[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PH8AXSV2FFZ5NSEFE8EWJZ":3,"skill-same:01M6PH8AXSV2FFZ5NSEFE8EWJZ":94},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":14,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6PH8AXSV2FFZ5NSEFE8EWJZ","nemo-rl-session-memory",null,"Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.","headmktlucca-ui\u002Fneuroads-lp","headmktlucca-ui","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F247379838?v=4","01M6PDVAV6M1W96D1SR1PDF8CS","NeuroAds","01M6PDVAZ4P281GNDKD45CYTF5",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fnemo-rl-session-memory\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"nemo rl session memory","memory","NeMo","session memory","session","rl","use","preserve","for","checkpoints","long","do","manage","code review","short","repo","branch","code","tasks","review","2026-11-10 10:12:30",false,"---\nname: nemo-rl-session-memory\nlicense: Apache-2.0\ndescription: \"Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.\"\nwhen_to_use: Preserving or recovering coding-agent context; creating checkpoints for long-running work, handoffs, disconnects, VS Code restarts, branch switches, or nontrivial edits.\n---\n\n# Session Memory\n\nKeep a durable, human-readable record of the current working session so another agent can resume after a disconnect with minimal context loss.\n\n## When To Use\n\nUse this skill when:\n- The user asks to preserve, recover, checkpoint, or manage agent memory.\n- Work is long-running, experimental, or likely to span disconnects.\n- You are about to make nontrivial edits, run long jobs, switch branches, or pause for user input.\n- You resume in a repo that already has `.\u002Fsession\u002F` directories.\n\n## Session Directory\n\nCreate one directory per working session:\n\n```bash\nmkdir -p session\ndate +%Y%m%d_%H%M%S\nmkdir -p session\u002F\u003Csession_date_time>\n```\n\nUse local time from the machine. Reuse the same session directory for all checkpoints in the same conversation unless the user explicitly starts a new session.\n\nExpected files:\n- `session_state.md` - overall goal, current subtask, loaded skills, status, plan, assumptions, blockers, and next actions.\n- `timeline.md` - append-only log of major actions, commands, results, and decisions.\n- `files.md` - files inspected, files changed, and why they matter.\n- `handoff.md` - concise resume instructions for the next agent.\n\nAdd other files only when useful, such as `experiments.tsv`, `review_notes.md`, or copied command logs.\n\n## Start Or Resume\n\nAt the start of a session:\n1. Check for existing session directories:\n\n```bash\nls -dt session\u002F* 2>\u002Fdev\u002Fnull | head\n```\n\n2. If the user is resuming work, read the latest relevant `session_state.md`, `timeline.md`, and `handoff.md`.\n3. If no relevant session exists, create a new timestamped directory.\n4. Write an initial `session_state.md` with the user's overall goal, current subtask, loaded skills, repo path, branch, and known constraints.\n\nDo not treat session notes as the only source of truth. Verify important claims against git state, files, and command output before acting.\n\n## Checkpoint Rhythm\n\nWrite a checkpoint:\n- After gathering enough context to form a plan.\n- Before and after meaningful code edits.\n- Before long-running commands, experiments, branch switches, or anything hard to reconstruct from chat.\n- When the user changes direction.\n- Before final response if the session has meaningful state worth resuming.\n- At least every 30 minutes during active long-running work.\n\nPrefer updating the same files rather than creating many small checkpoint files. Keep the record compact and scannable.\n\n## File Templates\n\n### `session_state.md`\n\n```markdown\n# Session State\n\n- Session: \u003Csession_date_time>\n- Repo: \u003Cabsolute repo path>\n- Branch: \u003Cbranch name>\n- Started: \u003Clocal timestamp>\n- Updated: \u003Clocal timestamp>\n\n## Goal\n\u003CStable overall user goal in one or two sentences. Preserve this across follow-up steering unless the user explicitly changes it.>\n\n## Current Subtask\n\u003CImmediate task or steering request currently being handled.>\n\n## Loaded Skills\n- `\u003Cskill-name>` - \u003Cwhy it was loaded and any important instructions to preserve.>\n\n## Current Status\n\u003CWhat is true now. Include completed work and verification status.