[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ASQ1MJDX7QDB85GQRWJ2MH":3,"skill-same:01M7ASQ1MJDX7QDB85GQRWJ2MH":123},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7ASQ1MJDX7QDB85GQRWJ2MH","lustra",null,"Use when the user wants to clean up AI slop, harden a codebase, or run technical due diligence: review code for security flaws and vulnerable or wrongly-licensed dependencies, find and remove dead code, audit dependency health, run and triage linters, type checkers, test suites and formatters, evaluate design principles (SOLID and the cohesion\u002Fcoupling equivalents for non-OO stacks), audit logging and observability, find performance smells, check documentation and CI health, scaffold baseline configs for the detected stack, do a structured code review, guide a one-major-at-a-time dependency migration, fix project structure, or produce one aggregated health report across all of these. Triggers on phrases like clean this up, find security issues, remove dead code, check dependencies, lint, typecheck, run the tests, format, review my code, check the design, check logging, is this slow, migrate a dependency, fix the project structure, set up the project, audit everything, due diligence, or this looks like AI slop. Wraps the detected stack's real tooling — dependency auditor, linter, type checker, test runner, formatter, dead-code and license scanners — and triages its output. Not for UI\u002Fvisual design work.","saski\u002Farnesto","saski","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F140356?v=4","01M7ASBDSNXTRYDYB4K1PEA1RV","01M7ASBDTAKBDAAV99S1GE7HK6",6,"Unlicense","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: lustra\ndescription: \"Use when the user wants to clean up AI slop, harden a codebase, or run technical due diligence: review code for security flaws and vulnerable or wrongly-licensed dependencies, find and remove dead code, audit dependency health, run and triage linters, type checkers, test suites and formatters, evaluate design principles (SOLID and the cohesion\u002Fcoupling equivalents for non-OO stacks), audit logging and observability, find performance smells, check documentation and CI health, scaffold baseline configs for the detected stack, do a structured code review, guide a one-major-at-a-time dependency migration, fix project structure, or produce one aggregated health report across all of these. Triggers on phrases like clean this up, find security issues, remove dead code, check dependencies, lint, typecheck, run the tests, format, review my code, check the design, check logging, is this slow, migrate a dependency, fix the project structure, set up the project, audit everything, due diligence, or this looks like AI slop. Wraps the detected stack's real tooling — dependency auditor, linter, type checker, test runner, formatter, dead-code and license scanners — and triages its output. Not for UI\u002Fvisual design work.\"\nuser-invocable: true\nargument-hint: \"[audit|baseline|review|types|tests|analyze|format|security|license|deadcode|deps|design|observability|perf|docs|migrate|ci|structure] [target]\"\nallowed-tools: Bash Read Edit Grep Glob\n---\n\n# Lustra\n\nLustra wraps real code-hygiene tooling and applies judgment on top of it. It does not\nguess where a tool would. It runs the tool, filters false positives, ranks what matters,\nand applies only the changes the user approves.\n\n## Dispatch\n\n`$1` is the command. `$2` and beyond are the target (a path or glob). When no target is\ngiven, default to the whole repository.\n\n- If `$1` is empty or `help`, print the command list below and stop.\n- Otherwise read `${CLAUDE_SKILL_DIR}\u002Freference\u002F$1.md` and follow it exactly, scoped to the\n  target. If `reference\u002F$1.md` does not exist, say so and print the command list.\n\n## Commands\n\nGrouped by lifecycle phase. `audit` runs the diagnostic ones together.\n\n**Assess \u002F start**\n- `audit` — meta-command: one graded health report across every dimension (due diligence).\n- `baseline` — scaffold the guardrail configs a project should have, for the detected stack.\n\n**Iterate**\n- `review` — structured correctness \u002F design \u002F slop review of a diff or path.\n- `types` — type-checker triage; catch `any`\u002F`@ts-ignore`-style evasion.\n- `tests` — run the suite, coverage on the diff, catch fake\u002Fempty tests.\n- `analyze` — the linter's findings plus AI-slop smells that no rule catches.\n- `format` — formatting drift, fixed mechanically.\n\n**Polish**\n- `security` — vulnerabilities: secrets, injection, broken authorization, vulnerable deps.\n- `license` — dependency license compatibility and IP risk.\n- `deadcode` — unused files, exports, and dependencies; deletes only what is confirmed.