[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JTEWM0JFX78FB3HW8F8EZ2":3,"skill-same:01M6JTEWM0JFX78FB3HW8F8EZ2":68},{"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":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6JTEWM0JFX78FB3HW8F8EZ2","diagnosing-bgs-problems",null,"Use when a BGS modded game has CTD, crash log, FPS drop, stuttering, freeze, performance, won't start, 崩溃, 掉帧, 卡顿 symptoms and the user needs a symptom-first diagnostic ladder. NOT for proactive post-install testing; use testing-bgs-modpack.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FBB-84C\u002Fbgs-modding-superpowers\u002Fskills\u002Fdiagnosing-bgs-problems\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"diagnosing bgs problems","modpack","when","for","ladder","diagnostic","proactive","post","drop","log","testing","crash","use","install","user","game","freeze","first","start","performance","2026-11-10 10:12:30",false,"---\nname: diagnosing-bgs-problems\ndescription: Use when a BGS modded game has CTD, crash log, FPS drop, stuttering, freeze, performance, won't start, 崩溃, 掉帧, 卡顿 symptoms and the user needs a symptom-first diagnostic ladder. NOT for proactive post-install testing; use testing-bgs-modpack.\n---\n\n# Diagnosing BGS Problems (judgment skill)\n\nCrashes and FPS collapses are not solved by ritual. A diagnostic pass starts with the symptom the player can reproduce, turns it into evidence, and only then chooses the tool or fix. Scanner output, last-installed-mod panic, and generic optimization lists are inputs to investigate, not verdicts to obey.\n\n## The Iron Law\n\n```text\n+----------------------------------------------------------------------------------------------+\n| Diagnose the symptom before prescribing the cure: reproduce it, collect evidence, isolate the |\n| trigger, then assign root cause. A scanner's mod name is a clue, never the diagnosis.          |\n+----------------------------------------------------------------------------------------------+\n```\n\n## Route gate (one primary skill per intent)\n\nUse this skill when the primary question is: **\"It crashed \u002F FPS tanked \u002F froze \u002F won't start — what is the diagnostic ladder?\"**\n\nDo **not** use this skill as the primary skill for adjacent intents:\n\n| User intent | Primary skill |\n|---|---|\n| \"I installed a batch; how do I proactively verify it before playing?\" | `testing-bgs-modpack` |\n| \"Which record wins \u002F why is this override wrong \u002F should I patch or reorder?\" | `xedit-conflict-audit` |\n| \"Is this archive\u002Floose asset conflict causing the problem?\" | `using-bgs-archive`, then KB for game-specific asset\u002Fprecombine facts |\n| \"Should this mod be in the pack at all?\" | `evaluating-bgs-mods` |\n\nTerminal handoff: once the ladder identifies the root-cause class, stop diagnosing and hand off to the narrow tool skill: `xedit-conflict-audit` for record-level evidence, `using-bgs-archive` for asset\u002Farchive evidence, `writing-bgs-load-order` for plugin enablement\u002Forder, or the relevant per-game KB record for crash-log signatures and console-tool routes.\n\n## When to use \u002F When NOT\n\nUse when:\n\n- The user says CTD, crash log, freeze, won't start, FPS drop, stuttering, performance, 崩溃, 掉帧, or 卡顿.\n- A scanner or crash log named something and the user wants to know whether to remove it.\n- A specific place\u002Faction\u002Fsave route reliably crashes or tanks FPS.\n- The game boots but the same area, menu, combat event, save load, or scene still fails.\n- The question is reactive triage after a symptom appeared.\n\nDo not use when:\n\n- The user is doing planned post-install smoke\u002Fsemantic verification before symptoms appear; use `testing-bgs-modpack`.\n- The user asks for a broad conflict survey rather than a symptom-first failure ladder.\n- The user wants a generic optimization shopping list without a reproducible problem.\n- You are about to inline game-specific logger names, crash signatures, console commands, or toolchain facts. Query KB instead.\n- You are tempted to treat the latest installed mod, the loudest scanner line, or a single successful boot as proof.\n\n## Process Flow\n\n```dot\ndigraph diagnosing_bgs_problems {\n  rankdir=TB;\n  node [shape=box];\n\n  start [shape=doublecircle, label=\"Symptom reported\\nCTD \u002F freeze \u002F FPS drop \u002F won't start\"];\n  classify [label=\"Classify symptom\\ncrash? freeze? low FPS? stutter? missing scene? startup failure?