>\n\n## Plan\n- [ ] \u003CNext concrete step>\n- [ ] \u003CNext concrete step>\n\n## Assumptions\n- \u003CAssumption and how to verify it if needed.>\n\n## Blockers\n- \u003CBlocker or \"None known\".>\n```\n\n### `timeline.md`\n\n```markdown\n# Timeline\n\n## \u003Clocal timestamp>\n- User asked: \u003Cbrief request>\n- Context gathered: \u003Cfiles\u002Fcommands and key result>\n- Decision: \u003Cimportant choice and rationale>\n- Result: \u003Cedits\u002Ftests\u002Foutcome>\n```\n\n### `files.md`\n\n```markdown\n# Files\n\n## Inspected\n- `\u003Cpath>` - \u003Cwhy it mattered>\n\n## Changed\n- `\u003Cpath>` - \u003Cwhat changed and why>\n\n## Generated\n- `\u003Cpath>` - \u003Cpurpose>\n```\n\n### `handoff.md`\n\n```markdown\n# Handoff\n\n## Resume From Here\n\u003COne paragraph summary of the current state.>\n\n## Next Actions\n- \u003CMost important next action>\n- \u003CVerification or cleanup still needed>\n\n## Watch Outs\n- \u003CRisks, user preferences, or repo constraints the next agent must preserve.>\n```\n\n## Recovery Workflow\n\nWhen resuming after a disconnect:\n1. Find the likely latest session directory.\n2. Read `handoff.md` first, then `session_state.md`, then recent `timeline.md`.\n3. Run lightweight verification such as `git status --short`, `git branch --show-current`, and targeted file reads.\n4. Continue from the latest verified next action.\n5. Append a timeline entry noting the recovery and any mismatches found.\n\n## Quality Rules\n\n- Keep notes factual and terse. Future agents need state, not a transcript.\n- Record command outcomes that matter, especially failed tests or skipped verification.\n- Mention uncommitted changes and whether they were made by the current agent or pre-existing.\n- Do not store secrets, tokens, private credentials, or large logs in session files.\n- If a session file becomes large, summarize old details and keep the latest next actions near the top of `handoff.md`.\n","# Session Memory\n\nKeep a durable, human-readable record of the current working session so another agent can resume after a disconnect with minimal context loss.\n\n## When To Use\n\nUse this skill when:\n- The user asks to preserve, recover, checkpoint, or manage agent memory.\n- Work is long-running, experimental, or likely to span disconnects.\n- You are about to make nontrivial edits, run long jobs, switch branches, or pause for user input.\n- You resume in a repo that already has `.\u002Fsession\u002F` directories.\n\n## Session Directory\n\nCreate one directory per working session:\n\n```bash\nmkdir -p session\ndate +%Y%m%d_%H%M%S\nmkdir -p session\u002F\u003Csession_date_time>\n```\n\nUse local time from the machine. Reuse the same session directory for all checkpoints in the same conversation unless the user explicitly starts a new session.\n\nExpected files:\n- `session_state.md` - overall goal, current subtask, loaded skills, status, plan, assumptions, blockers, and next actions.\n- `timeline.md` - append-only log of major actions, commands, results, and decisions.\n- `files.md` - files inspected, files changed, and why they matter.\n- `handoff.md` - concise resume instructions for the next agent.\n\nAdd other files only when useful, such as `experiments.tsv`, `review_notes.md`, or copied command logs.\n\n## Start Or Resume\n\nAt the start of a session:\n1. Check for existing session directories:\n\n```bash\nls -dt session\u002F* 2>\u002Fdev\u002Fnull | head\n```\n\n2. If the user is resuming work, read the latest relevant `session_state.md`, `timeline.md`, and `handoff.md`.\n3. If no relevant session exists, create a new timestamped directory.\n4. Write an initial `session_state.md` with the user's overall goal, current subtask, loaded skills, repo path, branch, and known constraints.\n\nDo not treat session notes as the only source of truth. Verify important claims against git state, files, and command output before acting.\n\n## Checkpoint Rhythm\n\nWrite a checkpoint:\n- After gathering enough context to form a plan.\n- Before and after meaningful code edits.\n- Before long-running commands, experiments, branch switches, or anything hard to reconstruct from chat.\n- When the user changes direction.\n- Before final response if the session has meaningful state worth resuming.\n- At least every 30 minutes during active long-running work.