[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CS085HWNFSA3QVF5Q999D4":3,"skill-same:01M7CS085HWNFSA3QVF5Q999D4":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CS085HWNFSA3QVF5Q999D4","bama-improve-loop",null,"Autonomous loop that works through docs\u002FSTORIES.md one story at a time for a macOS app, building, snapshotting, comparing against reference screenshots, fixing, and committing, until a milestone is done. Use when the user says \"keep going\", \"work through the backlog\", \"make it match the reference\", or wants an unattended improvement loop.","newmindsgroup\u002Fvisual-design-kit","newmindsgroup","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F38358889?v=4","01M7CRXVBNJ0WGRTNWHWY2HVQ9","01M7CRXVC9ZXSZBAPZTP3Y39CA",2,"MIT","https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit\u002Fblob\u002Fmain\u002Fextras\u002Fbama-mac-studio\u002Fskills\u002Fbama-improve-loop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bama-improve-loop\ndescription: Autonomous loop that works through docs\u002FSTORIES.md one story at a time for a macOS app, building, snapshotting, comparing against reference screenshots, fixing, and committing, until a milestone is done. Use when the user says \"keep going\", \"work through the backlog\", \"make it match the reference\", or wants an unattended improvement loop.\nargument-hint: \"[milestone, e.g. M1]\"\n---\n\n\u003C!-- Version-Timestamp: 2026-10-27 07:36:32 AST -->\n\n## Adapted execution contract\n\nThis is the pinned, MIT-attributed BAMA capability adapted for the owned design kit. Read `ADAPTATION.md` at the BAMA package root before executing helpers. Project instructions, approved DESIGN.md and canonical tokens take precedence. Use supported Codex or Claude Code tools. Resolve this skill's sibling files relative to its installed SKILL.md; `skill_dir` is a task-local shell variable that you set to that resolved directory before running the examples in either host. Invoke a named `bama-*` skill through the host's supported skill mechanism.\n\nStage local builds by default. Installation, signing identity selection, launch, CLI linking, MCP registration, system setting changes and capture access are separate explicit operations. Existing task authorization applies; ask only for an action not already authorized. Stage or commit only when the current task or repository workflow authorizes it. Stage explicit paths and include required attribution. The helpers do not commit. Preserve the feature, story and testing workflow below using the hardened helpers. Legacy installed-app paths in examples must be replaced by the staged binary returned by `build.sh`.\n\nBefore a new scaffold exists, keep planning evidence under the selected `\u003CAppName>-planning\u002Fdocs\u002F` sibling or an existing approved planning folder. Treat docs paths below as relative to that planning folder until the fresh app is scaffolded, then copy the planning docs explicitly without replacing existing files. For an existing app, keep its current project layout.\n\nThe upstream acceptance statements describe checks to perform, never completed results. Screenshots, runtime behavior, permissions and cross-host acceptance require actual evidence. Use synthetic data and owned temporary test roots. Do not run a hosted session over real app data without project authorization.\n\n\n\n# Improve loop\n\nOne pass through the loop takes one story from `todo` to `done`:\n\n```text\npick story -> plan -> code -> .\u002Fbuild.sh -> snapshot -> compare -> fix -> commit -> update STORIES.md\n```\n\nStop after the milestone the user named, or after the current milestone if\nthey named none. Then report.\n\n## 1. Pick\n\nOpen `docs\u002FSTORIES.md`. Take the first `todo` story in the current\nmilestone whose dependencies are `done`. Set it to `doing`.\n\n## 2. Plan\n\nIf the story adds a screen, an action, or words and has no `UX:` block\nyet, invoke the host-supported skill `bama-ux-design` first.\n\nWrite two to five lines in your head or in the commit body: which files\nchange, which model fields are new, which menu command and shortcut it adds,\nwhich snapshot page shows it. If the story needs a new SwiftData field, give\nit a default value so existing databases keep loading.\n\n## 3. Code\n\nFollow the `bama-swift-swiftui` and `bama-mac-design` skills, the story's `UX:`\nblock, and `design\u002FDESIGN-SYSTEM.md` if the app has one. System hooks follow\n`bama-os-integrations`. Keep each view file under about 300 lines.\nPut new pages in the `SidebarItem` enum so snapshot mode visits them.\n\n## 4. Build and snapshot\n\nFollow the `bama-build-and-verify` skill. If the story has logic, add a test\nor a self-test step (`bama-test-mac-app` skill). Use seed data (`APP_SEED=1`) so pages\nshow real content.\n\n## 5. Compare\n\nOpen your snapshot and the story's reference screenshot side by side with\nthe Read tool. Write down the differences that matter, in this order:\n\n1. Missing or wrong behavior from the acceptance criteria.