[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JTHEMR52JK732VJHX0KYRG":3,"skill-same:01M6JTHEMR52JK732VJHX0KYRG":65},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M6JTHEMR52JK732VJHX0KYRG","xedit-conflict-audit",null,"Use when auditing conflicts in a Bethesda plugin set — determining for a record (or a plugin's records) which override wins, what the conflict label is, what references it, and whether the configuration is safe or breaking.","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\u002Fxedit-conflict-audit\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"audit","xedit conflict audit","conflict","what the","when","for","which","it","records","record","safe","configuration","references","conflicts","use","SET","plugin","2026-11-10 10:12:30",false,"---\nname: xedit-conflict-audit\ndescription: Use when auditing conflicts in a Bethesda plugin set — determining for a record (or a plugin's records) which override wins, what the conflict label is, what references it, and whether the configuration is safe or breaking.\n---\n\n# xEdit Conflict Audit (W2)\n\nInherits the hub `xedit-automation` skill. Do not restate routing or anti-patterns here; this skill is the W2 workflow only.\n\n## Purpose\n\nFor a record or a plugin in scope, produce a verdict: `no_conflict | itpo | itm | minor | breaking`, plus the winning override, the override chain, and a list of plugins that reference the record. Output is a concise summary, not the raw daemon round-trips.\n\n## When To Use\n\n- \"Why is this mod's change not showing up?\" → audit the affected records.\n- \"Which plugins overlap on this NPC \u002F weapon \u002F armour \u002F keyword?\" → audit by editor ID \u002F form ID.\n- \"Is this load order safe to ship?\" → audit a representative sample of records.\n\n## Tools\n\nUse these MCP intent tools (do not drop to `xedit_call` unless an intent tool does not fit):\n\n- `xedit_session` (always first; once per conversation).\n- `xedit_list_capabilities` (once per conversation; sanity-check drift).\n- `xedit_find_record` (locate the record(s) you want to audit).\n- `xedit_inspect_conflicts` (the verdict tool).\n- `xedit_read_record` (when you need to see the actual conflicting field values).\n- `xedit_call` for r6-only daemon fields that no intent wrapper exposes yet:\n  `records.references`, `records.conflict_status`, and `records.apply_filter`.\n\nIf the conflict is broad (many records across many plugins), do not loop through them one by one in the orchestrator — **delegate to a read-only investigator sub-agent** (see Hub skill, \"Sub-agent delegation recipes\").\n\n## 补丁 vs 改顺序决策 \u002F Patch-vs-reorder decision\n\nThis is the judgment gate after the tool surface tells you what wins. xEdit shows the override chain; it does not decide whether the right answer is accept, reorder, clean, remove, or patch. BB84's rule is situational thought over ritual: most overlap is normal, sorting is a single-choice lever, and exhaustive FormID stitching is not realistic at pack scale.\n\nUse this section only to choose the remedy. If the verdict becomes PATCH, stop here and hand off; this W2 skill audits conflicts and names intent, it does not author patch records.\n\n```dot\ndigraph patch_vs_reorder {\n  rankdir=TB;\n  node [shape=box];\n\n  start [shape=doublecircle, label=\"Focused conflict readback\\n(record fields + winning override)\"];\n  behavior [shape=diamond, label=\"Does this conflict explain\\nreal broken\u002Fmissing behavior?\"];\n  normal [shape=doublecircle, label=\"ACCEPT\\nnormal overlap \u002F chosen winner\"];\n  itm [shape=diamond, label=\"Is the losing\u002Fwinning edit\\njust copied vanilla?\"];\n  clean [shape=doublecircle, label=\"CLEAN\\nITM candidate; do not invent meaning\"];\n  systemic [shape=diamond, label=\"Is one side a systemic rule\\nand the other incidental author tweak?\"];\n  reorder [shape=doublecircle, label=\"REORDER\\nlet the systemic rule win\"];\n  needed [shape=diamond, label=\"Are needed fields split\\nacross multiple plugins?