\n- `deps` — dependency health and upgrades: outdated, deprecated, duplicated. Reports\n  unused deps and advisories but defers deletion to `deadcode` and vuln fixes to `security`.\n- `design` — module\u002Fpackage design quality: SOLID, or cohesion\u002Fcoupling\u002Fcomposition for\n  non-OO stacks. Module-scoped, unlike diff-scoped `review` or layout-scoped `structure`.\n- `observability` — logging and instrumentation quality so failures are diagnosable.\n- `perf` — performance smells: N+1, blocking IO, unbounded growth, bundle weight.\n- `docs` — documentation drift and undocumented public surface.\n\n**Maintain**\n- `migrate` — guided one-major-at-a-time dependency migration: changelog, codemods, suite.\n- `ci` — pipeline soundness: real gates, CI security, reproducibility.\n- `structure` — detect the stack, then report or reorganize project structure.\n\n## Rules that override every reference file\n\nThese come from the project's own engineering guidelines and are not negotiable:\n\n1. **Surgical.** Every changed line must trace to the requested command. Never \"improve\"\n   adjacent code, comments, or formatting that the command did not target.\n2. **No silent changes — ever.** Nothing is auto-applied, not even mechanically-safe\n   formatting or an unambiguously unused import. Every change is presented as an itemized\n   checklist with its evidence\u002Fdiff, and only the items the user approves are applied.\n3. **Report honestly.** If a tool is missing, a step was skipped, or a finding is\n   low-confidence, say so plainly. Do not present a partial pass as a clean one.\n4. **English only**, in all output and any code or config you write.\n5. **Confirm before any file or dependency change.** Not just destructive or\n   hard-to-reverse ones — every edit goes through the Confirmation flow below as a staged,\n   explicitly-confirmed checklist, never a bulk rewrite.\n\n## Confirmation flow\n\nThe single flow every command follows (the `deadcode` pattern). Reference files do not\nredefine it:\n\n1. Run the read-only detect\u002Ftriage steps automatically — these never need confirmation.\n2. Present every proposed change as an itemized checklist: the `file`\u002Ftarget, the exact\n   action (command or diff), and the evidence\u002Freason per item.\n3. Apply only the items the user approves, in one reviewable change.\n4. Re-run the relevant check to confirm clean, then report what was applied, what was\n   skipped, and why.\n\nRead-only detection is exempt. Changing files or dependencies is not.\n\n## Stack detection\n\nEvery command that runs a tool first identifies the stack. Reference files point here and\ndo not redefine this:\n\n1. Read the manifests at the target root to identify language and framework:\n   `package.json` (and the framework), `pyproject.toml`\u002F`setup.py`, `go.mod`,\n   `Cargo.toml`, `pom.xml`\u002F`build.gradle`, `Gemfile`, `composer.json`.\n2. State the detected stack explicitly before running anything. If detection is ambiguous\n   or the repo is polyglot, ask rather than assume.\n3. Pick the tool from the reference file's per-ecosystem table. If no tool exists for the\n   detected stack, say so and fall back to static reading — mark that result\n   lower-confidence. Never run a stack's tool against a project that is not that stack.\n","# Lustra\n\nLustra wraps real code-hygiene tooling and applies judgment on top of it. It does not\nguess where a tool would. It runs the tool, filters false positives, ranks what matters,\nand applies only the changes the user approves.\n\n## Dispatch\n\n`$1` is the command. `$2` and beyond are the target (a path or glob). When no target is\ngiven, default to the whole repository.\n\n- If `$1` is empty or `help`, print the command list below and stop.\n- Otherwise read `${CLAUDE_SKILL_DIR}\u002Freference\u002F$1.md` and follow it exactly, scoped to the\n  target. If `reference\u002F$1.md` does not exist, say so and print the command list.\n\n## Commands\n\nGrouped by lifecycle phase. `audit` runs the diagnostic ones together.\n\n**Assess \u002F start**\n- `audit` — meta-command: one graded health report across every dimension (due diligence).\n- `baseline` — scaffold the guardrail configs a project should have, for the detected stack.\n\n**Iterate**\n- `review` — structured correctness \u002F design \u002F slop review of a diff or path.\n- `types` — type-checker triage; catch `any`\u002F`@ts-ignore`-style evasion.\n- `tests` — run the suite, coverage on the diff, catch fake\u002Fempty tests.\n- `analyze` — the linter's findings plus AI-slop smells that no rule catches.\n- `format` — formatting drift, fixed mechanically.