\n2. Words and flow: names, surface, and states that differ from the `UX:`\n   block or `docs\u002FGLOSSARY.md`.\n3. Layout: wrong column, wrong order, missing element, and every FAIL from\n   the grid checks.\n4. Hierarchy: what is biggest, boldest, first.\n5. Spacing and alignment.\n6. Color and details.\n\nFollow the selected reconstruction contract. For a faithful reconstruction, preserve observed structure, behavior and visual treatment, using semantic native controls styled to match where possible. Replacing the reference with platform defaults is a deliberate adaptation, not an automatic improvement. Record an unavoidable platform difference, its evidence and the accepted target decision. An explicitly adapted native version can use native conventions while retaining the observed task model.\n\nNo reference screenshot (no app was cloned)? Compare against the story's\nacceptance lines and the `bama-mac-design` rules instead.\n\nSnapshot only the pages a story touches (`APP_SNAPSHOT_PAGES`), and the\nfull set at the end of each milestone.\n\nFix, rebuild, and compare again. Three rounds per story at most. If it still\ndoes not match, set the story to `todo` again with a note that says what is\nblocking, and move on.\n\n## 6. Commit and record\n\n```bash\ngit diff --check  # review scoped changes; do not stage automatically\n# Commit only under the project workflow with required attribution.\n```\n\nSet the story to `done` in `docs\u002FSTORIES.md` and commit that with the code.\nOne story per commit, so any story can be reverted on its own. M1 may\nland as one commit when its stories share one skeleton (model, pages,\nlist, persistence); from M2 on, one story per reviewed change.\n\n## 7. Report\n\nAt the end of the loop, report to the user:\n\n- Stories done, with one line each and the snapshot paths that show them.\n- Stories blocked, and why.\n- Anything the user should try by hand (shortcuts, drag and drop).\n- The next story in line.\n\nThen `.\u002Fbuild.sh --open` so the user can try the new build.\n\n## Milestone check-in\n\nWhen the last story of a milestone is `done`, invoke the host-supported skill\n`bama-improve-architecture` before you start the next milestone. Unattended, do\nits top recommendation only if it is `Strong`, and leave the rest in the\nreview file for the user.\n\nWhen a story fixes a bug, add an entry to `docs\u002FFIXLOG.md`: symptom,\ncause, fix, and a last line `Rule: \u003Cwhat to always or never do>`. The fix\nlog outlives squashed history, and the check-in reads it.\n\n## Running it unattended\n\nThe loop works with no one watching, because every step checks itself:\nthe build, the snapshots, the acceptance criteria. To let it run longer,\nstart it with a clear limit (\"finish M2, then stop\"), make sure the tree is\ncommitted before you start, and never let it touch the user's real database.\nEach story is a separate commit, so the user can review the history in the\nmorning and revert anything they do not like.\n\nDone when every story in the milestone is `done` or named in the report as\nblocked with a reason, each done story has its own commit, and the user\nhas the report.\n","\u003C!-- Version-Timestamp: 2026-10-27 07:36:32 AST -->\n\n## Adapted execution contract\n\nThis is the pinned, MIT-attributed BAMA capability adapted for the owned design kit. Read `ADAPTATION.md` at the BAMA package root before executing helpers. Project instructions, approved DESIGN.md and canonical tokens take precedence. Use supported Codex or Claude Code tools. Resolve this skill's sibling files relative to its installed SKILL.md; `skill_dir` is a task-local shell variable that you set to that resolved directory before running the examples in either host. Invoke a named `bama-*` skill through the host's supported skill mechanism.\n\nStage local builds by default. Installation, signing identity selection, launch, CLI linking, MCP registration, system setting changes and capture access are separate explicit operations. Existing task authorization applies; ask only for an action not already authorized. Stage or commit only when the current task or repository workflow authorizes it. Stage explicit paths and include required attribution. The helpers do not commit. Preserve the feature, story and testing workflow below using the hardened helpers. Legacy installed-app paths in examples must be replaced by the staged binary returned by `build.sh`.\n\nBefore a new scaffold exists, keep planning evidence under the selected `\u003CAppName>-planning\u002Fdocs\u002F` sibling or an existing approved planning folder. Treat docs paths below as relative to that planning folder until the fresh app is scaffolded, then copy the planning docs explicitly without replacing existing files. For an existing app, keep its current project layout.\n\nThe upstream acceptance statements describe checks to perform, never completed results. Screenshots, runtime behavior, permissions and cross-host acceptance require actual evidence. Use synthetic data and owned temporary test roots. Do not run a hosted session over real app data without project authorization.