\"];\n  patch [shape=doublecircle, label=\"PATCH\\nselectively forward needed fields\"];\n  remove [shape=doublecircle, label=\"REMOVE \u002F REJECT\\nmod role or data not worth repair debt\"];\n\n  start -> behavior;\n  behavior -> normal [label=\"no\"];\n  behavior -> itm [label=\"yes \u002F suspicious\"];\n  itm -> clean [label=\"yes\"];\n  itm -> systemic [label=\"no\"];\n  systemic -> reorder [label=\"yes\"];\n  systemic -> needed [label=\"no\"];\n  needed -> patch [label=\"yes\"];\n  needed -> remove [label=\"no: data not needed \u002F role fails\"];\n}\n```\n\n| Decision | Use when | Do not use when |\n|---|---|---|\n| ACCEPT | The later winner is the intended rule, or the lost edit is not needed for this pack. | You have not read the actual fields; \"no crash\" is not proof. |\n| REORDER | One plugin expresses a broader systemic rule and the other edit is incidental. Let the rule win to reduce patch surface. | Needed fields are split across both sides; order can only choose one winner. |\n| PATCH | Multiple plugins carry needed data for the same FormID, and sorting would lose required behavior either way. | You only feel uncomfortable seeing red; most data overlap is normal. |\n| CLEAN | The record is an unchanged copy of vanilla \u002F ITM candidate. | You are about to delete a value whose purpose you have not understood. |\n| REMOVE \u002F REJECT | The conflict reveals the mod's relevant data is not needed, off-role, or not worth the repair debt. | The source is silent on a hard removal threshold; do not invent one. |\n\n### KB query discipline\n\nThis decision section is game-agnostic. Do not inline game-specific xEdit lore,\nrecord-class gotchas, or community patch-position folklore here.\n\nUse KB when the conflict family depends on current game or ecosystem facts:\n\n```text\nbgs_kb_query({ query: \"xedit patch vs reorder conflict family\", domains: [\"xedit\", \"load-order\"], games: [\"\u003Ccurrent game>\"] })\n```\n\nIf KB is silent, mark `[GAP]` instead of inventing a game-specific rule.\n\n### Red flags (STOP)\n\n| Thought | Reality |\n|---|---|\n| \"Red means broken; fix every red cell.\" | Red means overlapping data. Most overlap is normal; chase behavior-breaking conflicts. |\n| \"Just reorder until both changes work.\" | Reordering is a single-choice lever: A wins or B wins. It cannot merge values. |\n| \"The rightmost value wins, so the rest is irrelevant.\" | Earlier columns are evidence of lost behavior; read them before deciding. |\n| \"I'll drag the field directly into the winning mod.\" | That mutates the source mod and creates cleanup debt. Make a patch if both values are needed. |\n| \"xEdit can patch everything, so order doesn't matter.\" | True in principle, impractical at real pack scale. Use order to reduce patch debt. |\n| \"xEdit shows the conflict, so xEdit alone proves the cause.\" | Some problems are script-use or presentation mismatches; mark uncertainty instead of guessing. |\n\n### Rationalizations\n\n| Excuse | Reality |\n|---|---|\n| \"Sorting is easier; I'll avoid patches.\" | Sorting chooses one side. If both sides contain needed fields, you are still dropping data. |\n| \"I'll patch all conflicts now so future me is safe.\" | Exhaustive FormID stitching is repair debt. Patch only the conflicts tied to intended behavior. |\n| \"The later mod is newer, so its override must be intended.\" | Later means winner, not correct. Compare the field's meaning against the pack's need. |\n| \"The game boots, so the conflict is acceptable.\" | Lost fields can silently disable features. Booting is not semantic success. |\n| \"The field label is obvious enough.\" | Some data names are abstract. If you do not know the purpose, investigate before forwarding. |\n\nWhen the verdict is PATCH, route to `xedit-automation` (see its `## 补丁创作判断` section).\n\n## R6 broad-audit shortcuts (capability gated)\n\nCheck `xedit_list_capabilities` and branch on `system.capabilities.supports.*`.\nUse these r6+ one-call forms when available; old child-by-child and\nrecord-by-record loops remain the fallback for pre-r6 daemons.