[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77TQWYAM7H4NB14FA9841TY":3,"skill-same:01M77TQWYAM7H4NB14FA9841TY":52},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M77TQWYAM7H4NB14FA9841TY","momentic-spec",null,"Improve code correctness using Momentic specs in the feature development process","Reihantt6\u002Fsns-myagent","Reihantt6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219822095?v=4","01M77KK94PV8B7C2D9XWXNS8DJ","Mohamad Reihan tegar prasetya","01M77KK958QFMTHYXGXFV7KZ79",2,"MIT","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fmomentic-spec\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Improve code correctness using Momentic specs in the feature development process\"\n---\n# Momentic spec-driven development\n\nWrite the expected product behavior as Momentic tests before implementing it.\nThe tests define the contract; do not make the tests fit the implementation.\n\n## Non-negotiable sequence\n\n1. Read repository guidance, `momentic.config.yaml`, and nearby tests and\n   modules.\n2. Identify and report the exact Momentic tests expected to be affected.\n3. Create or modify those tests before changing product code.\n4. Review the test diff as a product specification.\n5. Only then implement the product change.\n6. Use fast code-level checks while implementing; do not run Momentic after\n   every edit or commit.\n7. At a durable end-to-end checkpoint, prepare the required test state, enable\n   the affected tests that should now pass, and ask whether to run the smallest\n   affected set.\n\nDo not begin product implementation until the intended test specifications are\non disk. If the user changes the requirement, update the spec first again.\n\n## Choose the affected tests\n\n- If the user names specific existing tests, start with those tests and keep the\n  work focused on them. Expand the set only when repository evidence shows\n  another test or shared module is directly affected.\n- For new user-visible functionality, create the smallest new test or tests that\n  describe the new user journey.\n- For changed functionality, update the existing tests that describe the old\n  behavior instead of adding duplicate coverage.\n- Trace shared components and modules far enough to find real behavioral impact.\n  Do not infer the affected set from filenames alone.\n- If no Momentic test is affected, state why before making product changes. Do\n  not make cosmetic test edits merely to produce a test diff.\n\nBefore editing product code, report each affected test path and whether it will\nbe added, changed, or left unchanged.\n\n## Write the product specification first\n\nThe pre-implementation test should describe the requested outcome, even when the\ncurrent product cannot satisfy it yet.\n\n- Preserve unrelated setup, teardown, data, assertions, and test intent.\n- Do not weaken an assertion or preserve old behavior just because that matches\n  the current implementation.\n- Mark a test `disabled: true` when the implementation or a required dependency\n  is not ready and the test is not expected to pass yet. Record why it is\n  disabled and what must become true before enabling it.\n- Do not use `disabled: true` merely because local credentials or a runnable\n  environment are unavailable. That is a validation limitation, not necessarily\n  an expected product failure.\n- Keep the delta narrow. One changed product contract should normally have one\n  focused test delta.\n\nAfter writing the tests, summarize the expected failing or disabled behavior and\nconfirm the tests express the user's request before implementing it.\n\n## Follow the codebase's testing language\n\nRead nearby tests and follow their established conventions, including folder\nplacement, naming, modules, setup, data, and preference for AI checks, page\nchecks, or element checks. Apply baseline Momentic practices where the codebase\ndoes not express a preference:\n\n- Prefer native Momentic steps and natural-language targets over JavaScript or\n  selectors.\n- Keep assertions minimal and user-driven, with an explicit outcome check after\n  a flexible action.\n- Reuse existing modules for established flows such as authentication, setup,\n  and navigation instead of recreating those flows inline.\n- Do not reorganize or modify a shared module unless the requested product\n  contract requires it. Account for every test that consumes a changed module.\n- Never work around a real product failure by changing the test.\n\n## Prefer AI action V3 for new specifications\n\nFor a new test, prefer an AI action V3 `act:` step when a high-level goal reads\nmore clearly as a product specification, especially for a long flow. Reuse\nexisting modules for known subflows and use `act:` for the new behavior rather\nthan hiding reusable setup inside one large goal.\n\nKeep goals short, specific, and outcome-oriented. Pair an `act:` step with the\nsame assertion style used by nearby tests so the test verifies the result, not\nonly that the agent stopped.\n\nAI action V3 caches generated steps after a successful run and self-heals when a\ncached step misses:\n\n- Keep caching enabled for stable product flows. Cached reruns are faster and\n  more deterministic.\n- Set `cache: false` only when the goal is inherently dynamic and should be\n  re-derived every run, such as opening the most recent record or responding to\n  frequently changing content.\n- Do not disable cache to hide a stale or incorrect specification. When the\n  intended behavior changes, update the goal or step description so its cache\n  identity changes.