[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79P6J5CMTW1QJSXGV9D8ZFF":3,"skill-same:01M79P6J5CMTW1QJSXGV9D8ZFF":46},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79P6J5CMTW1QJSXGV9D8ZFF","bmad-loop-resolve",null,"Interactive escalation-resolution workflow for the bmad-loop orchestrator. A bmad-loop run paused on a CRITICAL escalation (a contradiction or gap a dev\u002Freview session could not safely resolve alone); you and the human disambiguate the frozen spec so the story can be re-driven. Invoked as \u002Fbmad-loop-resolve \u003Cstory-key>. Unlike the automated dev\u002Freview sessions this session is interactive — a human is present and you SHOULD ask.","OrigoStudio\u002Forigo-design","OrigoStudio","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F256943203?v=4","01M79P1MQHVZ4PTXBQVM11Q00S","Origo Studio","01M79P1MR8S30QEEM0Z6MGX1MA",1,"MIT","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-loop-resolve\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bmad-loop-resolve\ndescription: 'Interactive escalation-resolution workflow for the bmad-loop orchestrator. A bmad-loop run paused on a CRITICAL escalation (a contradiction or gap a dev\u002Freview session could not safely resolve alone); you and the human disambiguate the frozen spec so the story can be re-driven. Invoked as \u002Fbmad-loop-resolve \u003Cstory-key>. Unlike the automated dev\u002Freview sessions this session is interactive — a human is present and you SHOULD ask.'\n---\n\n# bmad-loop Escalation Resolution\n\nA `bmad-loop` run drove a story through dev → review, a session raised a\n**CRITICAL escalation** (work could not proceed safely — usually a contradiction\nor an unanswered question in the _frozen spec_), and the orchestrator paused the\nwhole run for a human. The session that escalated is gone; you are a fresh\ninteractive session whose job is to **resolve the ambiguity with the human and\nupdate the frozen spec**, so the orchestrator can re-arm the story and re-drive\nit against a corrected spec.\n\nThis is **interactive**: a human IS present. Ask questions, present options,\nrecommend — but the human makes the call. (`$BMAD_LOOP_MODE` is intentionally\nunset for this session; the never-ask automation rules do NOT apply.)\n\n## Identity & I\u002FO contract\n\nThese environment variables are set:\n\n- `$BMAD_LOOP_RUN_DIR` — the paused run's directory.\n- `$BMAD_LOOP_STORY_KEY` — the escalated story key (also your invocation argument).\n- `$BMAD_LOOP_RESOLVE_CONTEXT` — path to a `context.json` written for you.\n\n**Read `$BMAD_LOOP_RESOLVE_CONTEXT` FIRST.** Its schema:\n\n```json\n{\n  \"story_key\": \"6-4-cli-list-command\",\n  \"run_id\": \"20260613-111429-6a14\",\n  \"spec_file\": \"\u002Fabs\u002Fpath\u002Fto\u002F_bmad-output\u002Fimplementation-artifacts\u002Fspec-\u003Cstory>.md\",\n  \"baseline_commit\": \"\u003Csha>\",\n  \"paused_reason\": \"CRITICAL escalation from review session: ...\",\n  \"escalations\": [\n    {\n      \"type\": \"\u003Ckind>\",\n      \"severity\": \"CRITICAL\",\n      \"detail\": \"\u003Cwhat's ambiguous\u002Fcontradictory>\"\n    }\n  ],\n  \"resolution_path\": \"\u002Fabs\u002Fpath\u002Fto\u002F\u003Crun>\u002Fresolve\u002F\u003Cstory>\u002Fresolution.json\"\n}\n```\n\nIn **stories mode** (folder+id dispatch) the context also carries a `stories`\nblock — the manifest intent for this story, so you can see WHAT it is meant to do\nwithout hunting for it:\n\n```json\n{\n  \"stories\": {\n    \"spec_folder\": \"_bmad-output\u002Fepic-1\",\n    \"story\": {\n      \"id\": \"6-4-cli-list-command\",\n      \"title\": \"CLI list command\",\n      \"description\": \"…\",\n      \"spec_checkpoint\": false,\n      \"done_checkpoint\": false,\n      \"invoke_dev_with\": \"…free-text planner→dev note, or ''…\"\n    },\n    \"sentinel\": {\n      \"kind\": \"unresolved\",\n      \"path\": \"...