\n\n### Recursive references (`supports.referencesRecursive`)\n\nFor CELL\u002FWRLD\u002FDIAL\u002FQUST targets, prefer:\n\n```text\nxedit_call({\n  command: \"records.references\",\n  args: { file, formId, recursive: true }\n})\n```\n\n`recursive: true` unions outgoing references across ChildGroup descendants, so\none call replaces the old \"list every ChildGroup child, then reference-probe each\nchild\" loop. Deep reference: `xedit.references-recursive.v1`.\n\n### ChildGroup conflict summary (`supports.conflictStatusChildGroup`)\n\nWhen `records.conflict_status` returns `result.childGroup`, read that block\nbefore expanding individual records. It summarizes per-signature child-group\nstate as `{ total, conflicting }` and includes a capped `conflictingHits` array\n(cap 20) for the first concrete children to inspect.\n\nThis is the broad-audit starting point for CELL\u002FWRLD\u002FDIAL\u002FQUST conflicts:\nsummarize the `childGroup` block, then deep-read only `conflictingHits` or a\nsmall representative sample. Deep reference: `xedit.conflict-status-childgroup.v1`.\n\n### `apply_filter` regex + `parentFormId` (`supports.applyFilterExtensions`)\n\nUse `records.apply_filter` to collapse broad candidate discovery into a single\nserver-side query when the daemon advertises `supports.applyFilterExtensions`\n(or the narrower `.regex` \u002F `.multiPattern` subkeys, if exposed separately).\n\n- Regex fields: `editorIdRegex`, `displayNameRegex`, `fullNameRegex`,\n  `baseEditorIdRegex`, `baseDisplayNameRegex`.\n- Regex engine: `System.RegularExpressions.TRegEx`.\n- Guardrails: 100ms per-record timeout, 4-worker semaphore, and a\n  `RegexSlotsExhausted` response counter so saturation is distinguishable from\n  no matches.\n- Multi-pattern OR: each `*Pattern` and `*Regex` field may be a scalar string or\n  an array with OR semantics; max 32 entries.\n- `parentFormId`: single-call ancestor filtering, e.g. \"all REFRs whose\n  container chain contains CELL X\" without building your own parent walk.\n\nDeep reference: `xedit.apply-filter-extensions.v1`.\n\n## Workflow\n\n1. **Bootstrap session.** `xedit_session({})`. Confirm `gameMode`, `consentEnabled` not needed here (read-only), and `loadOrderSize` matches expectation.\n2. **Sanity-check capabilities.** `xedit_list_capabilities({})`. Read the `drift.onlyInLive` and `drift.onlyInDigest` arrays plus the r6 support keys. If a target command you intend to use is missing from live, stop and tell the user.\n3. **Scope the audit.** Decide whether the audit is per-record, per-plugin, per-signature, or parent-scoped (e.g. all REFRs under a CELL).\n4. **Locate records with the narrowest supported query.**\n   - Per-record by FormID: `xedit_find_record({ file, formId })`.\n   - Per-editor-ID: `xedit_find_record({ editorId })`.\n   - Parent-scoped or regex candidate set on r6+: `xedit_call({ command: \"records.apply_filter\", args: { file?, signature?, parentFormId?, editorIdRegex?, ... } })`.\n   - Per-plugin fallback: `xedit_call({ command: \"records.list\", args: { file, signature? } })`, then iterate or delegate if large.\n5. **Inspect conflicts with child-group awareness.** For each focused target, prefer `xedit_inspect_conflicts({ file, formId })`. For broad CELL\u002FWRLD\u002FDIAL\u002FQUST targets on r6+, call `records.conflict_status` through `xedit_call` if you need the raw `result.childGroup` summary; expand only `conflictingHits` or a representative sample instead of probing every child.\n6. **Collect references efficiently.** On r6+, `xedit_call({ command: \"records.references\", args: { file, formId, recursive: true } })` gives a ChildGroup-wide outgoing-reference union. On pre-r6, fall back to the old child walk or delegate the loop.\n7. **Classify verdicts.** Read the `verdict` field from the intent tool or map the raw `records.conflict_status` result with the same W2 labels:\n   - `no_conflict` → safe.\n   - `itpo` \u002F `itm` → likely safe; consider cleaning.\n   - `minor` → human review.\n   - `breaking` → halt and surface.\n8. **For non-trivial verdicts, read the actual record.** `xedit_read_record({ file, formId })`. Compare `record.fields` vs `winningOverride` vs `baseRecord`. Identify the diverging fields.\n9. **Summarise.** Produce a short report: one row per record or child-group signature bucket audited, columns `[file, formId, editorId\u002Fsignature, verdict, winningFile, referencerCount, childGroupConflicts]`. Surface only the breaking\u002Fminor verdicts to the user by default; the rest are appendix.