[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXQAGEJBHM7ZG0SP9GCZQR":3,"skill-same:01M6BXQAGEJBHM7ZG0SP9GCZQR":63},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":12,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M6BXQAGEJBHM7ZG0SP9GCZQR","diagnosing-bugs",null,"Diagnose code failures, intermittent bugs, and performance regressions. For NodeTool workflow-run failures, use nodetool-troubleshooter.","nodetool-ai\u002Fnodetool","nodetool-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F164873569?v=4","01M6BXPFDW36K9K1MR8ZH63HG2","nodetool.ai","01M6BXPFJ893XM219GQN60B0WK",633,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdiagnosing-bugs\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"diagnosing bugs","bugs","performance","workflow","diagnose","run","code","nodetool","use","for","2026-11-10 10:12:30",false,"---\nname: diagnosing-bugs\ndescription: \"Diagnose code failures, intermittent bugs, and performance regressions. For NodeTool workflow-run failures, use nodetool-troubleshooter.\"\n---\n\n# Diagnosing Bugs\n\nFind the cause of the reported symptom, fix it within the requested scope, and\nretain evidence that the fix works. Read relevant code and logs to construct a\nreproduction. Existing domain terms and ADRs constrain the diagnosis.\n\n## Establish the failure\n\nPrefer an existing harness or test that reaches the affected behavior. Otherwise\nbuild the smallest practical test, CLI invocation, HTTP request, or browser\nscenario. Read the applicable entry in the\n[harness reference](..\u002F..\u002F..\u002Fdocs\u002Fharnesses.md) before using a harness.\n\nRun the reproduction before changing behavior. Capture the command, exit status,\ninput, and observed symptom. An unrelated setup failure does not reproduce the\nbug. Reduce inputs when useful, retaining the original case.\n\nFor intermittent failures, record the observed rate and conditions. Use seeded\ninputs, bounded repetition, or targeted stress to improve the signal. For\nperformance regressions, capture a comparable timing or profiler baseline before\nthe fix. Avoid arbitrary repetition targets or latency requirements for the harness.\n\nIf the environment cannot reproduce the failure, continue useful code and log\ninspection and label hypotheses as unverified. Request only the missing artifact\nor access needed to establish the failure. Do not claim a reproduced or fixed bug\nwithout evidence, or add production instrumentation without authorization.\n\n## Test the cause\n\nState a falsifiable hypothesis and the observation that would distinguish it\nfrom plausible alternatives. Use a debugger, targeted instrumentation, or\nbisection as appropriate. Change one relevant variable at a time and update the\nhypothesis from the result. Do not invent extra hypotheses to meet a quota.\n\nTag temporary instrumentation so it can be removed. Preserve unrelated edits\nwhen reverting an experiment.\n\n## Fix and verify\n\nRetain the reproduction as a regression test or runnable fixture at a boundary\nthat exercises the real failure. Observe it fail before the fix and pass after.\nRecheck the original scenario if the retained case was reduced.\n\nIf no suitable test boundary exists, explain the limitation and retain the best\navailable reproduction. Do not substitute a test that cannot detect the symptom.\nReport necessary architectural follow-up without starting an unrelated refactor.\n\nRemove temporary instrumentation and files created only for the experiment.\nComplete the [mandatory post-change verification](..\u002F..\u002F..\u002FAGENTS.md#mandatory-post-change-verification).\nReport the cause, changed behavior, and actual verification results. Stop when\nthe requested fix and required checks are complete.\n","# Diagnosing Bugs\n\nFind the cause of the reported symptom, fix it within the requested scope, and\nretain evidence that the fix works. Read relevant code and logs to construct a\nreproduction. Existing domain terms and ADRs constrain the diagnosis.\n\n## Establish the failure\n\nPrefer an existing harness or test that reaches the affected behavior. Otherwise\nbuild the smallest practical test, CLI invocation, HTTP request, or browser\nscenario. Read the applicable entry in the\n[harness reference](..