[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71AX03VABGG4AEGTVCXCAT2":3,"skill-same:01M71AX03VABGG4AEGTVCXCAT2":80},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":64,"updatedAt":65,"install":66,"resources":79},"01M71AX03VABGG4AEGTVCXCAT2","diff-walkthrough",null,"Present a changeset for comprehension: reorganize the diff by reviewer value\n(core logic first, wiring condensed, boilerplate summarized), distill dense\nhunks into pseudocode, trace surprising behavior changes on a concrete\ninput, and tag the few genuinely tricky hunks. Use when asked to \"walk me\nthrough the diff\u002FPR\", \"explain what changed\", or to catch someone up on a\nbranch. Not a review: it explains, it does not judge — for findings use\n\u002Freview (or \u002Fbasic-review), for quality use \u002Fclean-code.","ariadoss\u002Fsuperskills","ariadoss","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F414341?v=4","01M71AC7383PT6JCRZSQJ4AVTM","Danilo Stern-Sapad","01M71AC73Y7NTBTJ9KQYNENRRE",12,"MIT","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fdiff-walkthrough\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"diff walkthrough","diff","walkthrough","judge","read","me","catch","review","reviewer","wiring","code","Bash","when","pseudocode","clean","up","canvas","distill","changeset","branch","2026-11-10 10:12:30",false,"---\nname: diff-walkthrough\nversion: 1.0.0\ndescription: |\n  Present a changeset for comprehension: reorganize the diff by reviewer value\n  (core logic first, wiring condensed, boilerplate summarized), distill dense\n  hunks into pseudocode, trace surprising behavior changes on a concrete\n  input, and tag the few genuinely tricky hunks. Use when asked to \"walk me\n  through the diff\u002FPR\", \"explain what changed\", or to catch someone up on a\n  branch. Not a review: it explains, it does not judge — for findings use\n  \u002Freview (or \u002Fbasic-review), for quality use \u002Fclean-code.\ntriggers:\n  - walk me through the diff\n  - walk me through this pr\n  - explain what changed\n  - catch me up on this branch\nallowed-tools:\n  - Bash\n  - Read\n  - Grep\n  - Glob\nmetadata.upstream: https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins (pr-review-canvas\u002Fskills\u002Fpr-review-canvas, MIT)\n---\n\n# \u002Fdiff-walkthrough\n\nPresent a changeset reorganized for reviewer comprehension — not in file-tree\norder, not a raw diff dump. This skill explains what happened; it does not\nreview. Findings belong to `\u002Freview` or `\u002Fbasic-review`.\n\n## Gather the diff\n\nAccept a branch, a range, staged\u002Funcommitted changes, or a PR reference (with\n`gh pr diff` when the remote is reachable). **If the user did not say which\nchangeset they mean, stop and ask.** Never guess from recent history or fall\nback to a silent default — a walkthrough of the wrong diff is worse than no\nwalkthrough.\n\n## Group changes for comprehension\n\nDo **not** present files in alphabetical or tree order. Reorganize into\nsections ordered by reviewer value:\n\n1. **Core logic** — new behavior, algorithm changes, state transitions, API\n   surface changes. Show the real hunks with surrounding context.\n2. **Wiring & integration** — route registration, dependency injection, config\n   plumbing that connects the core logic. Condensed: enough to confirm\n   correctness.\n3. **Boilerplate & mechanical** — renames, import reordering, generated code,\n   formatting, type re-exports. Summarize as a list of files and stats; no\n   inline hunks unless something is genuinely surprising there.\n\nLead with core logic: attention is freshest at the top.\n\n## Distill dense logic into pseudocode\n\nWhen a core hunk is dense — nested conditions, state machines, retry\u002Fbackoff,\nmulti-step transforms — add a few lines of pseudocode next to it that strip\nsyntax and error handling to expose the essential control flow. Only for hunks\nthat are genuinely hard to scan; straightforward changes need no mirror.\n\n## Trace surprising behavior on a concrete example\n\nWhen a hunk changes behavior in a way that is hard to predict from reading it\n— reordered operations, new short-circuits, altered edge cases — pick one\nsmall, realistic input and walk it through the old and new code paths\nside by side, highlighting the step where they diverge and the observable\noutcome. Reserve this for genuinely surprising changes.