[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ASRVMYVFZTA1TS6HE53RP2":3,"skill-same:01M7ASRVMYVFZTA1TS6HE53RP2":91},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7ASRVMYVFZTA1TS6HE53RP2","nullables",null,"Writes tests without mocks using Nullables. Use when writing tests, especially testing code with external I\u002FO (HTTP, files, databases, clocks, random numbers), designing infrastructure wrappers or replacing mocking libraries.","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\u002Fnullables\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nullables\ndescription: Writes tests without mocks using Nullables. Use when writing tests, especially testing code with external I\u002FO (HTTP, files, databases, clocks, random numbers), designing infrastructure wrappers or replacing mocking libraries.\n---\n\n# Nullables: Testing Without Mocks\n\nSTARTER_CHARACTER = ⭕️\n\n## The Problem\n\nExternal I\u002FO is slow and flaky. Tests hitting real databases, APIs, or file systems run slow and fail randomly. We want tests that run in milliseconds and never fail due to network issues.\n\nMocking libraries solve speed but introduce a new problem: they couple tests to implementation by verifying specific method calls. Test code using mocking libraries is brittle—it breaks when code is refactored, even when behavior is unchanged.\n\n## The Solution\n\nNullables are production code with an \"off switch\" for infrastructure—not test doubles, but real code you can ship (dry-run modes, cache warming, offline operation). They enable **narrow, sociable, state-based tests**:\n\n- **Narrow**: Each test focuses on one class\u002Fmodule, not broad end-to-end flows\n- **Sociable**: Tests use real dependencies—only infrastructure I\u002FO is neutralized. (Contrast with \"solitary\" tests that mock everything, isolating the class under test.)\n- **State-based**: Assert on outputs and state, not on which methods were called\n\n## When to Use\n\n**Use Nullables for:**\n- Code that talks to external systems (HTTP, files, databases, clocks, random)\n- Third-party libraries you don't control\n- Non-deterministic operations\n\n**Don't use Nullables for:**\n- Pure logic — test directly, no wrapper needed\n- Your own classes — make them Nullable directly, or null their dependencies\n\n**Greenfield**: Add wrappers incrementally as tests demand—don't over-engineer upfront.\n\n**Existing codebase**: See [migration.md](references\u002Fmigration.md) for incremental conversion strategies.\n\n## The Foundation: A-Frame Architecture\n\nA-Frame is the architectural insight that makes Nullables work especially well. \nTraditional layered architecture stacks Logic on top of Infrastructure, making Logic depend on slow, brittle I\u002FO. \nA-Frame makes them **peers** instead:\n\n```\n        Application (coordinates)\n            ↓              ↓\nLogic (pure, tested)    Infrastructure (Nullables)\n```\n\n**Key rule:** Logic never imports Infrastructure directly. Application coordinates between them via [Logic Sandwich](references\u002Farchitecture\u002Flogic-sandwich.md): read → process → write.\n\n- **Logic** — pure functions, no I\u002FO\n- **Infrastructure** — wrapped with `create()`\u002F`createNull()`\n- **Application** — thin coordination layer\n\nThis separation lets you swap real infrastructure for nulled versions without touching Logic. For full details, see [a-frame.md](references\u002Farchitecture\u002Fa-frame.md). For event-driven code, see [event-driven.md](references\u002Farchitecture\u002Fevent-driven.md).\n\n## Core Pattern: Two Factory Methods\n\nEvery infrastructure wrapper has two creation paths:\n\n```javascript\nclass Clock {\n  static create() {\n    return new Clock(Date);  \u002F\u002F Real system clock\n  }\n\n  static createNull(now = \"2020-01-01T00:00:00Z\") {\n    return new Clock(new StubbedDate(now));  \u002F\u002F Controlled clock\n  }\n\n  constructor(dateClass) {\n    this._dateClass = dateClass;\n  }\n\n  now() {\n    return new this._dateClass().toISOString();\n  }\n}\n\n\u002F\u002F Embedded stub - lives in production code, not test files\nclass StubbedDate {\n  constructor(isoString) {\n    this._time = new Date(isoString).getTime();\n  }\n  toISOString() {\n    return new Date(this._time).toISOString();\n  }\n}\n```\n\n**Key principles:**\n- `createNull()` parameters match the caller's abstraction level (ISO strings, not milliseconds)\n- Embedded stubs live alongside the wrapper, implementing only what's actually used\n- Add [Output Tracking](references\u002Fbuilding\u002Foutput-tracking.md) to observe what was written\n\nFor complete construction details, see [infrastructure-wrappers.md](references\u002Fbuilding\u002Finfrastructure-wrappers.md).