\"];\n  kb [label=\"Query KB for current game\\nlogger\u002Fsignature\u002Ftool facts\\n(do not rely on memory)\"];\n  reproduce [label=\"Reproduce or pin route\\nwhere, action, save, cell, menu, newest batch\"];\n  evidence [label=\"Collect evidence\\ncrash log, repeat count, measured bottleneck, isolated trigger\"];\n  weak [shape=diamond, label=\"Only weak signal?\\nscanner blame \u002F last mod \u002F one boot\"];\n  strengthen [label=\"Strengthen signal\\nrepeat, bisect batch, compare clean route, inspect exact asset\u002Frecord\u002Fcell\"];\n  split [shape=diamond, label=\"Root-cause class?\"];\n  engine [label=\"Engine\u002Fperformance bottleneck\\nmeasure, compare, query game KB\"];\n  record [label=\"Record\u002Fplugin conflict\\nhand off to xedit-conflict-audit\"];\n  asset [label=\"Asset\u002Farchive\u002Floose issue\\nhand off to using-bgs-archive + KB\"];\n  install [label=\"Missing prerequisite \u002F loader \u002F startup setup\\nquery KB or setup skill\"];\n  verdict [shape=doublecircle, label=\"Diagnostic verdict\\nroot cause + evidence + next narrow action\"];\n\n  start -> classify -> kb -> reproduce -> evidence -> weak;\n  weak -> strengthen [label=\"yes\"];\n  strengthen -> evidence;\n  weak -> split [label=\"no\"];\n  split -> engine;\n  split -> record;\n  split -> asset;\n  split -> install;\n  engine -> verdict;\n  record -> verdict;\n  asset -> verdict;\n  install -> verdict;\n}\n```\n\n## KB query discipline\n\nThis skill teaches the diagnostic posture. It does **not** carry game-specific crash signatures, logger names, console-tool commands, or current community tooling in the body.\n\nAlways query the KB before assigning meaning to crash-log or performance evidence:\n\n```text\nbgs_kb_query({\n  query: \"\u003Cgame> crash log scanner attribution triage\",\n  domains: [\"debugging\"],\n  games: [\"\u003Ccurrent game>\"]\n})\n\nbgs_kb_query({\n  query: \"\u003Csymptom> diagnostic ladder performance crash freeze stutter\",\n  domains: [\"debugging\", \"engine\", \"archive-precedence\", \"load-order\"],\n  games: [\"\u003Ccurrent game>\"]\n})\n```\n\nIf the KB has no record for the current game's logger or signature, say so as `[GAP]`, then proceed only with game-agnostic evidence: reproducibility, recent-change window, isolation\u002Fbisect, and readback from the appropriate tool surface.\n\n[STOP] If you are about to write a specific crash logger name, signature phrase, or console command into this skill body, STOP. That belongs in a KB record. This skill may instruct the agent to query for those facts; it must not fossilize them.\n\n## Checklist\n\n1. Name the exact symptom in user language: crash, freeze, FPS drop, stutter, won't start, missing scene, or UI\u002Floader failure.\n2. Ask for or infer the reproducible route: where, what action, which save, which menu\u002Fload\u002Fcell, and whether it happens every time.\n3. Query KB for the current game's crash-log, performance, and tooling facts before interpreting evidence.\n4. Separate hard evidence from weak leads: logs, repeatable triggers, measured bottlenecks, exact asset\u002Frecord\u002Fcell readback vs scanner blame, last-installed-mod bias, and one-off boots.\n5. If the signal is weak, strengthen it before prescribing: repeat, isolate the trigger, bisect the recent batch, or inspect the specific record\u002Fasset route.\n6. For crashes\u002Ffreezes, preserve the crash log or absence-of-log fact and group crashes by action\u002Fmodule\u002Fsignature, not by a single scary line.\n7. For FPS\u002Fstutter, measure the bottleneck route if the current game has a known measurement path in KB; do not assume ordinary graphics tradeoffs solve a CPU\u002Frender-command bottleneck.\n8. For \"won't start\", distinguish loader\u002Fruntime\u002Fprerequisite failure from plugin\u002Fcontent failure before disabling mods.\n9. For archive\u002Floose asset suspicion, route to `using-bgs-archive` and query KB for asset precedence or precompute\u002Fprecombine-style facts.\n10. For record-level suspicion, route to `xedit-conflict-audit` and prove the winner\u002Foverride state instead of changing order by vibes.\n11. State the verdict as: symptom, reproduced signal, evidence, root-cause class, next narrow action, and remaining uncertainty.