\n\n## Verification (what counts as semantic pass)\n\n- The audit's verdict for each spot-checked record matches what manual xEdit GUI inspection would show.\n- For breaking verdicts, you have read the actual record fields and can name the diverging fields.\n- The output report is concise: one row per record or child-group signature\n  bucket, no raw daemon envelopes.\n- The session's audit log (`.opencode\u002Fartifacts\u002Fxedit-mcp\u002Faudit\u002FYYYY-MM-DD.jsonl`) contains one entry per MCP tool call you made.\n\nIf you cannot meet these for a record, mark it `unknown` in the report and explain why — do not guess.\n\n## Common Mistakes\n\n- Calling `xedit_call records.conflict_status` directly when `xedit_inspect_conflicts` would do it with the verdict label already mapped; use raw `records.conflict_status` only when you need r6 response blocks such as `result.childGroup`.\n- Treating `no_conflict` as proof of safety without reading at least one representative record.\n- Looping through hundreds of records in the orchestrator's context when r6 `recursive`, `childGroup`, `apply_filter`, or delegation would collapse the work.\n- Forgetting to call `xedit_session` first; downstream tools will refuse with `state_violation`.\n- Asking the daemon for a file that is not in the load order; `LOAD001` will fire — load it via the session first.\n\n## Delegation hints\n\nThis workflow is a strong candidate for read-only sub-agent delegation in two cases:\n\n1. **Large scope** (> ~10 records to audit) — the round-trips will fill the orchestrator's context. Delegate the loop; receive the per-record summary table.\n2. **Exploratory diagnosis** (\"I don't know which record is causing this in-game issue\") — let a sub-agent triangulate by editor ID and signature; you'll get the candidates back.\n\nWhen delegating, include this skill and the hub skill in the sub-agent's prompt and provide the scope + budget.\n","# xEdit Conflict Audit (W2)\n\nInherits the hub `xedit-automation` skill. Do not restate routing or anti-patterns here; this skill is the W2 workflow only.\n\n## Purpose\n\nFor a record or a plugin in scope, produce a verdict: `no_conflict | itpo | itm | minor | breaking`, plus the winning override, the override chain, and a list of plugins that reference the record. Output is a concise summary, not the raw daemon round-trips.\n\n## When To Use\n\n- \"Why is this mod's change not showing up?\" → audit the affected records.\n- \"Which plugins overlap on this NPC \u002F weapon \u002F armour \u002F keyword?\" → audit by editor ID \u002F form ID.\n- \"Is this load order safe to ship?\" → audit a representative sample of records.\n\n## Tools\n\nUse these MCP intent tools (do not drop to `xedit_call` unless an intent tool does not fit):\n\n- `xedit_session` (always first; once per conversation).\n- `xedit_list_capabilities` (once per conversation; sanity-check drift).\n- `xedit_find_record` (locate the record(s) you want to audit).\n- `xedit_inspect_conflicts` (the verdict tool).\n- `xedit_read_record` (when you need to see the actual conflicting field values).\n- `xedit_call` for r6-only daemon fields that no intent wrapper exposes yet:\n  `records.references`, `records.conflict_status`, and `records.apply_filter`.\n\nIf the conflict is broad (many records across many plugins), do not loop through them one by one in the orchestrator — **delegate to a read-only investigator sub-agent** (see Hub skill, \"Sub-agent delegation recipes\").\n\n## 补丁 vs 改顺序决策 \u002F Patch-vs-reorder decision\n\nThis is the judgment gate after the tool surface tells you what wins. xEdit shows the override chain; it does not decide whether the right answer is accept, reorder, clean, remove, or patch. BB84's rule is situational thought over ritual: most overlap is normal, sorting is a single-choice lever, and exhaustive FormID stitching is not realistic at pack scale.\n\nUse this section only to choose the remedy. If the verdict becomes PATCH, stop here and hand off; this W2 skill audits conflicts and names intent, it does not author patch records.