\n\nPrefer updating the same files rather than creating many small checkpoint files. Keep the record compact and scannable.\n\n## File Templates\n\n### `session_state.md`\n\n```markdown\n# Session State\n\n- Session: \u003Csession_date_time>\n- Repo: \u003Cabsolute repo path>\n- Branch: \u003Cbranch name>\n- Started: \u003Clocal timestamp>\n- Updated: \u003Clocal timestamp>\n\n## Goal\n\u003CStable overall user goal in one or two sentences. Preserve this across follow-up steering unless the user explicitly changes it.>\n\n## Current Subtask\n\u003CImmediate task or steering request currently being handled.>\n\n## Loaded Skills\n- `\u003Cskill-name>` - \u003Cwhy it was loaded and any important instructions to preserve.>\n\n## Current Status\n\u003CWhat is true now. Include completed work and verification status.>\n\n## Plan\n- [ ] \u003CNext concrete step>\n- [ ] \u003CNext concrete step>\n\n## Assumptions\n- \u003CAssumption and how to verify it if needed.>\n\n## Blockers\n- \u003CBlocker or \"None known\".>\n```\n\n### `timeline.md`\n\n```markdown\n# Timeline\n\n## \u003Clocal timestamp>\n- User asked: \u003Cbrief request>\n- Context gathered: \u003Cfiles\u002Fcommands and key result>\n- Decision: \u003Cimportant choice and rationale>\n- Result: \u003Cedits\u002Ftests\u002Foutcome>\n```\n\n### `files.md`\n\n```markdown\n# Files\n\n## Inspected\n- `\u003Cpath>` - \u003Cwhy it mattered>\n\n## Changed\n- `\u003Cpath>` - \u003Cwhat changed and why>\n\n## Generated\n- `\u003Cpath>` - \u003Cpurpose>\n```\n\n### `handoff.md`\n\n```markdown\n# Handoff\n\n## Resume From Here\n\u003COne paragraph summary of the current state.>\n\n## Next Actions\n- \u003CMost important next action>\n- \u003CVerification or cleanup still needed>\n\n## Watch Outs\n- \u003CRisks, user preferences, or repo constraints the next agent must preserve.>\n```\n\n## Recovery Workflow\n\nWhen resuming after a disconnect:\n1. Find the likely latest session directory.\n2. Read `handoff.md` first, then `session_state.md`, then recent `timeline.md`.\n3. Run lightweight verification such as `git status --short`, `git branch --show-current`, and targeted file reads.\n4. Continue from the latest verified next action.\n5. Append a timeline entry noting the recovery and any mismatches found.\n\n## Quality Rules\n\n- Keep notes factual and terse. Future agents need state, not a transcript.\n- Record command outcomes that matter, especially failed tests or skipped verification.\n- Mention uncommitted changes and whether they were made by the current agent or pre-existing.\n- Do not store secrets, tokens, private credentials, or large logs in session files.\n- If a session file becomes large, summarize old details and keep the latest next actions near the top of `handoff.md`.\n",{"name":5,"license":15,"description":7,"when_to_use":52},"Preserving or recovering coding-agent context; creating checkpoints for long-running work, handoffs, disconnects, VS Code restarts, branch switches, or nontrivial edits.","main","7a940b8e5af16c95e5c190a524421d32fc7445a9",".agent\u002Fskills\u002Fnemo-rl-session-memory","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui","https:\u002F\u002Fneuroads.com.br","2026-08-12 00:42:44",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add headmktlucca-ui\u002Fneuroads-lp --skill nemo-rl-session-memory",{"tool":66,"command":67},"bunx","bunx skills add headmktlucca-ui\u002Fneuroads-lp --skill nemo-rl-session-memory",{"tool":69,"command":70},"pnpm","pnpm dlx skills add headmktlucca-ui\u002Fneuroads-lp --skill nemo-rl-session-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fnemo-rl-session-memory\u002FSKILL.md",true,[74,80,84,88],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"BENCHMARK.md","REFERENCE","参考文档",4259,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fnemo-rl-session-memory\u002FBENCHMARK.