\n12. If no root cause is proven, say `NOT DIAGNOSED YET` and name the missing evidence; do not downgrade uncertainty into a confident fix.\n\n## Red Flags (STOP)\n\n| Thought | Reality |\n|---|---|\n| \"The scanner blamed mod X, so remove X.\" | Scanner attribution is heuristic. Treat it as a lead until the route, log pattern, or readback proves it. |\n| \"It booted once, so fixed.\" | Boot success does not prove the original crash\u002FFPS route. Re-run the symptom route. |\n| \"The last installed mod caused it.\" | The last mod is context, not root cause. Load order, stale data, assets, and older conflicts can surface only after a new batch. |\n| \"FPS is low; lower graphics settings first.\" | BGS engines can be CPU\u002Frender-command-bound. Query KB and measure the actual bottleneck before tuning the wrong side. |\n| \"No crash log means no diagnosis.\" | Absence of a log is itself evidence. It may point to startup\u002Floader\u002Fnative-runtime failure; query KB and isolate. |\n| \"I can fix this with a generic optimization list.\" | Lists are prescriptions. Diagnosis starts from the symptom and evidence, then picks the narrow fix. |\n| \"The user wants speed, so skip the route.\" | BB84's posture is patience. Skipping the route is how the same failure returns under a different name. |\n\n## Rationalizations\n\n| Excuse | Reality |\n|---|---|\n| \"Crash-log tools exist so I don't have to think.\" | Logs reduce search space; they do not decide causality for you. |\n| \"Bisecting is slow; I can guess from experience.\" | Guessing burns more time when the first confident prescription is wrong. Bisect only the relevant recent window, but bisect it. |\n| \"If disabling one mod stops the crash, that mod is bad.\" | It may be the trigger, a dependency victim, an asset provider, or the first mod exposing a deeper conflict. Prove the class. |\n| \"Optimization mods are harmless; install them all.\" | Unnecessary changes add variables. If the symptom is not the bottleneck they address, they muddy the diagnosis. |\n| \"The tool name is enough context.\" | Tool names are game-specific facts. Query KB for current meaning, version assumptions, and known limitations. |\n| \"The player only wants the game working, not a report.\" | The shortest useful report is still evidence-based: symptom, proof, root-cause class, next action. Anything less is ritual. |\n\n## Recommended Approach: Senior Curator's Lens\n\n> This section reflects an experienced curator's perspective, distilled from BB84's\n> BGS modpack curation work. It is RECOMMENDED guidance, **not enforced rule**.\n> If the user has a working diagnostic process they prefer, the agent SHOULD\n> respect that. The objective rules in this skill body still apply.\n\nRecommended diagnostic mindset:\n\n1. **Crash logs lie. Buffout4 \u002F Trainwreck \u002F .NET SF tell you where the crash\n   surfaced, often not where it originated.** Use the stack trace as one signal\n   among many, not as ground truth.\n2. **Suspect your last change first.** The mod \u002F patch \u002F load-order edit you\n   made most recently has highest prior probability of being the cause, even if\n   the crash log points elsewhere.\n3. **In-game behavioral verification > short smoke test.** Many failures only\n   surface after 30+ minutes of real play (script state accumulation, area\n   transitions, quest state). BB84 reference: 1.0 → 2.0 transition where\n   \"stable 60fps no crash\" claim was wrong because the curator had not played\n   deeply enough.\n4. **Silent failure modes are the dangerous class.** LL miscoherence, missing\n   item drops, NPC outfit incoherence — these don't crash anything but degrade\n   the world. Triage these proactively, not reactively.\n\nSee KB record `mod-evaluation.bb84-curator-perspective-reference` for the full\ncurator essay.\n\n## See also\n\n- `testing-bgs-modpack` — proactive post-install verification before a crash\u002Fperformance symptom exists.\n- `xedit-conflict-audit` — record-level root causes, winning overrides, and conflict severity after diagnosis points at plugin data.\n- `using-bgs-archive` — archive\u002Floose-file asset root causes; query KB for game-specific asset\u002Fprecompute\u002Fprecombine facts.\n- `writing-bgs-load-order` — plugin enablement and load-order file mechanics when diagnosis points at plugin ordering.\n- `bgs_kb_query` — required for per-game crash-log toolchains, scanner limitations, console-tool routes, engine signatures, and current community facts.