\n\n## Call attention to tricky things — sparingly\n\nWhen a hunk hides something risky or easy to miss, mark it with a short tag\n(`Subtle`, `Breaking`, `Race condition`, `Perf`) and one sentence. Overuse\ndestroys the signal; a few tags per walkthrough is the ceiling.\n\n## Tone\n\nWrite reviewer-facing commentary, not a changelog: **why** it changed, how\nfiles interact (\"the new validator in core.py is invoked by the route added\nin routes.py\"), anything the diff alone does not make obvious. One or two\nsentences per note. No findings, no verdicts, no \"LGTM\".\n\n---\n\nAdapted from [cursor\u002Fplugins](https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins)\n`pr-review-canvas\u002Fskills\u002Fpr-review-canvas\u002FSKILL.md` (MIT, © Cursor) — the\ncanvas-SDK presentation layer replaced with markdown conventions.\n","# \u002Fdiff-walkthrough\n\nPresent a changeset reorganized for reviewer comprehension — not in file-tree\norder, not a raw diff dump. This skill explains what happened; it does not\nreview. Findings belong to `\u002Freview` or `\u002Fbasic-review`.\n\n## Gather the diff\n\nAccept a branch, a range, staged\u002Funcommitted changes, or a PR reference (with\n`gh pr diff` when the remote is reachable). **If the user did not say which\nchangeset they mean, stop and ask.** Never guess from recent history or fall\nback to a silent default — a walkthrough of the wrong diff is worse than no\nwalkthrough.\n\n## Group changes for comprehension\n\nDo **not** present files in alphabetical or tree order. Reorganize into\nsections ordered by reviewer value:\n\n1. **Core logic** — new behavior, algorithm changes, state transitions, API\n   surface changes. Show the real hunks with surrounding context.\n2. **Wiring & integration** — route registration, dependency injection, config\n   plumbing that connects the core logic. Condensed: enough to confirm\n   correctness.\n3. **Boilerplate & mechanical** — renames, import reordering, generated code,\n   formatting, type re-exports. Summarize as a list of files and stats; no\n   inline hunks unless something is genuinely surprising there.\n\nLead with core logic: attention is freshest at the top.\n\n## Distill dense logic into pseudocode\n\nWhen a core hunk is dense — nested conditions, state machines, retry\u002Fbackoff,\nmulti-step transforms — add a few lines of pseudocode next to it that strip\nsyntax and error handling to expose the essential control flow. Only for hunks\nthat are genuinely hard to scan; straightforward changes need no mirror.\n\n## Trace surprising behavior on a concrete example\n\nWhen a hunk changes behavior in a way that is hard to predict from reading it\n— reordered operations, new short-circuits, altered edge cases — pick one\nsmall, realistic input and walk it through the old and new code paths\nside by side, highlighting the step where they diverge and the observable\noutcome. Reserve this for genuinely surprising changes.\n\n## Call attention to tricky things — sparingly\n\nWhen a hunk hides something risky or easy to miss, mark it with a short tag\n(`Subtle`, `Breaking`, `Race condition`, `Perf`) and one sentence. Overuse\ndestroys the signal; a few tags per walkthrough is the ceiling.\n\n## Tone\n\nWrite reviewer-facing commentary, not a changelog: **why** it changed, how\nfiles interact (\"the new validator in core.py is invoked by the route added\nin routes.py\"), anything the diff alone does not make obvious. One or two\nsentences per note. No findings, no verdicts, no \"LGTM\".\n\n---\n\nAdapted from [cursor\u002Fplugins](https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins)\n`pr-review-canvas\u002Fskills\u002Fpr-review-canvas\u002FSKILL.md` (MIT, © Cursor) — the\ncanvas-SDK presentation layer replaced with markdown conventions.