\u002Fstories\u002F6-4-cli-list-command-unresolved.md\",\n      \"blocking_condition\": \"…the reason planning halted…\"\n    }\n  }\n}\n```\n\nThe `sentinel` sub-block is present ONLY when the escalated story is a **sentinel**\n(see the stories-mode section below); an ordinary escalation omits it.\n\nYour **output marker** is the file at `resolution_path`. Writing it is the LAST\naction of a successful resolution. Schema:\n\n```json\n{\n  \"story_key\": \"\u003Ckey>\",\n  \"decision\": \"\u003Cone or two sentences: the rule you and the human chose>\",\n  \"spec_file\": \"\u003Cthe spec you edited>\",\n  \"spec_updated\": true,\n  \"restore_patch\": \"\u003Coptional: path to a saved intent-gap patch to re-apply>\"\n}\n```\n\n`restore_patch` is **optional** and used only for the intent-gap patch-restore\ncase below — omit it entirely for an ordinary resolution.\n\n## What you MUST do\n\n1. **Read the context**, then read the **frozen spec** at `spec_file` in full —\n   especially its `\u003Cfrozen-after-approval>` block (the intent the dev\u002Freview\n   sessions treat as authoritative). The escalation is almost always that this\n   block is silent on, or contradicts, a case the implementation hit.\n2. **Present the escalation plainly** to the human: what is ambiguous or\n   contradictory, why it blocks safe implementation, and **2–4 concrete\n   resolution options** with a clear recommendation and its trade-offs. Keep it\n   tight — quote the relevant spec lines.\n3. **Get the human's decision.** Ask follow-ups if the choice is unclear. Do not\n   invent requirements; if the human is unsure, help them reason, don't guess.\n4. **Update the frozen spec** to encode the decision unambiguously: amend the\n   `\u003Cfrozen-after-approval>` block and any affected acceptance criteria \u002F test\n   matrix rows so a fresh dev session has exactly one correct reading. Make the\n   smallest change that removes the ambiguity. You MAY use the `bmad-spec` or\n   `bmad-correct-course` skills if a larger spec change is warranted.\n5. **Write the resolution marker** at `resolution_path` (schema above), then tell\n   the human the resolution is recorded and they can exit this session — the\n   orchestrator will offer to **re-arm the story and resume the run** (a clean\n   rebuild against the corrected spec).\n\n## Special case: a review-stage `intent gap` with a saved patch\n\nWhen the escalation came from the **review step** halting on an `intent gap`, the\ndev session first **saved its attempted change as a patch file** (in the\nimplementation-artifacts folder) before reverting the tree — the escalation\n`detail` and the spec's `## Review Triage Log` reference the patch path. That\npatch is concrete evidence: it shows exactly which reading of the intent the run\nimplemented.\n\n**First check `restore_supported` in the context file.** When it is `false`\n(worktree-isolation runs: the re-drive discards and re-mounts the unit's\nworktree, so an in-place restore can never land; an escalation with no recorded\nspec: a restored patch has no review to resume; a pre-planning sentinel wedge:\nthere is no attempted implementation to restore), **never offer the restore\noption and never record `restore_patch`** — the orchestrator would reject the\nresolution and this whole session's negotiation would be wasted. The patch is\nstill available as evidence.\n\nUse the patch two ways:\n\n- **As evidence.** Read the patch (and the diff it represents) to see what the\n  guessed reading produced — often clearer input for writing the clarification\n  than the questions alone.\n- **When the attempted reading was actually correct.** Sometimes the run's guess\n  is the right one and only the _intent_ was silent. Present this as an explicit\n  option to the human: _\"the implementation read it as X, which is in fact what we\n  want — amend the intent to say X, and resume **review** on the already-written\n  change instead of re-implementing it.