\u002F..\u002F..\u002Fdocs\u002Fharnesses.md) before using a harness.\n\nRun the reproduction before changing behavior. Capture the command, exit status,\ninput, and observed symptom. An unrelated setup failure does not reproduce the\nbug. Reduce inputs when useful, retaining the original case.\n\nFor intermittent failures, record the observed rate and conditions. Use seeded\ninputs, bounded repetition, or targeted stress to improve the signal. For\nperformance regressions, capture a comparable timing or profiler baseline before\nthe fix. Avoid arbitrary repetition targets or latency requirements for the harness.\n\nIf the environment cannot reproduce the failure, continue useful code and log\ninspection and label hypotheses as unverified. Request only the missing artifact\nor access needed to establish the failure. Do not claim a reproduced or fixed bug\nwithout evidence, or add production instrumentation without authorization.\n\n## Test the cause\n\nState a falsifiable hypothesis and the observation that would distinguish it\nfrom plausible alternatives. Use a debugger, targeted instrumentation, or\nbisection as appropriate. Change one relevant variable at a time and update the\nhypothesis from the result. Do not invent extra hypotheses to meet a quota.\n\nTag temporary instrumentation so it can be removed. Preserve unrelated edits\nwhen reverting an experiment.\n\n## Fix and verify\n\nRetain the reproduction as a regression test or runnable fixture at a boundary\nthat exercises the real failure. Observe it fail before the fix and pass after.\nRecheck the original scenario if the retained case was reduced.\n\nIf no suitable test boundary exists, explain the limitation and retain the best\navailable reproduction. Do not substitute a test that cannot detect the symptom.\nReport necessary architectural follow-up without starting an unrelated refactor.\n\nRemove temporary instrumentation and files created only for the experiment.\nComplete the [mandatory post-change verification](..\u002F..\u002F..\u002FAGENTS.md#mandatory-post-change-verification).\nReport the cause, changed behavior, and actual verification results. Stop when\nthe requested fix and required checks are complete.\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac",".agents\u002Fskills\u002Fdiagnosing-bugs",90,"https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool","https:\u002F\u002Fnodetool.ai\u002F","https:\u002F\u002Fgithub.com\u002Fnodetool-ai","No-code AI development","2026-11-14 03:12:08",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add nodetool-ai\u002Fnodetool --skill diagnosing-bugs",{"tool":49,"command":50},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill diagnosing-bugs",{"tool":52,"command":53},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill diagnosing-bugs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdiagnosing-bugs\u002FSKILL.md",true,[57],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fhitl-loop.template.sh","SCRIPT","脚本",1164,"https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdiagnosing-bugs\u002Fscripts\u002Fhitl-loop.template.sh",[64,97,127,142,158,183],{"skillNo":65,"name":26,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":79,"publishedAt":29},"01M6BY4D93R0Q9400ZHJ04DXP1","Use the NodeTool MCP server to build, validate, run, and debug visual AI workflows, and to work with assets, collections, and jobs. Use when the user mentions NodeTool or asks for a workflow graph, a node, or a media generation run on their NodeTool server.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fplugins\u002Fchatgpt\u002Fnodetool\u002Fskills\u002Fnodetool\u002FSKILL.md",[69,74],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[26,80,81,22,82,83,84,24,85,86,87,88,89,90,27,91,92,93,94,95,28,96],"MCP","mcp server","workflows","validate","debug","graph","server","Media","assets","work","node","visual","generation","collections","media generation","with","when",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":106,"publishedAt":29},"01M6BY4AEB05ZPBRVD078ATR2H","wan-2-6-prompting","Prompt Alibaba's Wan 2.6 video — text-to-video with a global style line plus timing-bracketed shots, and image-to-video that describes only what changes over time. Covers the shot-mode switch per provider, the prompt budget, negative prompts, motion intensity wording, audio input and prompt expansion. Use whenever the model id names a Wan 2.6 video route (alibaba\u002Fwan-2.6\u002Ftext-to-video, alibaba\u002Fwan-2.6\u002Fimage-to-video, wan-video\u002Fwan-2.6-t2v, wan-video\u002Fwan-2.6-i2v, wan-video\u002Fwan2.6-i2v-flash) on generate_video, animate_image or a TextToVideo node. Not for Wan 2.5 or 2.7, or the Wan 2.6 image routes.