\n",{"name":5,"version":44,"triggers":45,"description":50,"allowed-tools":51,"metadata.upstream":55},"1.0.0",[46,47,48,49],"walk me through the diff","walk me through this pr","explain what changed","catch me up on this branch","Present a changeset for comprehension: reorganize the diff by reviewer value\n(core logic first, wiring condensed, boilerplate summarized), distill dense\nhunks into pseudocode, trace surprising behavior changes on a concrete\ninput, and tag the few genuinely tricky hunks. Use when asked to \"walk me\nthrough the diff\u002FPR\", \"explain what changed\", or to catch someone up on a\nbranch. Not a review: it explains, it does not judge — for findings use\n\u002Freview (or \u002Fbasic-review), for quality use \u002Fclean-code.\n",[30,52,53,54],"Read","Grep","Glob","https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins (pr-review-canvas\u002Fskills\u002Fpr-review-canvas, MIT)","main","c7ec8d78e5dc37484c2cfe90ab04de163d97dd41","skills\u002Fdiff-walkthrough",0,"https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills","https:\u002F\u002Fhyperion360.com\u002Fblog\u002Fparallel-ai-agents-engineering-workflow\u002F","https:\u002F\u002Fgithub.com\u002Fariadoss","https:\u002F\u002Fdanilosapad.com\u002F","CEO & Founder of @Hyperion360","2026-11-01 12:36:50",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add ariadoss\u002Fsuperskills --skill diff-walkthrough",{"tool":72,"command":73},"bunx","bunx skills add ariadoss\u002Fsuperskills --skill diff-walkthrough",{"tool":75,"command":76},"pnpm","pnpm dlx skills add ariadoss\u002Fsuperskills --skill diff-walkthrough","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fdiff-walkthrough\u002FSKILL.md",true,[],[81,107,130,149,178,194],{"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":92,"publishedAt":39},"01M71AZE3MPF891RM354EMRYA1","youtube","Download YouTube video transcripts when user provides a YouTube URL or asks to download\u002Fget\u002Ffetch a transcript from YouTube. Also use when user wants to transcribe or get captions\u002Fsubtitles from a YouTube video.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[83,93,94,95,96,97,98,30,99,31,100,101,102,103,23,104,105,106],"user","download","transcribe","write","transcript","video transcripts","URL","Captions","get","fetch","Video","use","subtitles","transcripts",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":39},"01M71AZAYR85PW6BJGSQXS4BN2","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code. Produces an engineering plan complete with TDD tasks, DRY\u002FSOLID\u002FYAGNI principles, a required Test Plan & Verification section, and a coverage target — then auto-runs \u002Fplan-eng-review as an independent double-check before execution.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[114,115,96,116,117,26,118,29,119,31,120,121,122,123,124,125,126,127,128,129],"write plan","plan","dry","verification","tasks","you","auto","eng","coverage","complete","section","for","test plan","target","as","yagni",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":39},"01M71AZ8NDDP5ZMGEE6FSC4FKR","worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fworktrees\u002FSKILL.md",[],[132,137,138,139,104,140,141,142,143,144,145,117,146,31,147,148],"implementation","workspace","with","plans","feature","isolation","git","directory","work","git worktrees","selection","Safety",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":158,"publishedAt":39},"01M71AZ4ZQHTNWFRZVYHKQFP08","web-perf","Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-perf\u002FSKILL.md",[155],{"categoryNo":156,"categoryName":157,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000023","Skill与智能体开发",[159,160,161,162,163,164,165,166,167,31,168,169,170,171,172,173,174,175,176,177],"web","perf","web perf","resources","MCP","layout","optimize","documentation","caching","qa","knowledge","devtools","issues","render","re","performance","chrome devtools","vitals","never",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":39},"01M71AZ2KZNWYEGKKRMJH8PYG2","verify","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[180,123,185,186,145,117,187,188,31,189,104,190,191,192,193],"commands","about","claims","output","assertions","claim","prs","evidence","running",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":200,"publishedAt":39},"01M71AZ0ACCK7N1QMWQK1FV2HJ","validate-idea","Validate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate-idea\u002FSKILL.md",[],[201,202,203,204,205,206,207,31,208,104,209],"validate","idea","validate idea","framework","it","minimalist","test","business","before building"]