\"_ If the human chooses this:\n  1. Still **amend the intent** in the spec so it unambiguously says X (step 4\n     above is unchanged — the frozen intent must match the restored code).\n  2. Add **`\"restore_patch\": \"\u003Cthe saved patch path>\"`** to `resolution.json`\n     (copy the path verbatim from the escalation detail \u002F triage log).\n\n  The orchestrator then re-arms the spec to `in-review`, re-applies the patch onto\n  the baseline, and re-dispatches — the session resumes at the review step on the\n  restored diff. **Do NOT `git apply` the patch yourself and do NOT set the spec\n  status** — the orchestrator does both deterministically at re-arm.\n\n  **The restore must not overlap resolution commits.** Re-arm advances the\n  re-drive's baseline to the branch's post-resolve HEAD, but the saved patch was\n  diffed from the ORIGINAL baseline — so if this session left commits that touch\n  the patch's own files, the restore's `git apply` fails and the story\n  re-escalates (loudly, by design: the orchestrator never silently merges the\n  resolution with the stale attempt). If the resolution work already includes or\n  supersedes the attempted change, **omit `restore_patch`** — the commits survive\n  re-arm as the re-drive's starting point, so a from-scratch re-drive builds\n  directly on them.\n\nIf the attempted reading was wrong (the common case), omit `restore_patch`\nentirely: the orchestrator re-drives from scratch against the corrected intent.\n\n## What you MUST NOT do\n\n- **Do NOT** write the orchestrator's `result.json` — that is a dev\u002Freview\n  artifact; this is not one of those sessions.\n- **Do NOT** change `sprint-status.yaml`, and **do NOT** set the spec's `status:`\n  field — the orchestrator deterministically re-arms the spec status on resume.\n  Edit spec **content** only.\n- **Do NOT** implement the story, write feature code, run tests, or commit. Your\n  job ends at a corrected spec + the resolution marker.\n- **Do NOT** widen scope. Resolve exactly the escalated ambiguity; if you notice\n  unrelated problems, note them to the human but leave them alone.\n\n## Stories mode: sentinels and the preserved copy\n\nIn stories mode a story that could not even be **planned** — the dev session hit\na contradiction or gap before it could write a real spec — leaves a fixed-slug\n**sentinel** file instead of a frozen spec: `\u003Cid>-unresolved.md` (the intent was\ntoo ambiguous to plan) or `\u003Cid>-ambiguous.md` (more than one story spec matched\nthe id). The context's `stories.sentinel` block names it and carries the\n`blocking_condition` the session recorded.\n\nA sentinel is **not a spec you edit** — there is no plan or `\u003Cfrozen-after-approval>`\nblock inside it. So for a sentinel:\n\n- **Do not try to amend a frozen spec** (step 4's \"edit the frozen spec\" does not\n  apply — there isn't one). Instead resolve the _upstream_ ambiguity so a fresh\n  planning pass can succeed: usually that means clarifying `SPEC.md` (the epic\n  spec) or this story's entry in `stories.yaml` — the `title` \u002F `description` \u002F\n  `invoke_dev_with` the planner reads — with the human.\n- On **re-arm** the orchestrator does NOT flip the sentinel to `ready-for-dev`\n  (there is no plan to route to). It **preserves a copy** of the sentinel under\n  `{run}\u002Fsentinels\u002F\u003Cid>-\u003Ckind>.md` as a breadcrumb, **deletes** the sentinel, and\n  the next dispatch re-plans the story from scratch (leg 1 again for a\n  `spec_checkpoint` story). You do not touch the sentinel file yourself.\n- Write the resolution marker as usual once the human has decided how to\n  disambiguate; set `spec_file` to whatever you edited (e.g. `SPEC.md`), or omit\n  it if the fix was entirely in `stories.yaml`.