\n\n## Testing with Nullables\n\nEvery wrapper follows the same pattern. Here's how you test code that uses one:\n\n```javascript\ndescribe(\"App\", () => {\n  it(\"transforms input and writes result\", () => {\n    const { output } = run({ args: [\"hello\"] });\n    assert.deepEqual(output.data, [\"uryyb\\n\"]);  \u002F\u002F ROT-13\n  });\n\n  function run({ args = [] } = {}) {\n    const commandLine = CommandLine.createNull({ args });\n    const output = commandLine.trackOutput();\n    new App(commandLine).run();\n    return { output };\n  }\n});\n```\n\nTests exercise real `App` code. Only infrastructure I\u002FO is neutralized. The `run()` helper protects tests from constructor changes ([Signature Shielding](references\u002Ftest-patterns.md#helper-functions-signature-shielding)).\n\n### Testing Philosophy\n\n- **State-based, not interaction-based** — verify what was produced, not which methods were called\n- **Sociable, not solitary** — tests use real dependencies; only infrastructure is nulled. Bugs cause multiple test failures, pinpointing the problem\n- **Paranoic Telemetry** — assume everything fails. Test error paths, timeouts, and failures as thoroughly as happy paths\n- **Collaborator-Based Isolation** — use dependencies' own methods in assertions rather than hardcoding expectations:\n  ```javascript\n  \u002F\u002F BAD: Breaks if format changes (also leaks implementation details into your clients, creates bad coupling)\n  assert.deepEqual(output.data, [{ level: \"info\", message: \"Done\", ts: 123 }]);\n  \u002F\u002F GOOD: Uses dependency's format\n  assert.deepEqual(output.data, [logger.formatEntry(\"info\", \"Done\")]);\n  ```\n- **Narrow Integration Tests** — sociable tests verify logic; add a few tests per wrapper that hit real systems to catch stub drift\n\nFor testing techniques (sequences, time, events, errors), see [test-patterns.md](references\u002Ftest-patterns.md).\n\n## Building Patterns\n\nThese patterns work together:\n\n- **[Output Tracking](references\u002Fbuilding\u002Foutput-tracking.md)** — Observe what was produced, not which methods called\n- **[Configurable Responses](references\u002Fbuilding\u002Fconfigurable-responses.md)** — Control what Nullables return at your abstraction level\n- **[Embedded Stubs](references\u002Fbuilding\u002Fembedded-stubs.md)** — Stubs live in production code, maintained with wrapper\n- **[Wrapper Composition](references\u002Fbuilding\u002Finfrastructure-wrappers.md#wrapper-composition-fake-it-once-you-make-it)** — High-level code composes from lower-level Nullables; only leaves have stubs\n\n## Anti-Patterns\n\n**Using mock libraries** — Couples tests to implementation. Don't import sinon, jest.mock, etc. Nullables replace them.\n\n**Constructor connects to infrastructure** — Constructors should perform no work. Defer connections to explicit methods. See [Zero-Impact Instantiation](references\u002Fbuilding\u002Finfrastructure-wrappers.md#zero-impact-instantiation).\n\n**Parameters at wrong abstraction level** — `createNull()` should accept domain concepts, not implementation details:\n```javascript\n\u002F\u002F BAD: Leaking HTTP details\nLoginClient.createNull({ httpResponse: { status: 200, body: '{\"email\":\"x\"}' } });\n\u002F\u002F GOOD: Domain level\nLoginClient.createNull({ email: \"user@example.com\", verified: true });\n```\n\n**Stubs in test files** — Stubs belong in production code alongside the wrapper. See [embedded-stubs.md](references\u002Fbuilding\u002Fembedded-stubs.md).\n\n**Stub as complex as the real thing** — If your stub needs significant logic, reconsider the abstraction.\n","# Nullables: Testing Without Mocks\n\nSTARTER_CHARACTER = ⭕️\n\n## The Problem\n\nExternal I\u002FO is slow and flaky. Tests hitting real databases, APIs, or file systems run slow and fail randomly. We want tests that run in milliseconds and never fail due to network issues.\n\nMocking libraries solve speed but introduce a new problem: they couple tests to implementation by verifying specific method calls. Test code using mocking libraries is brittle—it breaks when code is refactored, even when behavior is unchanged.\n\n## The Solution\n\nNullables are production code with an \"off switch\" for infrastructure—not test doubles, but real code you can ship (dry-run modes, cache warming, offline operation). They enable **narrow, sociable, state-based tests**:\n\n- **Narrow**: Each test focuses on one class\u002Fmodule, not broad end-to-end flows\n- **Sociable**: Tests use real dependencies—only infrastructure I\u002FO is neutralized. (Contrast with \"solitary\" tests that mock everything, isolating the class under test.)