\n","# Diagnosing BGS Problems (judgment skill)\n\nCrashes and FPS collapses are not solved by ritual. A diagnostic pass starts with the symptom the player can reproduce, turns it into evidence, and only then chooses the tool or fix. Scanner output, last-installed-mod panic, and generic optimization lists are inputs to investigate, not verdicts to obey.\n\n## The Iron Law\n\n```text\n+----------------------------------------------------------------------------------------------+\n| Diagnose the symptom before prescribing the cure: reproduce it, collect evidence, isolate the |\n| trigger, then assign root cause. A scanner's mod name is a clue, never the diagnosis.          |\n+----------------------------------------------------------------------------------------------+\n```\n\n## Route gate (one primary skill per intent)\n\nUse this skill when the primary question is: **\"It crashed \u002F FPS tanked \u002F froze \u002F won't start — what is the diagnostic ladder?\"**\n\nDo **not** use this skill as the primary skill for adjacent intents:\n\n| User intent | Primary skill |\n|---|---|\n| \"I installed a batch; how do I proactively verify it before playing?\" | `testing-bgs-modpack` |\n| \"Which record wins \u002F why is this override wrong \u002F should I patch or reorder?\" | `xedit-conflict-audit` |\n| \"Is this archive\u002Floose asset conflict causing the problem?\" | `using-bgs-archive`, then KB for game-specific asset\u002Fprecombine facts |\n| \"Should this mod be in the pack at all?\" | `evaluating-bgs-mods` |\n\nTerminal handoff: once the ladder identifies the root-cause class, stop diagnosing and hand off to the narrow tool skill: `xedit-conflict-audit` for record-level evidence, `using-bgs-archive` for asset\u002Farchive evidence, `writing-bgs-load-order` for plugin enablement\u002Forder, or the relevant per-game KB record for crash-log signatures and console-tool routes.\n\n## When to use \u002F When NOT\n\nUse when:\n\n- The user says CTD, crash log, freeze, won't start, FPS drop, stuttering, performance, 崩溃, 掉帧, or 卡顿.\n- A scanner or crash log named something and the user wants to know whether to remove it.\n- A specific place\u002Faction\u002Fsave route reliably crashes or tanks FPS.\n- The game boots but the same area, menu, combat event, save load, or scene still fails.\n- The question is reactive triage after a symptom appeared.\n\nDo not use when:\n\n- The user is doing planned post-install smoke\u002Fsemantic verification before symptoms appear; use `testing-bgs-modpack`.\n- The user asks for a broad conflict survey rather than a symptom-first failure ladder.\n- The user wants a generic optimization shopping list without a reproducible problem.\n- You are about to inline game-specific logger names, crash signatures, console commands, or toolchain facts. Query KB instead.\n- You are tempted to treat the latest installed mod, the loudest scanner line, or a single successful boot as proof.\n\n## Process Flow\n\n```dot\ndigraph diagnosing_bgs_problems {\n  rankdir=TB;\n  node [shape=box];\n\n  start [shape=doublecircle, label=\"Symptom reported\\nCTD \u002F freeze \u002F FPS drop \u002F won't start\"];\n  classify [label=\"Classify symptom\\ncrash? freeze? low FPS? stutter? missing scene? startup failure?\"];\n  kb [label=\"Query KB for current game\\nlogger\u002Fsignature\u002Ftool facts\\n(do not rely on memory)\"];\n  reproduce [label=\"Reproduce or pin route\\nwhere, action, save, cell, menu, newest batch\"];\n  evidence [label=\"Collect evidence\\ncrash log, repeat count, measured bottleneck, isolated trigger\"];\n  weak [shape=diamond, label=\"Only weak signal?\\nscanner blame \u002F last mod \u002F one boot\"];\n  strengthen [label=\"Strengthen signal\\nrepeat, bisect batch, compare clean route, inspect exact asset\u002Frecord\u002Fcell\"];\n  split [shape=diamond, label=\"Root-cause class?