_id` back to the\n   `tool_use` for name and input. Older transcripts without the field: match the denial text, label\n   counts unverified, never for `mcp__*` (the server writes that text).\n2. **Rank.** Key Bash on command plus first subcommand (`git log`), MCP on the full\n   `mcp__\u003Cserver>__\u003Ctool>`. Drop under ~3 uses, keep the top ~20.\n3. **Keep only read-only.** Drop: interpreters and runners (`python`, `node`, `bun`, `bash`,\n   `npx`, `bunx`, `uvx`); wildcards of task runners (`npm run *`, `make *`, `just *`; exact\n   `Bash(bun run typecheck)` is fine); `curl`, `wget`, `git fetch`, `git pull`, any `gh api`,\n   `docker exec`, `kubectl exec`, `sudo`; `find -exec` or `-delete`; any `-c key=value`,\n   `--exec-path`, `--upload-pack`, `VAR=x` prefix, pipe or redirection; anything under an existing\n   `deny` or `ask` rule; commands Claude Code already allows (`ls`, `cat`, `git status`, `rg`, most\n   read-only git and gh), because a denial there came from a rule or the classifier.\n4. **Exact rules only**: `Bash(git log --oneline -20)`, never `Bash(git log *)`, because read-only\n   subcommands have writing flags (`git log --output=\u003Cfile>`, `git branch -D`) and transcript\n   strings can be steered by prompt injection: an exact rule approves only what was observed. MCP:\n   one full tool name per rule, never `mcp__x__get_*`.\n5. **Mostly `user-rejected`** means the person said no: include the rule only with that stated.\n\nDestination: `permissions.allow` in `.claude\u002Fsettings.local.json`, never user scope, because the\nevidence spans every project. Deduplicate; never touch `deny` or `ask`.\n\n## Findings\n\nOne finding per rule and one for the mode: `change.kind: \"edit\"`, `target` the settings file, the\nrule in `detail`, `verdict: \"fix\"`, `question: \"permissions\"`. Asked alone: a table `| # | Rule |\nCount | Denial kinds | Why read-only |`, then what was skipped and why (\"dropped `git push`:\nwrites; dropped `cat`: already allowed\"). Ask once; apply only on yes; then say the file, the rules\nadded, and how to remove them.\n\n## Red flags\n\n- When a candidate is a wildcard, narrow it to the observed command or drop it, because a wildcard\n  approves flags nobody saw.\n- When the command was denied by a `deny` rule, skip it, because the person decided already.\n\n## Say it in the reply\n\nThe table, what was skipped, and every rule and mode change awaiting a yes.\n","# Permissions tune\n\nEvery prompt for a read-only command costs a decision that changes nothing. The built-in\n`\u002Ffewer-permission-prompts` writes wildcard rules into project settings; this skill writes exact\nrules for the observed calls into the local settings, because a wildcard also approves flags nobody\nsaw. Propose two things:\nauto mode as the default, and exact allow rules for read-only calls that keep prompting. Both\nwiden what runs unasked, so each is its own question naming every change. Shared reading and apply\nrules are in the `usage` skill. A prompt saves no tokens: `savingTokens` is 0, and `savingNote`\nsays the prompts removed (\"~9 prompts per session\").\n\n## 1. Auto mode\n\nRead `permissions.defaultMode` by key from user, project and local settings. Healthy: user says\n`\"auto\"` and nothing overrides it. A project value other than `\"auto\"` wins over the user's: say\nso. Skip with one line when managed policy sets `defaultMode` or any file has `disableAutoMode:\n\"disable\"`. Otherwise propose `\"permissions\": {\"defaultMode\": \"auto\"}` in `~\u002F.claude\u002Fsettings.json`\nonly, because `\"auto\"` in project settings is ignored. It applies to every project.\n\n## 2. Allow rules\n\nThe ledger records uses, not prompts, so read the ~50 newest transcripts.\n\n1. **Collect** `user` entries with `toolDenialKind` (`user-rejected`, `permission-rule`,\n   `automode-*`); `interrupted` and `cancelled` are aborts. Follow `tool_use_id` back to the\n   `tool_use` for name and input. Older transcripts without the field: match the denial text, label\n   counts unverified, never for `mcp__*` (the server writes that text).\n2. **Rank.** Key Bash on command plus first subcommand (`git log`), MCP on the full\n   `mcp__\u003Cserver>__\u003Ctool>`. Drop under ~3 uses, keep the top ~20.\n3. **Keep only read-only.** Drop: interpreters and runners (`python`, `node`, `bun`, `bash`,\n   `npx`, `bunx`, `uvx`); wildcards of task runners (`npm run *`, `make *`, `just *`; exact\n   `Bash(bun run typecheck)` is fine); `curl`, `wget`, `git fetch`, `git pull`, any `gh api`,\n   `docker exec`, `kubectl exec`, `sudo`; `find -exec` or `-delete`; any `-c key=value`,\n   `--exec-path`, `--upload-pack`, `VAR=x` prefix, pipe or redirection; anything under an existing\n   `deny` or `ask` rule; commands Claude Code already allows (`ls`, `cat`, `git status`, `rg`, most\n   read-only git and gh), because a denial there came from a rule or the classifier.\n4. **Exact rules only**: `Bash(git log --oneline -20)`, never `Bash(git log *)`, because read-only\n   subcommands have writing flags (`git log --output=\u003Cfile>`, `git branch -D`) and transcript\n   strings can be steered by prompt injection: an exact rule approves only what was observed. MCP:\n   one full tool name per rule, never `mcp__x__get_*`.\n5. **Mostly `user-rejected`** means the person said no: include the rule only with that stated.\n\nDestination: `permissions.allow` in `.claude\u002Fsettings.local.json`, never user scope, because the\nevidence spans every project. Deduplicate; never touch `deny` or `ask`.\n\n## Findings\n\nOne finding per rule and one for the mode: `change.kind: \"edit\"`, `target` the settings file, the\nrule in `detail`, `verdict: \"fix\"`, `question: \"permissions\"`. Asked alone: a table `| # | Rule |\nCount | Denial kinds | Why read-only |`, then what was skipped and why (\"dropped `git push`:\nwrites; dropped `cat`: already allowed\"). Ask once; apply only on yes; then say the file, the rules\nadded, and how to remove them.\n\n## Red flags\n\n- When a candidate is a wildcard, narrow it to the observed command or drop it, because a wildcard\n  approves flags nobody saw.\n- When the command was denied by a `deny` rule, skip it, because the person decided already.\n\n## Say it in the reply\n\nThe table, what was skipped, and every rule and mode change awaiting a yes.\n",{"name":5,"description":7},"main","c385fc50aadaee7296445e049153ce0560a9c80c","plugins\u002Fqsm-usage\u002Fskills\u002Fpermissions-tune","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 permissions-tune",{"tool":36,"command":37},"bunx","bunx skills add qsmark-labs\u002Fqsm-marketplace --skill permissions-tune",{"tool":39,"command":40},"pnpm","pnpm dlx skills add qsmark-labs\u002Fqsm-marketplace --skill permissions-tune","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fqsmark-labs\u002Fqsm-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fqsm-usage\u002Fskills\u002Fpermissions-tune\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",[],[]]