\n- **State-based**: Assert on outputs and state, not on which methods were called\n\n## When to Use\n\n**Use Nullables for:**\n- Code that talks to external systems (HTTP, files, databases, clocks, random)\n- Third-party libraries you don't control\n- Non-deterministic operations\n\n**Don't use Nullables for:**\n- Pure logic — test directly, no wrapper needed\n- Your own classes — make them Nullable directly, or null their dependencies\n\n**Greenfield**: Add wrappers incrementally as tests demand—don't over-engineer upfront.\n\n**Existing codebase**: See [migration.md](references\u002Fmigration.md) for incremental conversion strategies.\n\n## The Foundation: A-Frame Architecture\n\nA-Frame is the architectural insight that makes Nullables work especially well. \nTraditional layered architecture stacks Logic on top of Infrastructure, making Logic depend on slow, brittle I\u002FO. \nA-Frame makes them **peers** instead:\n\n```\n        Application (coordinates)\n            ↓              ↓\nLogic (pure, tested)    Infrastructure (Nullables)\n```\n\n**Key rule:** Logic never imports Infrastructure directly. Application coordinates between them via [Logic Sandwich](references\u002Farchitecture\u002Flogic-sandwich.md): read → process → write.\n\n- **Logic** — pure functions, no I\u002FO\n- **Infrastructure** — wrapped with `create()`\u002F`createNull()`\n- **Application** — thin coordination layer\n\nThis separation lets you swap real infrastructure for nulled versions without touching Logic. For full details, see [a-frame.md](references\u002Farchitecture\u002Fa-frame.md). For event-driven code, see [event-driven.md](references\u002Farchitecture\u002Fevent-driven.md).\n\n## Core Pattern: Two Factory Methods\n\nEvery infrastructure wrapper has two creation paths:\n\n```javascript\nclass Clock {\n  static create() {\n    return new Clock(Date);  \u002F\u002F Real system clock\n  }\n\n  static createNull(now = \"2020-01-01T00:00:00Z\") {\n    return new Clock(new StubbedDate(now));  \u002F\u002F Controlled clock\n  }\n\n  constructor(dateClass) {\n    this._dateClass = dateClass;\n  }\n\n  now() {\n    return new this._dateClass().toISOString();\n  }\n}\n\n\u002F\u002F Embedded stub - lives in production code, not test files\nclass StubbedDate {\n  constructor(isoString) {\n    this._time = new Date(isoString).getTime();\n  }\n  toISOString() {\n    return new Date(this._time).toISOString();\n  }\n}\n```\n\n**Key principles:**\n- `createNull()` parameters match the caller's abstraction level (ISO strings, not milliseconds)\n- Embedded stubs live alongside the wrapper, implementing only what's actually used\n- Add [Output Tracking](references\u002Fbuilding\u002Foutput-tracking.md) to observe what was written\n\nFor complete construction details, see [infrastructure-wrappers.md](references\u002Fbuilding\u002Finfrastructure-wrappers.md).\n\n## Testing with Nullables\n\nEvery wrapper follows the same pattern. Here's how you test code that uses one:\n\n```javascript\ndescribe(\"App\", () => {\n  it(\"transforms input and writes result\", () => {\n    const { output } = run({ args: [\"hello\"] });\n    assert.deepEqual(output.data, [\"uryyb\\n\"]);  \u002F\u002F ROT-13\n  });\n\n  function run({ args = [] } = {}) {\n    const commandLine = CommandLine.createNull({ args });\n    const output = commandLine.trackOutput();\n    new App(commandLine).run();\n    return { output };\n  }\n});\n```\n\nTests exercise real `App` code. Only infrastructure I\u002FO is neutralized. The `run()` helper protects tests from constructor changes ([Signature Shielding](references\u002Ftest-patterns.md#helper-functions-signature-shielding)).\n\n### Testing Philosophy\n\n- **State-based, not interaction-based** — verify what was produced, not which methods were called\n- **Sociable, not solitary** — tests use real dependencies; only infrastructure is nulled. Bugs cause multiple test failures, pinpointing the problem\n- **Paranoic Telemetry** — assume everything fails. Test error paths, timeouts, and failures as thoroughly as happy paths\n- **Collaborator-Based Isolation** — use dependencies' own methods in assertions rather than hardcoding expectations:\n  ```javascript\n  \u002F\u002F BAD: Breaks if format changes (also leaks implementation details into your clients, creates bad coupling)\n  assert.deepEqual(output.data, [{ level: \"info\", message: \"Done\", ts: 123 }]);\n  \u002F\u002F GOOD: Uses dependency's format\n  assert.deepEqual(output.data, [logger.formatEntry(\"info\", \"Done\")]);\n  ```\n- **Narrow Integration Tests** — sociable tests verify logic; add a few tests per wrapper that hit real systems to catch stub drift\n\nFor testing techniques (sequences, time, events, errors), see [test-patterns.md](references\u002Ftest-patterns.md).