\n\n### Not a sentinel: more than one file matches the id\n\nDistinct from the single-file `\u003Cid>-ambiguous.md` sentinel above: when **more\nthan one** file in `stories\u002F` matches `\u003Cid>-*.md` (say `3-login.md` AND\n`3-signup.md`), the id itself is ambiguous _on disk_ and the orchestrator wedges\nthe story without picking either file. You can recognize this state by the\nescalation reason (`ambiguous story file match: \u003Cnames>`) and by what the\ncontext does NOT have: no `stories.sentinel` block and no single spec path.\n\nThe auto-clear above does **not** apply — there is no sentinel to preserve and\ndelete, and re-arming alone just re-wedges on the same duplicates. The\nresolution IS the cleanup: with the human, decide which file is the story's real\nspec and remove or rename the other (merge content first if both carry real\nwork; renaming must move it out of the `\u003Cid>-*` pattern or to another id).\nExactly one match re-dispatches that spec; zero matches re-plans from scratch.\nThen write the resolution marker as usual — re-arm + resume takes it from there.\n\n## If you cannot resolve it\n\nIf the human defers, the information needed is genuinely unavailable, or the\nright fix is out of scope for a spec edit (e.g. it needs a PRD\u002Farchitecture\nchange), say so plainly and **do not** write the resolution marker. Exiting\nwithout the marker leaves the story escalated and the run paused — the safe\ndefault. The orchestrator will not re-arm a story with no recorded resolution.\n","# bmad-loop Escalation Resolution\n\nA `bmad-loop` run drove a story through dev → review, a session raised a\n**CRITICAL escalation** (work could not proceed safely — usually a contradiction\nor an unanswered question in the _frozen spec_), and the orchestrator paused the\nwhole run for a human. The session that escalated is gone; you are a fresh\ninteractive session whose job is to **resolve the ambiguity with the human and\nupdate the frozen spec**, so the orchestrator can re-arm the story and re-drive\nit against a corrected spec.\n\nThis is **interactive**: a human IS present. Ask questions, present options,\nrecommend — but the human makes the call. (`$BMAD_LOOP_MODE` is intentionally\nunset for this session; the never-ask automation rules do NOT apply.)\n\n## Identity & I\u002FO contract\n\nThese environment variables are set:\n\n- `$BMAD_LOOP_RUN_DIR` — the paused run's directory.\n- `$BMAD_LOOP_STORY_KEY` — the escalated story key (also your invocation argument).\n- `$BMAD_LOOP_RESOLVE_CONTEXT` — path to a `context.json` written for you.\n\n**Read `$BMAD_LOOP_RESOLVE_CONTEXT` FIRST.** Its schema:\n\n```json\n{\n  \"story_key\": \"6-4-cli-list-command\",\n  \"run_id\": \"20260613-111429-6a14\",\n  \"spec_file\": \"\u002Fabs\u002Fpath\u002Fto\u002F_bmad-output\u002Fimplementation-artifacts\u002Fspec-\u003Cstory>.md\",\n  \"baseline_commit\": \"\u003Csha>\",\n  \"paused_reason\": \"CRITICAL escalation from review session: ...\",\n  \"escalations\": [\n    {\n      \"type\": \"\u003Ckind>\",\n      \"severity\": \"CRITICAL\",\n      \"detail\": \"\u003Cwhat's ambiguous\u002Fcontradictory>\"\n    }\n  ],\n  \"resolution_path\": \"\u002Fabs\u002Fpath\u002Fto\u002F\u003Crun>\u002Fresolve\u002F\u003Cstory>\u002Fresolution.json\"\n}\n```\n\nIn **stories mode** (folder+id dispatch) the context also carries a `stories`\nblock — the manifest intent for this story, so you can see WHAT it is meant to do\nwithout hunting for it:\n\n```json\n{\n  \"stories\": {\n    \"spec_folder\": \"_bmad-output\u002Fepic-1\",\n    \"story\": {\n      \"id\": \"6-4-cli-list-command\",\n      \"title\": \"CLI list command\",\n      \"description\": \"…\",\n      \"spec_checkpoint\": false,\n      \"done_checkpoint\": false,\n      \"invoke_dev_with\": \"…free-text planner→dev note, or ''…\"\n    },\n    \"sentinel\": {\n      \"kind\": \"unresolved\",\n      \"path\": \"...