\n- When MCP preview returns a `CacheId` for a step that will be persisted, carry\n  that cache ID into the saved step as required by the `momentic-test` skill.\n\n## Run at durable end-to-end checkpoints\n\nMomentic is true end-to-end validation, not the coding agent's inner feedback\nloop. Do not run affected Momentic tests after every file edit, implementation\nstep, commit, or small refactor.\n\nDo not execute Momentic tests by default. Editing and linting Momentic tests is\nallowed without confirmation, but test execution can take time and consume\ncredits. At a durable checkpoint:\n\n1. Stop before running Momentic.\n2. Tell the user exactly which tests or command you propose to run and, when\n   known, the expected duration or credit impact.\n3. Ask the user to confirm whether to run them.\n4. Run only after explicit confirmation. A direct request to run the specified\n   tests counts as confirmation.\n\nConfirmation covers only the proposed run. Ask again before another Momentic\nexecution unless the user explicitly authorized iterative reruns. If the user\ndeclines or does not confirm, continue with non-Momentic checks and report the\ntests as not run.\n\nUse faster repository checks such as unit tests, typechecking, and linting while\nbuilding. Run Momentic when the app has reached a logical checkpoint that is\ndurable and usable through the real UI:\n\n- For a small change, the checkpoint is usually the fully implemented change.\n- For a multi-stage or extra-large feature, a checkpoint can be a completed,\n  independently usable UI slice with all prerequisites needed for its affected\n  test. Do not wait for the entire feature when a meaningful component is\n  already testable end to end.\n- Do not treat an arbitrary commit boundary as a checkpoint. The deciding\n  question is whether a user can exercise the intended behavior through the\n  product and observe the specified outcome.\n\nAt each checkpoint, propose the smallest affected test set. After confirmation,\nrun it once, diagnose failures, and make a coherent fix. Request confirmation\nagain before rerunning unless iterative reruns were already authorized, and\nrerun only when there is a reasonable expectation that the end-to-end outcome\nchanged. Keep future specifications disabled until their checkpoint exists.\n\n## Own the test data and application state\n\nThe coding agent implementing the product change is responsible for making the\ncheckpoint cleanly runnable. Before invoking Momentic, identify and establish\nthe required data, account state, feature flags, permissions, integrations, and\nservice state. Do not leave prerequisite creation for the browser agent to\nimprovise through unrelated UI flows.\n\nPrefer existing test setup facilities. When the application lacks a reliable\nway to create prerequisites, the coding agent is encouraged to build safe,\ntest-environment-only capabilities such as:\n\n- idempotent endpoints or scripts that seed deterministic records and state\n- fixtures and factories for realistic test data\n- dedicated test accounts, roles, and authentication state\n- test-only controls for feature flags or external-service substitutes\n- scoped cleanup or unique-data mechanisms that prevent cross-run pollution\n\nAny new test capability must be inaccessible in production, explicitly gated to\napproved test environments, authenticated where appropriate, narrowly scoped,\nand safe to call repeatedly. Never add a production backdoor, weaken production\nauthorization, or encode the behavior under test inside the seed mechanism.\n\nDocument the setup contract and either execute it before the Momentic run or\ninvoke it from the test's established setup section. The resulting test should\nbe repeatable from a clean environment without relying on accidental state from\na previous run.\n\n## Edit and validate safely\n\nUse the installed `momentic-test` skill for detailed authoring, format, and MCP\nguidance.\n\n- Edit v2 tests (`fileType: momentic\u002Ftest\u002Fv2`) directly when the change is small\n  and the intended steps are clear.\n- Do not edit v1 test YAML directly. Use Momentic MCP tools to persist v1\n  changes.\n- Use MCP browser validation when UI discovery, live state, or locator behavior\n  is uncertain.\n- Lint the test specifications before product implementation when possible.\n- At a durable end-to-end checkpoint, remove `disabled: true` from tests that\n  are now expected to pass, establish their required state, and ask whether to\n  run the smallest affected set.\n- Leave a test disabled only when it is still intentionally not expected to\n  pass, and include the reason and enablement condition in the handoff.\n\nRun the repository's required product-code checks after implementation. In the\nhandoff, list the affected tests, their enabled or disabled state, the product\nbehavior implemented, and every validation that was or was not run.\n","# Momentic spec-driven development\n\nWrite the expected product behavior as Momentic tests before implementing it.\nThe tests define the contract; do not make the tests fit the implementation.\n\n## Non-negotiable sequence\n\n1. Read repository guidance, `momentic.config.yaml`, and nearby tests and\n   modules.\n2. Identify and report the exact Momentic tests expected to be affected.\n3. Create or modify those tests before changing product code.\n4. Review the test diff as a product specification.\n5. Only then implement the product change.\n6. Use fast code-level checks while implementing; do not run Momentic after\n   every edit or commit.\n7. At a durable end-to-end checkpoint, prepare the required test state, enable\n   the affected tests that should now pass, and ask whether to run the smallest\n   affected set.