\n\n```dot\ndigraph patch_vs_reorder {\n  rankdir=TB;\n  node [shape=box];\n\n  start [shape=doublecircle, label=\"Focused conflict readback\\n(record fields + winning override)\"];\n  behavior [shape=diamond, label=\"Does this conflict explain\\nreal broken\u002Fmissing behavior?\"];\n  normal [shape=doublecircle, label=\"ACCEPT\\nnormal overlap \u002F chosen winner\"];\n  itm [shape=diamond, label=\"Is the losing\u002Fwinning edit\\njust copied vanilla?\"];\n  clean [shape=doublecircle, label=\"CLEAN\\nITM candidate; do not invent meaning\"];\n  systemic [shape=diamond, label=\"Is one side a systemic rule\\nand the other incidental author tweak?\"];\n  reorder [shape=doublecircle, label=\"REORDER\\nlet the systemic rule win\"];\n  needed [shape=diamond, label=\"Are needed fields split\\nacross multiple plugins?\"];\n  patch [shape=doublecircle, label=\"PATCH\\nselectively forward needed fields\"];\n  remove [shape=doublecircle, label=\"REMOVE \u002F REJECT\\nmod role or data not worth repair debt\"];\n\n  start -> behavior;\n  behavior -> normal [label=\"no\"];\n  behavior -> itm [label=\"yes \u002F suspicious\"];\n  itm -> clean [label=\"yes\"];\n  itm -> systemic [label=\"no\"];\n  systemic -> reorder [label=\"yes\"];\n  systemic -> needed [label=\"no\"];\n  needed -> patch [label=\"yes\"];\n  needed -> remove [label=\"no: data not needed \u002F role fails\"];\n}\n```\n\n| Decision | Use when | Do not use when |\n|---|---|---|\n| ACCEPT | The later winner is the intended rule, or the lost edit is not needed for this pack. | You have not read the actual fields; \"no crash\" is not proof. |\n| REORDER | One plugin expresses a broader systemic rule and the other edit is incidental. Let the rule win to reduce patch surface. | Needed fields are split across both sides; order can only choose one winner. |\n| PATCH | Multiple plugins carry needed data for the same FormID, and sorting would lose required behavior either way. | You only feel uncomfortable seeing red; most data overlap is normal. |\n| CLEAN | The record is an unchanged copy of vanilla \u002F ITM candidate. | You are about to delete a value whose purpose you have not understood. |\n| REMOVE \u002F REJECT | The conflict reveals the mod's relevant data is not needed, off-role, or not worth the repair debt. | The source is silent on a hard removal threshold; do not invent one. |\n\n### KB query discipline\n\nThis decision section is game-agnostic. Do not inline game-specific xEdit lore,\nrecord-class gotchas, or community patch-position folklore here.\n\nUse KB when the conflict family depends on current game or ecosystem facts:\n\n```text\nbgs_kb_query({ query: \"xedit patch vs reorder conflict family\", domains: [\"xedit\", \"load-order\"], games: [\"\u003Ccurrent game>\"] })\n```\n\nIf KB is silent, mark `[GAP]` instead of inventing a game-specific rule.\n\n### Red flags (STOP)\n\n| Thought | Reality |\n|---|---|\n| \"Red means broken; fix every red cell.\" | Red means overlapping data. Most overlap is normal; chase behavior-breaking conflicts. |\n| \"Just reorder until both changes work.\" | Reordering is a single-choice lever: A wins or B wins. It cannot merge values. |\n| \"The rightmost value wins, so the rest is irrelevant.\" | Earlier columns are evidence of lost behavior; read them before deciding. |\n| \"I'll drag the field directly into the winning mod.\" | That mutates the source mod and creates cleanup debt. Make a patch if both values are needed. |\n| \"xEdit can patch everything, so order doesn't matter.\" | True in principle, impractical at real pack scale. Use order to reduce patch debt. |\n| \"xEdit shows the conflict, so xEdit alone proves the cause.\" | Some problems are script-use or presentation mismatches; mark uncertainty instead of guessing. |\n\n### Rationalizations\n\n| Excuse | Reality |\n|---|---|\n| \"Sorting is easier; I'll avoid patches.\" | Sorting chooses one side. If both sides contain needed fields, you are still dropping data. |\n| \"I'll patch all conflicts now so future me is safe.\" | Exhaustive FormID stitching is repair debt. Patch only the conflicts tied to intended behavior. |\n| \"The later mod is newer, so its override must be intended.