\u002Fstories\u002F6-4-cli-list-command-unresolved.md\",\n      \"blocking_condition\": \"…the reason planning halted…\"\n    }\n  }\n}\n```\n\nThe `sentinel` sub-block is present ONLY when the escalated story is a **sentinel**\n(see the stories-mode section below); an ordinary escalation omits it.\n\nYour **output marker** is the file at `resolution_path`. Writing it is the LAST\naction of a successful resolution. Schema:\n\n```json\n{\n  \"story_key\": \"\u003Ckey>\",\n  \"decision\": \"\u003Cone or two sentences: the rule you and the human chose>\",\n  \"spec_file\": \"\u003Cthe spec you edited>\",\n  \"spec_updated\": true,\n  \"restore_patch\": \"\u003Coptional: path to a saved intent-gap patch to re-apply>\"\n}\n```\n\n`restore_patch` is **optional** and used only for the intent-gap patch-restore\ncase below — omit it entirely for an ordinary resolution.\n\n## What you MUST do\n\n1. **Read the context**, then read the **frozen spec** at `spec_file` in full —\n   especially its `\u003Cfrozen-after-approval>` block (the intent the dev\u002Freview\n   sessions treat as authoritative). The escalation is almost always that this\n   block is silent on, or contradicts, a case the implementation hit.\n2. **Present the escalation plainly** to the human: what is ambiguous or\n   contradictory, why it blocks safe implementation, and **2–4 concrete\n   resolution options** with a clear recommendation and its trade-offs. Keep it\n   tight — quote the relevant spec lines.\n3. **Get the human's decision.** Ask follow-ups if the choice is unclear. Do not\n   invent requirements; if the human is unsure, help them reason, don't guess.\n4. **Update the frozen spec** to encode the decision unambiguously: amend the\n   `\u003Cfrozen-after-approval>` block and any affected acceptance criteria \u002F test\n   matrix rows so a fresh dev session has exactly one correct reading. Make the\n   smallest change that removes the ambiguity. You MAY use the `bmad-spec` or\n   `bmad-correct-course` skills if a larger spec change is warranted.\n5. **Write the resolution marker** at `resolution_path` (schema above), then tell\n   the human the resolution is recorded and they can exit this session — the\n   orchestrator will offer to **re-arm the story and resume the run** (a clean\n   rebuild against the corrected spec).\n\n## Special case: a review-stage `intent gap` with a saved patch\n\nWhen the escalation came from the **review step** halting on an `intent gap`, the\ndev session first **saved its attempted change as a patch file** (in the\nimplementation-artifacts folder) before reverting the tree — the escalation\n`detail` and the spec's `## Review Triage Log` reference the patch path. That\npatch is concrete evidence: it shows exactly which reading of the intent the run\nimplemented.\n\n**First check `restore_supported` in the context file.** When it is `false`\n(worktree-isolation runs: the re-drive discards and re-mounts the unit's\nworktree, so an in-place restore can never land; an escalation with no recorded\nspec: a restored patch has no review to resume; a pre-planning sentinel wedge:\nthere is no attempted implementation to restore), **never offer the restore\noption and never record `restore_patch`** — the orchestrator would reject the\nresolution and this whole session's negotiation would be wasted. The patch is\nstill available as evidence.\n\nUse the patch two ways:\n\n- **As evidence.** Read the patch (and the diff it represents) to see what the\n  guessed reading produced — often clearer input for writing the clarification\n  than the questions alone.\n- **When the attempted reading was actually correct.** Sometimes the run's guess\n  is the right one and only the _intent_ was silent. Present this as an explicit\n  option to the human: _\"the implementation read it as X, which is in fact what we\n  want — amend the intent to say X, and resume **review** on the already-written\n  change instead of re-implementing it.