\n\n## Building Patterns\n\nThese patterns work together:\n\n- **[Output Tracking](references\u002Fbuilding\u002Foutput-tracking.md)** — Observe what was produced, not which methods called\n- **[Configurable Responses](references\u002Fbuilding\u002Fconfigurable-responses.md)** — Control what Nullables return at your abstraction level\n- **[Embedded Stubs](references\u002Fbuilding\u002Fembedded-stubs.md)** — Stubs live in production code, maintained with wrapper\n- **[Wrapper Composition](references\u002Fbuilding\u002Finfrastructure-wrappers.md#wrapper-composition-fake-it-once-you-make-it)** — High-level code composes from lower-level Nullables; only leaves have stubs\n\n## Anti-Patterns\n\n**Using mock libraries** — Couples tests to implementation. Don't import sinon, jest.mock, etc. Nullables replace them.\n\n**Constructor connects to infrastructure** — Constructors should perform no work. Defer connections to explicit methods. See [Zero-Impact Instantiation](references\u002Fbuilding\u002Finfrastructure-wrappers.md#zero-impact-instantiation).\n\n**Parameters at wrong abstraction level** — `createNull()` should accept domain concepts, not implementation details:\n```javascript\n\u002F\u002F BAD: Leaking HTTP details\nLoginClient.createNull({ httpResponse: { status: 200, body: '{\"email\":\"x\"}' } });\n\u002F\u002F GOOD: Domain level\nLoginClient.createNull({ email: \"user@example.com\", verified: true });\n```\n\n**Stubs in test files** — Stubs belong in production code alongside the wrapper. See [embedded-stubs.md](references\u002Fbuilding\u002Fembedded-stubs.md).\n\n**Stub as complex as the real thing** — If your stub needs significant logic, reconsider the abstraction.\n",{"name":5,"description":7},"main","3c24fc2c035029b08c7326774bee3fef8fb95566",".agents\u002Fskills\u002Fnullables",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":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add saski\u002Farnesto --skill nullables",{"tool":37,"command":38},"bunx","bunx skills add saski\u002Farnesto --skill nullables",{"tool":40,"command":41},"pnpm","pnpm dlx skills add saski\u002Farnesto --skill nullables","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002FSKILL.md",true,[45,51,55,59,63,67,71,75,79,83,87],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"credits.md","REFERENCE","参考文档",136,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Fcredits.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"links.md",443,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Flinks.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Farchitecture\u002Fa-frame.md",2365,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Freferences\u002Farchitecture\u002Fa-frame.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Farchitecture\u002Fevent-driven.md",3022,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Freferences\u002Farchitecture\u002Fevent-driven.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Farchitecture\u002Flogic-sandwich.md",3065,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Freferences\u002Farchitecture\u002Flogic-sandwich.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fbuilding\u002Fconfigurable-responses.md",5934,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Freferences\u002Fbuilding\u002Fconfigurable-responses.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fbuilding\u002Fembedded-stubs.md",7508,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Freferences\u002Fbuilding\u002Fembedded-stubs.md",{"path":76,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fbuilding\u002Finfrastructure-wrappers.md",12234,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Freferences\u002Fbuilding\u002Finfrastructure-wrappers.md",{"path":80,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fbuilding\u002Foutput-tracking.md",5005,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Freferences\u002Fbuilding\u002Foutput-tracking.md",{"path":84,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fmigration.md",4252,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Freferences\u002Fmigration.md",{"path":88,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Ftest-patterns.md",9542,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fnullables\u002Freferences\u002Ftest-patterns.md",[92,99,106,113,120,127],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"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":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"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":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"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",[],[]]