\n\n\n\n# Improve loop\n\nOne pass through the loop takes one story from `todo` to `done`:\n\n```text\npick story -> plan -> code -> .\u002Fbuild.sh -> snapshot -> compare -> fix -> commit -> update STORIES.md\n```\n\nStop after the milestone the user named, or after the current milestone if\nthey named none. Then report.\n\n## 1. Pick\n\nOpen `docs\u002FSTORIES.md`. Take the first `todo` story in the current\nmilestone whose dependencies are `done`. Set it to `doing`.\n\n## 2. Plan\n\nIf the story adds a screen, an action, or words and has no `UX:` block\nyet, invoke the host-supported skill `bama-ux-design` first.\n\nWrite two to five lines in your head or in the commit body: which files\nchange, which model fields are new, which menu command and shortcut it adds,\nwhich snapshot page shows it. If the story needs a new SwiftData field, give\nit a default value so existing databases keep loading.\n\n## 3. Code\n\nFollow the `bama-swift-swiftui` and `bama-mac-design` skills, the story's `UX:`\nblock, and `design\u002FDESIGN-SYSTEM.md` if the app has one. System hooks follow\n`bama-os-integrations`. Keep each view file under about 300 lines.\nPut new pages in the `SidebarItem` enum so snapshot mode visits them.\n\n## 4. Build and snapshot\n\nFollow the `bama-build-and-verify` skill. If the story has logic, add a test\nor a self-test step (`bama-test-mac-app` skill). Use seed data (`APP_SEED=1`) so pages\nshow real content.\n\n## 5. Compare\n\nOpen your snapshot and the story's reference screenshot side by side with\nthe Read tool. Write down the differences that matter, in this order:\n\n1. Missing or wrong behavior from the acceptance criteria.\n2. Words and flow: names, surface, and states that differ from the `UX:`\n   block or `docs\u002FGLOSSARY.md`.\n3. Layout: wrong column, wrong order, missing element, and every FAIL from\n   the grid checks.\n4. Hierarchy: what is biggest, boldest, first.\n5. Spacing and alignment.\n6. Color and details.\n\nFollow the selected reconstruction contract. For a faithful reconstruction, preserve observed structure, behavior and visual treatment, using semantic native controls styled to match where possible. Replacing the reference with platform defaults is a deliberate adaptation, not an automatic improvement. Record an unavoidable platform difference, its evidence and the accepted target decision. An explicitly adapted native version can use native conventions while retaining the observed task model.\n\nNo reference screenshot (no app was cloned)? Compare against the story's\nacceptance lines and the `bama-mac-design` rules instead.\n\nSnapshot only the pages a story touches (`APP_SNAPSHOT_PAGES`), and the\nfull set at the end of each milestone.\n\nFix, rebuild, and compare again. Three rounds per story at most. If it still\ndoes not match, set the story to `todo` again with a note that says what is\nblocking, and move on.\n\n## 6. Commit and record\n\n```bash\ngit diff --check  # review scoped changes; do not stage automatically\n# Commit only under the project workflow with required attribution.\n```\n\nSet the story to `done` in `docs\u002FSTORIES.md` and commit that with the code.\nOne story per commit, so any story can be reverted on its own. M1 may\nland as one commit when its stories share one skeleton (model, pages,\nlist, persistence); from M2 on, one story per reviewed change.\n\n## 7. Report\n\nAt the end of the loop, report to the user:\n\n- Stories done, with one line each and the snapshot paths that show them.\n- Stories blocked, and why.\n- Anything the user should try by hand (shortcuts, drag and drop).\n- The next story in line.\n\nThen `.\u002Fbuild.sh --open` so the user can try the new build.\n\n## Milestone check-in\n\nWhen the last story of a milestone is `done`, invoke the host-supported skill\n`bama-improve-architecture` before you start the next milestone. Unattended, do\nits top recommendation only if it is `Strong`, and leave the rest in the\nreview file for the user.\n\nWhen a story fixes a bug, add an entry to `docs\u002FFIXLOG.md`: symptom,\ncause, fix, and a last line `Rule: \u003Cwhat to always or never do>`. The fix\nlog outlives squashed history, and the check-in reads it.\n\n## Running it unattended\n\nThe loop works with no one watching, because every step checks itself:\nthe build, the snapshots, the acceptance criteria. To let it run longer,\nstart it with a clear limit (\"finish M2, then stop\"), make sure the tree is\ncommitted before you start, and never let it touch the user's real database.\nEach story is a separate commit, so the user can review the history in the\nmorning and revert anything they do not like.\n\nDone when every story in the milestone is `done` or named in the report as\nblocked with a reason, each done story has its own commit, and the user\nhas the report.