\n\n**Polish**\n- `security` — vulnerabilities: secrets, injection, broken authorization, vulnerable deps.\n- `license` — dependency license compatibility and IP risk.\n- `deadcode` — unused files, exports, and dependencies; deletes only what is confirmed.\n- `deps` — dependency health and upgrades: outdated, deprecated, duplicated. Reports\n  unused deps and advisories but defers deletion to `deadcode` and vuln fixes to `security`.\n- `design` — module\u002Fpackage design quality: SOLID, or cohesion\u002Fcoupling\u002Fcomposition for\n  non-OO stacks. Module-scoped, unlike diff-scoped `review` or layout-scoped `structure`.\n- `observability` — logging and instrumentation quality so failures are diagnosable.\n- `perf` — performance smells: N+1, blocking IO, unbounded growth, bundle weight.\n- `docs` — documentation drift and undocumented public surface.\n\n**Maintain**\n- `migrate` — guided one-major-at-a-time dependency migration: changelog, codemods, suite.\n- `ci` — pipeline soundness: real gates, CI security, reproducibility.\n- `structure` — detect the stack, then report or reorganize project structure.\n\n## Rules that override every reference file\n\nThese come from the project's own engineering guidelines and are not negotiable:\n\n1. **Surgical.** Every changed line must trace to the requested command. Never \"improve\"\n   adjacent code, comments, or formatting that the command did not target.\n2. **No silent changes — ever.** Nothing is auto-applied, not even mechanically-safe\n   formatting or an unambiguously unused import. Every change is presented as an itemized\n   checklist with its evidence\u002Fdiff, and only the items the user approves are applied.\n3. **Report honestly.** If a tool is missing, a step was skipped, or a finding is\n   low-confidence, say so plainly. Do not present a partial pass as a clean one.\n4. **English only**, in all output and any code or config you write.\n5. **Confirm before any file or dependency change.** Not just destructive or\n   hard-to-reverse ones — every edit goes through the Confirmation flow below as a staged,\n   explicitly-confirmed checklist, never a bulk rewrite.\n\n## Confirmation flow\n\nThe single flow every command follows (the `deadcode` pattern). Reference files do not\nredefine it:\n\n1. Run the read-only detect\u002Ftriage steps automatically — these never need confirmation.\n2. Present every proposed change as an itemized checklist: the `file`\u002Ftarget, the exact\n   action (command or diff), and the evidence\u002Freason per item.\n3. Apply only the items the user approves, in one reviewable change.\n4. Re-run the relevant check to confirm clean, then report what was applied, what was\n   skipped, and why.\n\nRead-only detection is exempt. Changing files or dependencies is not.\n\n## Stack detection\n\nEvery command that runs a tool first identifies the stack. Reference files point here and\ndo not redefine this:\n\n1. Read the manifests at the target root to identify language and framework:\n   `package.json` (and the framework), `pyproject.toml`\u002F`setup.py`, `go.mod`,\n   `Cargo.toml`, `pom.xml`\u002F`build.gradle`, `Gemfile`, `composer.json`.\n2. State the detected stack explicitly before running anything. If detection is ambiguous\n   or the repo is polyglot, ask rather than assume.\n3. Pick the tool from the reference file's per-ecosystem table. If no tool exists for the\n   detected stack, say so and fall back to static reading — mark that result\n   lower-confidence. Never run a stack's tool against a project that is not that stack.\n",{"name":5,"description":7,"allowed-tools":23,"argument-hint":24,"user-invocable":25},"Bash Read Edit Grep Glob","[audit|baseline|review|types|tests|analyze|format|security|license|deadcode|deps|design|observability|perf|docs|migrate|ci|structure] [target]",true,"main","3c24fc2c035029b08c7326774bee3fef8fb95566",".agents\u002Fskills\u002Flustra",0,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto","https:\u002F\u002Fgithub.com\u002Fsaski","http:\u002F\u002Fsaski.com","2026-11-12 20:09:16",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":25},[36,39,42],{"tool":37,"command":38},"npx","npx skills add saski\u002Farnesto --skill lustra",{"tool":40,"command":41},"bunx","bunx skills add saski\u002Farnesto --skill lustra",{"tool":43,"command":44},"pnpm","pnpm dlx skills add saski\u002Farnesto --skill lustra","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002FSKILL.md",[47,53,57,61,65,69,73,77,81,85,91,95,99,103,107,111,115,119],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"reference\u002Fanalyze.md","REFERENCE","参考文档",1937,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fanalyze.