\n\nDo not begin product implementation until the intended test specifications are\non disk. If the user changes the requirement, update the spec first again.\n\n## Choose the affected tests\n\n- If the user names specific existing tests, start with those tests and keep the\n  work focused on them. Expand the set only when repository evidence shows\n  another test or shared module is directly affected.\n- For new user-visible functionality, create the smallest new test or tests that\n  describe the new user journey.\n- For changed functionality, update the existing tests that describe the old\n  behavior instead of adding duplicate coverage.\n- Trace shared components and modules far enough to find real behavioral impact.\n  Do not infer the affected set from filenames alone.\n- If no Momentic test is affected, state why before making product changes. Do\n  not make cosmetic test edits merely to produce a test diff.\n\nBefore editing product code, report each affected test path and whether it will\nbe added, changed, or left unchanged.\n\n## Write the product specification first\n\nThe pre-implementation test should describe the requested outcome, even when the\ncurrent product cannot satisfy it yet.\n\n- Preserve unrelated setup, teardown, data, assertions, and test intent.\n- Do not weaken an assertion or preserve old behavior just because that matches\n  the current implementation.\n- Mark a test `disabled: true` when the implementation or a required dependency\n  is not ready and the test is not expected to pass yet. Record why it is\n  disabled and what must become true before enabling it.\n- Do not use `disabled: true` merely because local credentials or a runnable\n  environment are unavailable. That is a validation limitation, not necessarily\n  an expected product failure.\n- Keep the delta narrow. One changed product contract should normally have one\n  focused test delta.\n\nAfter writing the tests, summarize the expected failing or disabled behavior and\nconfirm the tests express the user's request before implementing it.\n\n## Follow the codebase's testing language\n\nRead nearby tests and follow their established conventions, including folder\nplacement, naming, modules, setup, data, and preference for AI checks, page\nchecks, or element checks. Apply baseline Momentic practices where the codebase\ndoes not express a preference:\n\n- Prefer native Momentic steps and natural-language targets over JavaScript or\n  selectors.\n- Keep assertions minimal and user-driven, with an explicit outcome check after\n  a flexible action.\n- Reuse existing modules for established flows such as authentication, setup,\n  and navigation instead of recreating those flows inline.\n- Do not reorganize or modify a shared module unless the requested product\n  contract requires it. Account for every test that consumes a changed module.\n- Never work around a real product failure by changing the test.\n\n## Prefer AI action V3 for new specifications\n\nFor a new test, prefer an AI action V3 `act:` step when a high-level goal reads\nmore clearly as a product specification, especially for a long flow. Reuse\nexisting modules for known subflows and use `act:` for the new behavior rather\nthan hiding reusable setup inside one large goal.\n\nKeep goals short, specific, and outcome-oriented. Pair an `act:` step with the\nsame assertion style used by nearby tests so the test verifies the result, not\nonly that the agent stopped.\n\nAI action V3 caches generated steps after a successful run and self-heals when a\ncached step misses:\n\n- Keep caching enabled for stable product flows. Cached reruns are faster and\n  more deterministic.\n- Set `cache: false` only when the goal is inherently dynamic and should be\n  re-derived every run, such as opening the most recent record or responding to\n  frequently changing content.\n- Do not disable cache to hide a stale or incorrect specification. When the\n  intended behavior changes, update the goal or step description so its cache\n  identity changes.\n- When MCP preview returns a `CacheId` for a step that will be persisted, carry\n  that cache ID into the saved step as required by the `momentic-test` skill.\n\n## Run at durable end-to-end checkpoints\n\nMomentic is true end-to-end validation, not the coding agent's inner feedback\nloop. Do not run affected Momentic tests after every file edit, implementation\nstep, commit, or small refactor.\n\nDo not execute Momentic tests by default. Editing and linting Momentic tests is\nallowed without confirmation, but test execution can take time and consume\ncredits. At a durable checkpoint:\n\n1. Stop before running Momentic.\n2. Tell the user exactly which tests or command you propose to run and, when\n   known, the expected duration or credit impact.\n3. Ask the user to confirm whether to run them.\n4. Run only after explicit confirmation. A direct request to run the specified\n   tests counts as confirmation.\n\nConfirmation covers only the proposed run. Ask again before another Momentic\nexecution unless the user explicitly authorized iterative reruns. If the user\ndeclines or does not confirm, continue with non-Momentic checks and report the\ntests as not run.\n\nUse faster repository checks such as unit tests, typechecking, and linting while\nbuilding. Run Momentic when the app has reached a logical checkpoint that is\ndurable and usable through the real UI:\n\n- For a small change, the checkpoint is usually the fully implemented change.