\"];\n  engine [label=\"Engine\u002Fperformance bottleneck\\nmeasure, compare, query game KB\"];\n  record [label=\"Record\u002Fplugin conflict\\nhand off to xedit-conflict-audit\"];\n  asset [label=\"Asset\u002Farchive\u002Floose issue\\nhand off to using-bgs-archive + KB\"];\n  install [label=\"Missing prerequisite \u002F loader \u002F startup setup\\nquery KB or setup skill\"];\n  verdict [shape=doublecircle, label=\"Diagnostic verdict\\nroot cause + evidence + next narrow action\"];\n\n  start -> classify -> kb -> reproduce -> evidence -> weak;\n  weak -> strengthen [label=\"yes\"];\n  strengthen -> evidence;\n  weak -> split [label=\"no\"];\n  split -> engine;\n  split -> record;\n  split -> asset;\n  split -> install;\n  engine -> verdict;\n  record -> verdict;\n  asset -> verdict;\n  install -> verdict;\n}\n```\n\n## KB query discipline\n\nThis skill teaches the diagnostic posture. It does **not** carry game-specific crash signatures, logger names, console-tool commands, or current community tooling in the body.\n\nAlways query the KB before assigning meaning to crash-log or performance evidence:\n\n```text\nbgs_kb_query({\n  query: \"\u003Cgame> crash log scanner attribution triage\",\n  domains: [\"debugging\"],\n  games: [\"\u003Ccurrent game>\"]\n})\n\nbgs_kb_query({\n  query: \"\u003Csymptom> diagnostic ladder performance crash freeze stutter\",\n  domains: [\"debugging\", \"engine\", \"archive-precedence\", \"load-order\"],\n  games: [\"\u003Ccurrent game>\"]\n})\n```\n\nIf the KB has no record for the current game's logger or signature, say so as `[GAP]`, then proceed only with game-agnostic evidence: reproducibility, recent-change window, isolation\u002Fbisect, and readback from the appropriate tool surface.\n\n[STOP] If you are about to write a specific crash logger name, signature phrase, or console command into this skill body, STOP. That belongs in a KB record. This skill may instruct the agent to query for those facts; it must not fossilize them.\n\n## Checklist\n\n1. Name the exact symptom in user language: crash, freeze, FPS drop, stutter, won't start, missing scene, or UI\u002Floader failure.\n2. Ask for or infer the reproducible route: where, what action, which save, which menu\u002Fload\u002Fcell, and whether it happens every time.\n3. Query KB for the current game's crash-log, performance, and tooling facts before interpreting evidence.\n4. Separate hard evidence from weak leads: logs, repeatable triggers, measured bottlenecks, exact asset\u002Frecord\u002Fcell readback vs scanner blame, last-installed-mod bias, and one-off boots.\n5. If the signal is weak, strengthen it before prescribing: repeat, isolate the trigger, bisect the recent batch, or inspect the specific record\u002Fasset route.\n6. For crashes\u002Ffreezes, preserve the crash log or absence-of-log fact and group crashes by action\u002Fmodule\u002Fsignature, not by a single scary line.\n7. For FPS\u002Fstutter, measure the bottleneck route if the current game has a known measurement path in KB; do not assume ordinary graphics tradeoffs solve a CPU\u002Frender-command bottleneck.\n8. For \"won't start\", distinguish loader\u002Fruntime\u002Fprerequisite failure from plugin\u002Fcontent failure before disabling mods.\n9. For archive\u002Floose asset suspicion, route to `using-bgs-archive` and query KB for asset precedence or precompute\u002Fprecombine-style facts.\n10. For record-level suspicion, route to `xedit-conflict-audit` and prove the winner\u002Foverride state instead of changing order by vibes.\n11. State the verdict as: symptom, reproduced signal, evidence, root-cause class, next narrow action, and remaining uncertainty.\n12. If no root cause is proven, say `NOT DIAGNOSED YET` and name the missing evidence; do not downgrade uncertainty into a confident fix.\n\n## Red Flags (STOP)\n\n| Thought | Reality |\n|---|---|\n| \"The scanner blamed mod X, so remove X.\" | Scanner attribution is heuristic. Treat it as a lead until the route, log pattern, or readback proves it. |\n| \"It booted once, so fixed.\" | Boot success does not prove the original crash\u002FFPS route. Re-run the symptom route. |\n| \"The last installed mod caused it.\" | The last mod is context, not root cause. Load order, stale data, assets, and older conflicts can surface only after a new batch. |\n| \"FPS is low; lower graphics settings first.\" | BGS engines can be CPU\u002Frender-command-bound. Query KB and measure the actual bottleneck before tuning the wrong side. |\n| \"No crash log means no diagnosis.\" | Absence of a log is itself evidence. It may point to startup\u002Floader\u002Fnative-runtime failure; query KB and isolate. |\n| \"I can fix this with a generic optimization list.\" | Lists are prescriptions. Diagnosis starts from the symptom and evidence, then picks the narrow fix. |\n| \"The user wants speed, so skip the route.