\" | Later means winner, not correct. Compare the field's meaning against the pack's need. |\n| \"The game boots, so the conflict is acceptable.\" | Lost fields can silently disable features. Booting is not semantic success. |\n| \"The field label is obvious enough.\" | Some data names are abstract. If you do not know the purpose, investigate before forwarding. |\n\nWhen the verdict is PATCH, route to `xedit-automation` (see its `## 补丁创作判断` section).\n\n## R6 broad-audit shortcuts (capability gated)\n\nCheck `xedit_list_capabilities` and branch on `system.capabilities.supports.*`.\nUse these r6+ one-call forms when available; old child-by-child and\nrecord-by-record loops remain the fallback for pre-r6 daemons.\n\n### Recursive references (`supports.referencesRecursive`)\n\nFor CELL\u002FWRLD\u002FDIAL\u002FQUST targets, prefer:\n\n```text\nxedit_call({\n  command: \"records.references\",\n  args: { file, formId, recursive: true }\n})\n```\n\n`recursive: true` unions outgoing references across ChildGroup descendants, so\none call replaces the old \"list every ChildGroup child, then reference-probe each\nchild\" loop. Deep reference: `xedit.references-recursive.v1`.\n\n### ChildGroup conflict summary (`supports.conflictStatusChildGroup`)\n\nWhen `records.conflict_status` returns `result.childGroup`, read that block\nbefore expanding individual records. It summarizes per-signature child-group\nstate as `{ total, conflicting }` and includes a capped `conflictingHits` array\n(cap 20) for the first concrete children to inspect.\n\nThis is the broad-audit starting point for CELL\u002FWRLD\u002FDIAL\u002FQUST conflicts:\nsummarize the `childGroup` block, then deep-read only `conflictingHits` or a\nsmall representative sample. Deep reference: `xedit.conflict-status-childgroup.v1`.\n\n### `apply_filter` regex + `parentFormId` (`supports.applyFilterExtensions`)\n\nUse `records.apply_filter` to collapse broad candidate discovery into a single\nserver-side query when the daemon advertises `supports.applyFilterExtensions`\n(or the narrower `.regex` \u002F `.multiPattern` subkeys, if exposed separately).\n\n- Regex fields: `editorIdRegex`, `displayNameRegex`, `fullNameRegex`,\n  `baseEditorIdRegex`, `baseDisplayNameRegex`.\n- Regex engine: `System.RegularExpressions.TRegEx`.\n- Guardrails: 100ms per-record timeout, 4-worker semaphore, and a\n  `RegexSlotsExhausted` response counter so saturation is distinguishable from\n  no matches.\n- Multi-pattern OR: each `*Pattern` and `*Regex` field may be a scalar string or\n  an array with OR semantics; max 32 entries.\n- `parentFormId`: single-call ancestor filtering, e.g. \"all REFRs whose\n  container chain contains CELL X\" without building your own parent walk.\n\nDeep reference: `xedit.apply-filter-extensions.v1`.\n\n## Workflow\n\n1. **Bootstrap session.** `xedit_session({})`. Confirm `gameMode`, `consentEnabled` not needed here (read-only), and `loadOrderSize` matches expectation.\n2. **Sanity-check capabilities.** `xedit_list_capabilities({})`. Read the `drift.onlyInLive` and `drift.onlyInDigest` arrays plus the r6 support keys. If a target command you intend to use is missing from live, stop and tell the user.\n3. **Scope the audit.** Decide whether the audit is per-record, per-plugin, per-signature, or parent-scoped (e.g. all REFRs under a CELL).\n4. **Locate records with the narrowest supported query.**\n   - Per-record by FormID: `xedit_find_record({ file, formId })`.\n   - Per-editor-ID: `xedit_find_record({ editorId })`.\n   - Parent-scoped or regex candidate set on r6+: `xedit_call({ command: \"records.apply_filter\", args: { file?, signature?, parentFormId?, editorIdRegex?, ... } })`.\n   - Per-plugin fallback: `xedit_call({ command: \"records.list\", args: { file, signature? } })`, then iterate or delegate if large.\n5. **Inspect conflicts with child-group awareness.** For each focused target, prefer `xedit_inspect_conflicts({ file, formId })`. For broad CELL\u002FWRLD\u002FDIAL\u002FQUST targets on r6+, call `records.conflict_status` through `xedit_call` if you need the raw `result.childGroup` summary; expand only `conflictingHits` or a representative sample instead of probing every child.