\"_ If the human chooses this:\n  1. Still **amend the intent** in the spec so it unambiguously says X (step 4\n     above is unchanged — the frozen intent must match the restored code).\n  2. Add **`\"restore_patch\": \"\u003Cthe saved patch path>\"`** to `resolution.json`\n     (copy the path verbatim from the escalation detail \u002F triage log).\n\n  The orchestrator then re-arms the spec to `in-review`, re-applies the patch onto\n  the baseline, and re-dispatches — the session resumes at the review step on the\n  restored diff. **Do NOT `git apply` the patch yourself and do NOT set the spec\n  status** — the orchestrator does both deterministically at re-arm.\n\n  **The restore must not overlap resolution commits.** Re-arm advances the\n  re-drive's baseline to the branch's post-resolve HEAD, but the saved patch was\n  diffed from the ORIGINAL baseline — so if this session left commits that touch\n  the patch's own files, the restore's `git apply` fails and the story\n  re-escalates (loudly, by design: the orchestrator never silently merges the\n  resolution with the stale attempt). If the resolution work already includes or\n  supersedes the attempted change, **omit `restore_patch`** — the commits survive\n  re-arm as the re-drive's starting point, so a from-scratch re-drive builds\n  directly on them.\n\nIf the attempted reading was wrong (the common case), omit `restore_patch`\nentirely: the orchestrator re-drives from scratch against the corrected intent.\n\n## What you MUST NOT do\n\n- **Do NOT** write the orchestrator's `result.json` — that is a dev\u002Freview\n  artifact; this is not one of those sessions.\n- **Do NOT** change `sprint-status.yaml`, and **do NOT** set the spec's `status:`\n  field — the orchestrator deterministically re-arms the spec status on resume.\n  Edit spec **content** only.\n- **Do NOT** implement the story, write feature code, run tests, or commit. Your\n  job ends at a corrected spec + the resolution marker.\n- **Do NOT** widen scope. Resolve exactly the escalated ambiguity; if you notice\n  unrelated problems, note them to the human but leave them alone.\n\n## Stories mode: sentinels and the preserved copy\n\nIn stories mode a story that could not even be **planned** — the dev session hit\na contradiction or gap before it could write a real spec — leaves a fixed-slug\n**sentinel** file instead of a frozen spec: `\u003Cid>-unresolved.md` (the intent was\ntoo ambiguous to plan) or `\u003Cid>-ambiguous.md` (more than one story spec matched\nthe id). The context's `stories.sentinel` block names it and carries the\n`blocking_condition` the session recorded.\n\nA sentinel is **not a spec you edit** — there is no plan or `\u003Cfrozen-after-approval>`\nblock inside it. So for a sentinel:\n\n- **Do not try to amend a frozen spec** (step 4's \"edit the frozen spec\" does not\n  apply — there isn't one). Instead resolve the _upstream_ ambiguity so a fresh\n  planning pass can succeed: usually that means clarifying `SPEC.md` (the epic\n  spec) or this story's entry in `stories.yaml` — the `title` \u002F `description` \u002F\n  `invoke_dev_with` the planner reads — with the human.\n- On **re-arm** the orchestrator does NOT flip the sentinel to `ready-for-dev`\n  (there is no plan to route to). It **preserves a copy** of the sentinel under\n  `{run}\u002Fsentinels\u002F\u003Cid>-\u003Ckind>.md` as a breadcrumb, **deletes** the sentinel, and\n  the next dispatch re-plans the story from scratch (leg 1 again for a\n  `spec_checkpoint` story). You do not touch the sentinel file yourself.\n- Write the resolution marker as usual once the human has decided how to\n  disambiguate; set `spec_file` to whatever you edited (e.g. `SPEC.md`), or omit\n  it if the fix was entirely in `stories.yaml`.