[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79RHBGRW17291QQ8ZNAT0HT":3,"skill-same:01M79RHBGRW17291QQ8ZNAT0HT":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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79RHBGRW17291QQ8ZNAT0HT","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.","thkennedy\u002Ftk-studio","thkennedy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4164502?v=4","01M79QZ8DMP5FF2HC6GS3S6FDF","Tim Kennedy","01M79QZ8EM9JBWJ15R5JNC4PW3",0,"MIT","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fapps\u002Fsupervisor\u002F.claude\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","ecd23b3c0458cd511812f643d9111e3d7c8235f4","apps\u002Fsupervisor\u002F.claude\u002Fskills\u002Fbmad-loop-resolve","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio","https:\u002F\u002Fgithub.com\u002Fthkennedy","https:\u002F\u002Ftimothyhkennedy.com","Just a guy who loves making tools, automation and games.","2026-11-10 20:38:16",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add thkennedy\u002Ftk-studio --skill bmad-loop-resolve",{"tool":38,"command":39},"bunx","bunx skills add thkennedy\u002Ftk-studio --skill bmad-loop-resolve",{"tool":41,"command":42},"pnpm","pnpm dlx skills add thkennedy\u002Ftk-studio --skill bmad-loop-resolve","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fapps\u002Fsupervisor\u002F.claude\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},"01M79RYSQ8C3MWDFTDSRAYFJYA","tk-studio-track","Tracking verbs on the bound Jira project — `block` moves a story the loop cannot progress, and each dependent story, to \"Blocked - Awaiting User\" with a comment that @mentions the owner (or, with `--engagement`, one engagement's questions issue, which `close` later moves to \"Done\"); `reply` posts the owner's answer (or \"Done.\") with the owner's host-only token and moves the issue to \"Block Resolved\"; `validate` checks that resolution and passes the issue back to work or re-blocks it with a follow-up. Use when the user says \"block this story\", \"tk track block\", \"put it in the owner's inbox\", \"reply to the blocked issue\", \"validate the resolution\", or a supervisor or engagement payload names this skill.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-track\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},"01M79RYMVE0031EV5B64MBGD8V","tk-studio-session","Session discipline as a surface — land a boundary handoff (optionally carrying knowledge deltas) and end the session, or resume a fresh session from a run workspace alone. Use when the user says \"hand off this run\", \"tk session\", \"resume the run\", or a boundary\u002Fbudget trigger says the session must split.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-session\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},"01M79RYFM9ATWHM6HAXJ3D19WV","tk-studio-research","Run a chartered research pass — survey the topics a charter scopes, grade every finding by evidence, land the findings in the run workspace, and emit observation events for recommendation-worthy ones. Use when the user says \"run the ecosystem watch\", \"tk research\", or a research job's invoke-skill directive names this skill.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-research\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},"01M79RYA1AWZZF83KBHGR6JDN3","tk-studio-report","One-verb human defect report — \"the skill did the wrong thing\" — recorded as a report event in the local measurement ledger. Use when the user says \"tk report\", \"report a defect\", \"that skill misbehaved\", or \"log a studio issue\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-report\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},"01M79RY33VMYR5YNPVFKWRNW9S","tk-studio-playable-judge","The playable-verify leg's screenshot judge (Story 34.3) — reads only a playable run's report.json and its frames, answers the fixed rubric (scene loaded, player visible and framed, no magenta or error overlay, HUD reads, the named moments shown) with pass or fail and findings each naming a frame and a rubric line. Driven headless by the supervisor's host leg on the project's sandbox tier; use when the payload names a playable `media` folder, or the user says \"judge the playable frames\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-playable-judge\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},"01M79RXY4AM8JM6ZK2MAR3W3X2","tk-studio-plan-sync","Planning adapter — canonicalize BMad-native planning artifacts (normalize pass, sole id authority) and sync them with the bound planning backend. Use when the user says \"sync the plan\", \"normalize planning artifacts\", \"tk plan sync\", or after stock BMad planning flows produce or change epics\u002Fstories.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-plan-sync\u002FSKILL.md",[],[]]