\n",{"name":5,"description":7,"argument-hint":23},"[milestone, e.g. M1]","main","753c596e097d0288f4f74e22d6b8457014eac8b2","extras\u002Fbama-mac-studio\u002Fskills\u002Fbama-improve-loop",0,"https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit","https:\u002F\u002Fgithub.com\u002Fnewmindsgroup","2026-11-10 11:31:50",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add newmindsgroup\u002Fvisual-design-kit --skill bama-improve-loop",{"tool":37,"command":38},"bunx","bunx skills add newmindsgroup\u002Fvisual-design-kit --skill bama-improve-loop",{"tool":40,"command":41},"pnpm","pnpm dlx skills add newmindsgroup\u002Fvisual-design-kit --skill bama-improve-loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit\u002Fblob\u002Fmain\u002Fextras\u002Fbama-mac-studio\u002Fskills\u002Fbama-improve-loop\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",101,"https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit\u002Fblob\u002Fmain\u002Fextras\u002Fbama-mac-studio\u002Fskills\u002Fbama-improve-loop\u002Fagents\u002Fopenai.yaml",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7CSR2BPCD04SARPWN7EJ5R0","web-design","Load before planning, designing, auditing or launching any website, landing page, cinematic hero, microsite or above-the-fold layout, or a prompt for Lovable, Bolt or v0 to build one, including regulated (prescription drug, health, finance), multilingual or market-specific launches. Covers page types (home, product, pricing, about, blog), conversion and ethical persuasion, responsive and fluid layouts, Core Web Vitals, SEO and structured data, localization and language-law requirements, stack and CMS choice (Astro, Next.js, WordPress, Webflow, Framer) and launch QA.","https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fvisual-design-studio\u002Fskills\u002Fweb-design\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7CSQX00CVQAWP2QDHKVXFMS","ux-design","Load before designing or reviewing any flow, form, onboarding, navigation or content for real users, especially low-literacy, older, neurodivergent, child or other specific audiences. Covers research and usability tests, heuristic reviews, personas and jobs to be done, journeys and service blueprints, information architecture, UX laws, SUS, SEQ and HEART metrics, plain language and reading level, and microcopy and error messages.","https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fvisual-design-studio\u002Fskills\u002Fux-design\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7CSQQE0HX6Q8YR2EA1TR6P4","ui-design","Load before designing or specifying any interface screen or component, even a quick one: forms, tables, navigation, dashboards, onboarding, auth and passkeys, pricing, checkout, search and filters, settings, empty, loading and error states, notifications, consent and age-appropriate flows, and AI chat and agent interfaces, all to WCAG 2.2 AA. Also picks React UI libraries (toasts, drawers, command menus). Gives component specs, state matrices, sizes, density and keyboard and accessibility behavior.","https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fvisual-design-studio\u002Fskills\u002Fui-design\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7CSQFM0F9QKZ17S54PYN8M7","typography","Choose, pair, size and set type for brand, web, app, print, slides, signage and motion: modular scales, fluid clamp() type, measure, leading, tracking, OpenType features, font licensing and web font loading, and multiscript setting for CJK, Arabic, Hebrew, Devanagari and Thai. Use when selecting or pairing fonts, building a type scale or type tokens, fixing weak hierarchy or bad line breaks, setting long-form text or numbers, loading web fonts, or localizing type for another market.","https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fvisual-design-studio\u002Fskills\u002Ftypography\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7CSQ95PB7K9JBEFYZVA7226","reference-reconstruction","Reconstructs the observed interface and behavior of a supplied app, site or screenshot set using a screen index, measurements, state and command maps, reusable components and matched-condition comparisons. Use when asked to reverse engineer, clone, reproduce or match a reference product, then adapt it if requested.","https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fvisual-design-studio\u002Fskills\u002Freference-reconstruction\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M7CSQ1XRH2MBXH21MSZ7PXWJ","print-packaging-social","Load before any print, packaging, label, barcode, social, out-of-home, slide-deck or email design question, even a quick one, and before making finished collateral files. Specs: bleed, safe zones, 300ppi, CMYK, PDF\u002FX preflight, dielines, barcodes, social formats with 9:16 safe areas, billboard letter heights, 16:9 decks, bulletproof email. Renders token-driven brand books, sell sheets, cards, carousels and decks to PDF and PNG with a Canva editable twin.","https:\u002F\u002Fgithub.com\u002Fnewmindsgroup\u002Fvisual-design-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fvisual-design-studio\u002Fskills\u002Fprint-packaging-social\u002FSKILL.md",[],[]]