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"evals\u002Fevals.json",2843,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fnemo-rl-session-memory\u002Fevals\u002Fevals.json",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"skill-card.md",3798,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fnemo-rl-session-memory\u002Fskill-card.md",{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"skill.oms.sig","OTHER","其他",4597,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fnemo-rl-session-memory\u002Fskill.oms.sig",[95,117,141,166,184,217],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":106,"publishedAt":47},"01M6PTDCZTXTGSTX4RFK901YSZ","xunit-skill","Generates xUnit.net tests in C#. Covers Fact\u002FTheory, constructor injection, IClassFixture, and FluentAssertions. Use when user mentions \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal\", \"C# xUnit\". Triggers on: \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal C#\", \"xUnit.net\".","MIT","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxunit-skill\u002FSKILL.md",[102,105],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[107,108,109,110,111,33,112,113,114,115,116],"xunit","xunit skill","testing","injection","user","tests","triggers","unit","unit-testing","C#",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":125,"publishedAt":47},"01M6PTCB59ZTG5FTMWGPYEMMBP","xcuitest-skill","Generates XCUITest UI tests for iOS\u002FiPadOS apps in Swift. Apple's native testing framework for reliable, fast UI automation. Supports local simulators and TestMu AI cloud real devices. Use when user mentions \"XCUITest\", \"XCTest\", \"iOS UI test\", \"Swift test\", \"XCUIApplication\". Triggers on: \"XCUITest\", \"XCTest UI\", \"iOS UI test\", \"Swift UI test\", \"XCUIApplication\", \"TestMu\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxcuitest-skill\u002FSKILL.md",[123,124],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[126,127,109,128,129,130,131,132,33,133,134,135,136,137,112,113,138,139,35,140],"xcuitest","xcuitest skill","automation","test","testing framework","ios","devices","mobile","mobile-testing","ui test","local","apple","apps","native","objective",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":151,"publishedAt":47},"01M6PTATMNTY9NF4J7KSR76YK6","world-builder","Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fworld-builder\u002FSKILL.md",[147,150],{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[152,153,154,155,156,157,158,159,33,160,39,161,162,163,164,35,165],"builder","world","world builder","MCP","create","mcp tools","Tools","game","pokemon","style","via","theme","zone","generative",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":174,"publishedAt":47},"01M6PT9Z92JTSQEHE1QR0NNW5F","webdriverio-skill","Generates WebdriverIO (WDIO) automation tests in JavaScript or TypeScript. Supports local and TestMu AI cloud. Use when user mentions \"WebdriverIO\", \"WDIO\", \"wdio.conf\", \"browser.url\", \"$\", \"$$\". Triggers on: \"WebdriverIO\", \"WDIO\", \"wdio\", \"browser.$\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwebdriverio-skill\u002FSKILL.md",[172,173],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[175,109,176,128,177,178,179,180,111,33,181,136,112,113,182,183],"webdriverio skill","typescript","javascript","browser","cloud","e2e","e2e-testing","URL","conf",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":199,"publishedAt":47},"01M6PT9NVK36ZWCQ69YXK3FR4K","web-design-guidelines","Web platform design and accessibility guidelines. Use when building web interfaces, auditing accessibility, implementing responsive layouts, or reviewing web UI code. Triggers on tasks involving HTML, CSS, web components, WCAG compliance, responsive design, or web performance.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb\u002FSKILL.md",[190,193,194],{"categoryNo":191,"categoryName":192,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":195,"categoryName":196,"taxonomyType":197,"taxonomyTypeDesc":198},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[200,201,202,203,204,205,206,207,208,45,44,209,210,211,212,213,214,215,113,216],"design","web","guidelines","web design guidelines","web design","css","performance","components","web components","web performance","ui","platform design","html","responsive design","responsive","platform","implementing",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":225,"publishedAt":47},"01M6PT9A3JKRE3X34276F2FW5R","watchos-design-guidelines","Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwatchos\u002FSKILL.md",[223,224],{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":195,"categoryName":196,"taxonomyType":197,"taxonomyTypeDesc":198},[200,202,226,45,210,33,227,228,137,215,229,113,138,230,35,231,232],"watchos design guidelines","workout","human","watch","interface","platform-design","features"]