\n- For a multi-stage or extra-large feature, a checkpoint can be a completed,\n  independently usable UI slice with all prerequisites needed for its affected\n  test. Do not wait for the entire feature when a meaningful component is\n  already testable end to end.\n- Do not treat an arbitrary commit boundary as a checkpoint. The deciding\n  question is whether a user can exercise the intended behavior through the\n  product and observe the specified outcome.\n\nAt each checkpoint, propose the smallest affected test set. After confirmation,\nrun it once, diagnose failures, and make a coherent fix. Request confirmation\nagain before rerunning unless iterative reruns were already authorized, and\nrerun only when there is a reasonable expectation that the end-to-end outcome\nchanged. Keep future specifications disabled until their checkpoint exists.\n\n## Own the test data and application state\n\nThe coding agent implementing the product change is responsible for making the\ncheckpoint cleanly runnable. Before invoking Momentic, identify and establish\nthe required data, account state, feature flags, permissions, integrations, and\nservice state. Do not leave prerequisite creation for the browser agent to\nimprovise through unrelated UI flows.\n\nPrefer existing test setup facilities. When the application lacks a reliable\nway to create prerequisites, the coding agent is encouraged to build safe,\ntest-environment-only capabilities such as:\n\n- idempotent endpoints or scripts that seed deterministic records and state\n- fixtures and factories for realistic test data\n- dedicated test accounts, roles, and authentication state\n- test-only controls for feature flags or external-service substitutes\n- scoped cleanup or unique-data mechanisms that prevent cross-run pollution\n\nAny new test capability must be inaccessible in production, explicitly gated to\napproved test environments, authenticated where appropriate, narrowly scoped,\nand safe to call repeatedly. Never add a production backdoor, weaken production\nauthorization, or encode the behavior under test inside the seed mechanism.\n\nDocument the setup contract and either execute it before the Momentic run or\ninvoke it from the test's established setup section. The resulting test should\nbe repeatable from a clean environment without relying on accidental state from\na previous run.\n\n## Edit and validate safely\n\nUse the installed `momentic-test` skill for detailed authoring, format, and MCP\nguidance.\n\n- Edit v2 tests (`fileType: momentic\u002Ftest\u002Fv2`) directly when the change is small\n  and the intended steps are clear.\n- Do not edit v1 test YAML directly. Use Momentic MCP tools to persist v1\n  changes.\n- Use MCP browser validation when UI discovery, live state, or locator behavior\n  is uncertain.\n- Lint the test specifications before product implementation when possible.\n- At a durable end-to-end checkpoint, remove `disabled: true` from tests that\n  are now expected to pass, establish their required state, and ask whether to\n  run the smallest affected set.\n- Leave a test disabled only when it is still intentionally not expected to\n  pass, and include the reason and enablement condition in the handoff.\n\nRun the repository's required product-code checks after implementation. In the\nhandoff, list the affected tests, their enabled or disabled state, the product\nbehavior implemented, and every validation that was or was not run.\n",{"description":7},"main","58843b159d7a4050d6b785a98b908cce505c0b92","agent\u002Fskills\u002Fmomentic-spec",0,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent","https:\u002F\u002Fgithub.com\u002FReihantt6","reihsns.web.id","2026-08-19 20:08:18",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Reihantt6\u002Fsns-myagent --skill momentic-spec",{"tool":38,"command":39},"bunx","bunx skills add Reihantt6\u002Fsns-myagent --skill momentic-spec",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Reihantt6\u002Fsns-myagent --skill momentic-spec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fmomentic-spec\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",235,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fmomentic-spec\u002Fagents\u002Fopenai.yaml",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M77XDCYZ407XYMF2T4P6F7VT","youtube-transcript","Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com\u002Fwatch?v=, youtu.be\u002F, or similar). Supports output with or without timestamps.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-transcript\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M77XD7PBC98J6MXGJJ2TJ8DX","youtube-thumbnail-design","YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A\u002FB testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-thumbnail-design\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M77XD2541C8HXJ6RHYZP4NGJ","youtube-short-maker","Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: \"youtube short\", \"make a youtube short\", \"shorts video\", \"short-form video\". NOT for long-form or landscape video.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-short-maker\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M77XCXKVSYK7KTZ3PQBVVGFD","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fxcode-project-setup\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M77XCR1DV8ZQK2NHWKVY4EWX","x402","Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — \"just use it\" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or \"build it in\" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx402\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M77XCMD3R3ZBZQQSW6E0793B","x-twitter-scraper","Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx-twitter-scraper\u002FSKILL.md",[],[]]