\n\n### Not a sentinel: more than one file matches the id\n\nDistinct from the single-file `\u003Cid>-ambiguous.md` sentinel above: when **more\nthan one** file in `stories\u002F` matches `\u003Cid>-*.md` (say `3-login.md` AND\n`3-signup.md`), the id itself is ambiguous _on disk_ and the orchestrator wedges\nthe story without picking either file. You can recognize this state by the\nescalation reason (`ambiguous story file match: \u003Cnames>`) and by what the\ncontext does NOT have: no `stories.sentinel` block and no single spec path.\n\nThe auto-clear above does **not** apply — there is no sentinel to preserve and\ndelete, and re-arming alone just re-wedges on the same duplicates. The\nresolution IS the cleanup: with the human, decide which file is the story's real\nspec and remove or rename the other (merge content first if both carry real\nwork; renaming must move it out of the `\u003Cid>-*` pattern or to another id).\nExactly one match re-dispatches that spec; zero matches re-plans from scratch.\nThen write the resolution marker as usual — re-arm + resume takes it from there.\n\n## If you cannot resolve it\n\nIf the human defers, the information needed is genuinely unavailable, or the\nright fix is out of scope for a spec edit (e.g. it needs a PRD\u002Farchitecture\nchange), say so plainly and **do not** write the resolution marker. Exiting\nwithout the marker leaves the story escalated and the run paused — the safe\ndefault. The orchestrator will not re-arm a story with no recorded resolution.\n",{"name":5,"description":7},"main","5d8b301b16a0b47e4c97f8c6d68ad82e0f86be2c",".agent\u002Fskills\u002Fbmad-loop-resolve",0,"https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design","https:\u002F\u002Fgithub.com\u002FOrigoStudio","Engineering ideas into products","2026-10-23 00:02:46",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add OrigoStudio\u002Forigo-design --skill bmad-loop-resolve",{"tool":38,"command":39},"bunx","bunx skills add OrigoStudio\u002Forigo-design --skill bmad-loop-resolve",{"tool":41,"command":42},"pnpm","pnpm dlx skills add OrigoStudio\u002Forigo-design --skill bmad-loop-resolve","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-loop-resolve\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M79PWH7HW9TE5FTCHJ1W968C","wds-agent-saga-analyst","Strategic business analyst and product discovery partner for WDS. Use when the user asks to talk to Saga or requests the WDS analyst.","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-agent-saga-analyst\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M79PWF5EAQTMC3XZBEFGP3HW","wds-agent-mimir-builder","Implementation agent. Owns the tech audit, the PRD, and the build. Reads Freya's Work Orders and turns them into working code — one verified task at a time.","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-agent-mimir-builder\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M79PWCR1845ETM01V6SKVDMN","wds-agent-freya-ux","Strategic UX designer and design thinking partner for WDS. Use when the user asks to talk to Freya or requests the WDS designer.","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-agent-freya-ux\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M79PW9MEM3299WHP4DN0AS46","wds-8-product-evolution","Brownfield improvements — the full WDS pipeline in miniature for existing products","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-8-product-evolution\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M79PW81V0VQJJP0A9A47WR8N","wds-7-design-system","Create, import, browse, and maintain design system components and tokens","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-7-design-system\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M79PW550F0KPHSWF5Z8Z529B","wds-6-asset-generation","Generate visual and text assets from specifications through AI-powered creative production","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-6-asset-generation\u002FSKILL.md",[],[]]