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fwan-2-6-prompting\u002FSKILL.md",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000016","图像与多媒体",[107,108,109,110,111,112,113,114,115,116,117,90,118,119,120,121,122,123,124,125,126],"wan 2 6 prompting","prompting","image","generate","Budget","Video","Audio","text","animate","model","flash","only","route","time","line","input","text-to-video","image-to-video","mode","expansion",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":135,"publishedAt":29},"01M6BY47T4748ZG5ZMTAR97ZWZ","video-workflow","Build a reusable NodeTool video workflow for batches or repeated inputs. For a single finished piece, use a storyboard skill.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-workflow\u002FSKILL.md",[133,134],{"categoryNo":104,"categoryName":105,"taxonomyType":72,"taxonomyTypeDesc":73},{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},[22,112,136,26,27,137,138,139,140,28,141],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":149,"publishedAt":29},"01M6BY4587N2SYN315SXGEMZC3","video-clone","Analyze a reference video and recreate its shot structure with a new product or cast in NodeTool.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-clone\u002FSKILL.md",[148],{"categoryNo":104,"categoryName":105,"taxonomyType":72,"taxonomyTypeDesc":73},[112,150,151,152,153,26,154,155,156,95,157],"video clone","clone","product","analyze","reference","cast","structure","new",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":165,"publishedAt":29},"01M6BY4257C2KQYYMD9EK6DK8E","video-audio-continuity","Keep sound continuous across a multi-scene piece cut from generated video — why one clip per scene hard-cuts the audio at every boundary, when to write all the scenes into a single generation instead, the sound-design vocabulary that survives a provider's copyright filter, and how to check the length, the aspect ratio and the mix of what came back. Use when a piece has more than one scene and the video model writes its own audio (Seedance 2, Veo 3, MiniMax H3, Kling 2.6 and later), or when a cut's sound drops out at the shot changes.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-audio-continuity\u002FSKILL.md",[164],{"categoryNo":104,"categoryName":105,"taxonomyType":72,"taxonomyTypeDesc":73},[112,113,166,167,168,169,170,171,116,172,173,174,175,176,177,178,179,180,181,182,96],"video audio continuity","continuity","design","boundary","how","why","write","generated","later","back","across","cut","how to","filter","mix","at","veo 3",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":190,"publishedAt":29},"01M6BY3ZANBSQMZRH4MG55R8Z7","veo-3-prompting","Prompt Google's Veo 3 video line — the five-element shot\u002Fsetting\u002Fsubject\u002Faction\u002Fdialogue structure, the cinematography vocabulary it reads directly, duration and aspect-ratio tradeoffs, the audio and auto-fix switches per provider, and the fixes for visual drift, temporal inconsistency and audio mismatch. Use whenever the model id contains veo3 or veo-3 (fal-ai\u002Fveo3.1 and its fast, lite, image-to-video, first-last-frame and reference-to-video routes, fal-ai\u002Fveo3\u002Fimage-to-video, google\u002Fveo3.1 on atlascloud, google\u002Fveo-3 and google\u002Fveo-3.1 on replicate, kie's veo-3-1, and Gemini's own veo-3.1-generate-preview) on generate_video, animate_image, generate_video_from_references or a TextToVideo node.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fveo-3-prompting\u002FSKILL.md",[189],{"categoryNo":104,"categoryName":105,"taxonomyType":72,"taxonomyTypeDesc":73},[191,192,108,182,109,193,194,110,195,196,112,113,115,116,197,198,199,200,201,202,203,156,204,205,206],"veo 3 prompting","veo","google","gemini","fast","first","fal","kie","replicate","fix","auto","references","drift","preview","element","auto-fix"]