\n6. **Collect references efficiently.** On r6+, `xedit_call({ command: \"records.references\", args: { file, formId, recursive: true } })` gives a ChildGroup-wide outgoing-reference union. On pre-r6, fall back to the old child walk or delegate the loop.\n7. **Classify verdicts.** Read the `verdict` field from the intent tool or map the raw `records.conflict_status` result with the same W2 labels:\n   - `no_conflict` → safe.\n   - `itpo` \u002F `itm` → likely safe; consider cleaning.\n   - `minor` → human review.\n   - `breaking` → halt and surface.\n8. **For non-trivial verdicts, read the actual record.** `xedit_read_record({ file, formId })`. Compare `record.fields` vs `winningOverride` vs `baseRecord`. Identify the diverging fields.\n9. **Summarise.** Produce a short report: one row per record or child-group signature bucket audited, columns `[file, formId, editorId\u002Fsignature, verdict, winningFile, referencerCount, childGroupConflicts]`. Surface only the breaking\u002Fminor verdicts to the user by default; the rest are appendix.\n\n## Verification (what counts as semantic pass)\n\n- The audit's verdict for each spot-checked record matches what manual xEdit GUI inspection would show.\n- For breaking verdicts, you have read the actual record fields and can name the diverging fields.\n- The output report is concise: one row per record or child-group signature\n  bucket, no raw daemon envelopes.\n- The session's audit log (`.opencode\u002Fartifacts\u002Fxedit-mcp\u002Faudit\u002FYYYY-MM-DD.jsonl`) contains one entry per MCP tool call you made.\n\nIf you cannot meet these for a record, mark it `unknown` in the report and explain why — do not guess.\n\n## Common Mistakes\n\n- Calling `xedit_call records.conflict_status` directly when `xedit_inspect_conflicts` would do it with the verdict label already mapped; use raw `records.conflict_status` only when you need r6 response blocks such as `result.childGroup`.\n- Treating `no_conflict` as proof of safety without reading at least one representative record.\n- Looping through hundreds of records in the orchestrator's context when r6 `recursive`, `childGroup`, `apply_filter`, or delegation would collapse the work.\n- Forgetting to call `xedit_session` first; downstream tools will refuse with `state_violation`.\n- Asking the daemon for a file that is not in the load order; `LOAD001` will fire — load it via the session first.\n\n## Delegation hints\n\nThis workflow is a strong candidate for read-only sub-agent delegation in two cases:\n\n1. **Large scope** (> ~10 records to audit) — the round-trips will fill the orchestrator's context. Delegate the loop; receive the per-record summary table.\n2. **Exploratory diagnosis** (\"I don't know which record is causing this in-game issue\") — let a sub-agent triangulate by editor ID and signature; you'll get the candidates back.\n\nWhen delegating, include this skill and the hub skill in the sub-agent's prompt and provide the scope + budget.\n",{"name":5,"description":7},"main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FBB-84C\u002Fbgs-modding-superpowers\u002Fskills\u002Fxedit-conflict-audit",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":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill xedit-conflict-audit",{"tool":57,"command":58},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill xedit-conflict-audit",{"tool":60,"command":61},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill xedit-conflict-audit","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\u002Fxedit-conflict-audit\u002FSKILL.md",true,[],[66,76,84,92,100,108],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":71,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":75},"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":75},"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":75},"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":75},"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":75},"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":75},"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",[],[]]