\" | BB84's posture is patience. Skipping the route is how the same failure returns under a different name. |\n\n## Rationalizations\n\n| Excuse | Reality |\n|---|---|\n| \"Crash-log tools exist so I don't have to think.\" | Logs reduce search space; they do not decide causality for you. |\n| \"Bisecting is slow; I can guess from experience.\" | Guessing burns more time when the first confident prescription is wrong. Bisect only the relevant recent window, but bisect it. |\n| \"If disabling one mod stops the crash, that mod is bad.\" | It may be the trigger, a dependency victim, an asset provider, or the first mod exposing a deeper conflict. Prove the class. |\n| \"Optimization mods are harmless; install them all.\" | Unnecessary changes add variables. If the symptom is not the bottleneck they address, they muddy the diagnosis. |\n| \"The tool name is enough context.\" | Tool names are game-specific facts. Query KB for current meaning, version assumptions, and known limitations. |\n| \"The player only wants the game working, not a report.\" | The shortest useful report is still evidence-based: symptom, proof, root-cause class, next action. Anything less is ritual. |\n\n## Recommended Approach: Senior Curator's Lens\n\n> This section reflects an experienced curator's perspective, distilled from BB84's\n> BGS modpack curation work. It is RECOMMENDED guidance, **not enforced rule**.\n> If the user has a working diagnostic process they prefer, the agent SHOULD\n> respect that. The objective rules in this skill body still apply.\n\nRecommended diagnostic mindset:\n\n1. **Crash logs lie. Buffout4 \u002F Trainwreck \u002F .NET SF tell you where the crash\n   surfaced, often not where it originated.** Use the stack trace as one signal\n   among many, not as ground truth.\n2. **Suspect your last change first.** The mod \u002F patch \u002F load-order edit you\n   made most recently has highest prior probability of being the cause, even if\n   the crash log points elsewhere.\n3. **In-game behavioral verification > short smoke test.** Many failures only\n   surface after 30+ minutes of real play (script state accumulation, area\n   transitions, quest state). BB84 reference: 1.0 → 2.0 transition where\n   \"stable 60fps no crash\" claim was wrong because the curator had not played\n   deeply enough.\n4. **Silent failure modes are the dangerous class.** LL miscoherence, missing\n   item drops, NPC outfit incoherence — these don't crash anything but degrade\n   the world. Triage these proactively, not reactively.\n\nSee KB record `mod-evaluation.bb84-curator-perspective-reference` for the full\ncurator essay.\n\n## See also\n\n- `testing-bgs-modpack` — proactive post-install verification before a crash\u002Fperformance symptom exists.\n- `xedit-conflict-audit` — record-level root causes, winning overrides, and conflict severity after diagnosis points at plugin data.\n- `using-bgs-archive` — archive\u002Floose-file asset root causes; query KB for game-specific asset\u002Fprecompute\u002Fprecombine facts.\n- `writing-bgs-load-order` — plugin enablement and load-order file mechanics when diagnosis points at plugin ordering.\n- `bgs_kb_query` — required for per-game crash-log toolchains, scanner limitations, console-tool routes, engine signatures, and current community facts.\n",{"name":5,"description":7},"main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FBB-84C\u002Fbgs-modding-superpowers\u002Fskills\u002Fdiagnosing-bgs-problems",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill diagnosing-bgs-problems",{"tool":60,"command":61},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill diagnosing-bgs-problems",{"tool":63,"command":64},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill diagnosing-bgs-problems","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FBB-84C\u002Fbgs-modding-superpowers\u002Fskills\u002Fdiagnosing-bgs-problems\u002FSKILL.md",true,[],[69,79,87,95,103,111],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":78},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":78},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":78},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"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":73,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":78},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":78},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":78},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]