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"reference\u002Faudit.md",2068,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Faudit.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"reference\u002Fbaseline.md",1605,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fbaseline.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"reference\u002Fci.md",1735,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fci.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"reference\u002Fdeadcode.md",1646,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fdeadcode.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"reference\u002Fdeps.md",2203,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fdeps.md",{"path":74,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":75,"sourceHtmlUrl":76},"reference\u002Fdesign.md",1764,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fdesign.md",{"path":78,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":79,"sourceHtmlUrl":80},"reference\u002Fdocs.md",1454,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fdocs.md",{"path":82,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":83,"sourceHtmlUrl":84},"reference\u002Fformat.md",1500,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fformat.md",{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"reference\u002Flicense.md","LICENSE","许可证",2139,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Flicense.md",{"path":92,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":93,"sourceHtmlUrl":94},"reference\u002Fmigrate.md",1681,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fmigrate.md",{"path":96,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":97,"sourceHtmlUrl":98},"reference\u002Fobservability.md",1725,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fobservability.md",{"path":100,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":101,"sourceHtmlUrl":102},"reference\u002Fperf.md",1740,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fperf.md",{"path":104,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":105,"sourceHtmlUrl":106},"reference\u002Freview.md",1685,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Freview.md",{"path":108,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":109,"sourceHtmlUrl":110},"reference\u002Fsecurity.md",1867,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fsecurity.md",{"path":112,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":113,"sourceHtmlUrl":114},"reference\u002Fstructure.md",1498,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Fstructure.md",{"path":116,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":117,"sourceHtmlUrl":118},"reference\u002Ftests.md",1566,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Ftests.md",{"path":120,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":121,"sourceHtmlUrl":122},"reference\u002Ftypes.md",1329,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flustra\u002Freference\u002Ftypes.md",[124,131,138,145,152,159],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":18},"01M7AT7F5FSHNAMFMF01N0QA1X","visualize","Use \u002Fvisualize for creating compact charts, diagrams, or other visuals inline as part of the conversation itself. It chooses among Markdown tables, Mermaid, inline HTML, and other supported in-transcript forms. Use Canvas for durable artifacts outside the transcript that users may revisit, refine, or share.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fvisualize\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":18},"01M7AT79MHSAR3JDDMP7DGERM9","update-cursor-settings","Modify Cursor\u002FVSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cursor-settings\u002FSKILL.md",[],[],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":18},"01M7AT73WF3Y22E0FKYAMCCJES","update-cli-config","View and modify Cursor CLI configuration settings in ~\u002F.cursor\u002Fcli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cli-config\u002FSKILL.md",[],[],{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":18},"01M7AT6F3FBP85AJJ5BJNR8B5W","statusline","Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fstatusline\u002FSKILL.md",[],[],{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":18},"01M7AT6D24QFS5XRAFN8S5XJ7W","split-to-prs","Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fsplit-to-prs\u002FSKILL.md",[],[],{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":18},"01M7AT69FYFN84XZKW452JV5DF","shell","Runs the rest of a \u002Fshell request as a literal shell command. Use only when the user explicitly invokes \u002Fshell and wants the following text executed directly in the terminal.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fshell\u002FSKILL.md",[],[]]