[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AX3QM639GSJHJAAE6VCAT1":3,"skill-same:01M7AX3QM639GSJHJAAE6VCAT1":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7AX3QM639GSJHJAAE6VCAT1","theater-recover-tmux",null,"Recover Theater participants after a tmux server restart or kill-server using retained participant metadata, native session resume, and an explicitly chosen conservative recovery mode.","mana-byte\u002Ftheater","mana-byte","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F93316844?v=4","01M7AX1XSX6E0DJHN1SA4MEAJ3","01M7AX1XTJYZBKJH863Y7N1D61",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmana-byte\u002Ftheater\u002Fblob\u002Fmain\u002Ftheater\u002Fskills\u002Fbuiltin\u002Ftheater-recover-tmux\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: theater-recover-tmux\ndescription: Recover Theater participants after a tmux server restart or kill-server using retained participant metadata, native session resume, and an explicitly chosen conservative recovery mode.\n---\n\n# Theater Recover tmux\n\nUse this skill to diagnose or recover Theater participants after a tmux server restart or\n`kill-server`. This is a workflow over existing Theater tools, not tmux cleanup or native mutation.\n\n## Find the incident\n\nBegin with `list_participants(include_dead=True, limit=100)`. If a page is full, continue with the\nlast row's stable id as `after_id`; repeat with the same limit until all retained rows have been\nexamined. Do not use names: dead names are absent and recyclable.\n\nIgnore rows missing either required reset field—`termination_reason` or `termination_incident`—or\n`terminated_at`. Keep only rows with `termination_reason=\"tmux_restart\"`, then group them by\n`termination_incident`. Use the incident the user names; otherwise choose the group whose maximum\n`terminated_at` is newest. If no complete group exists, say that Theater has no retained tmux-restart\ncandidates and stop.\n\nShow a concise recovery plan before spawning. For every candidate, include its stable id, harness,\ncwd, branch, session_id, resume_state, and the incident id and time. State which rows are expected\nto resume, which need workspace-only review, and which will be skipped.\n\n## Choose recovery and approval\n\nIf the user did not specify a recovery mode, ask exactly once with the host harness's native\nstructured ask-user tool:\n\n1. Best effort (recommended)\n2. Review plan first\n3. Manual per participant\n\nIf the host has no native structured ask-user tool, ask the same question in the normal response and\nstop until the user answers. Do not infer a mode from silence.\n\nObtain one explicit approval choice—`manual`, `edits`, or `yolo`—before any spawn. Reuse a choice\nthe user already gave; otherwise ask once. Theater has no approval default: never invent one.\n\nIn review-plan-first mode, make no spawn until the user approves the shown plan. In manual-per-\nparticipant mode, confirm each candidate before acting on it. Best effort proceeds only within the\nlimits below.\n\n## Recover conservatively\n\nBest effort never deletes, resets, overwrites, kills, invokes GC, or alters worktrees or branches.\nIt neither recreates nor cleans up anything. It only attempts the retained participant context where\nthe current state permits it.\n\nBefore each attempted recovery, re-list that stable id with\n`list_participants(include_dead=True, ids=[id])`. Skip it if it is now live, owned by a live\nparticipant, missing, or its `resume_state` is no longer `resumable`; report the observed state.\n\nFor a resumable row, call `spawn_session` with:\n\n- `resume` set to the stable predecessor participant id;\n- the retained `cwd`;\n- `worktree=False`;\n- the same `harness` and the chosen `approval`.\n\nResume reuses the predecessor's workspace: never combine it with `worktree`. Pass the retained\n`cwd`; a THEATER-owned (named or unique) worktree is rejoined even while other participants share\nit. A path owned by any other non-borrowed workspace is refused with `path_already_owned`.\n\nDo not invent a model or reasoning effort. Pass `model` or `reasoning_effort` only when the row\nactually records that native value; otherwise omit the parameter. Do not change the retained branch\nor request a new worktree.\n\nFor every non-resumable row, explain its `resume_state` rather than claiming conversational recovery:\n`live` (still running), `no_session_id` (Theater has not recorded the harness session id),\n`harness_cannot_resume` (the adapter does not support resume), `untrusted` (transcript provenance\nis below operator-level), `owned_by_live` (a live participant holds the trusted session or claims\nthis predecessor as a recovery successor), `harness_resume_rejected` (the harness preflight refused\nthe session).\nWorkspace-only recovery can spawn a replacement auditor only when it is safe and the selected\nrecovery mode or user confirmation explicitly permits the fallback. Use the same retained harness and\ncwd with `worktree=False` unless the user explicitly chooses otherwise. Approval is execution policy,\nnot authorization for the fallback. Describe it as workspace review, not a resumed conversation; apply\nthe same duplicate check first.\n\nVerify every spawn using its returned record and, when needed, `list_participants`. Summarize each\ncandidate as recovered, skipped, or failed, with its stable predecessor id and the reason. Do not\nperform cleanup after the summary.\n","# Theater Recover tmux\n\nUse this skill to diagnose or recover Theater participants after a tmux server restart or\n`kill-server`. This is a workflow over existing Theater tools, not tmux cleanup or native mutation.\n\n## Find the incident\n\nBegin with `list_participants(include_dead=True, limit=100)`. If a page is full, continue with the\nlast row's stable id as `after_id`; repeat with the same limit until all retained rows have been\nexamined. Do not use names: dead names are absent and recyclable.\n\nIgnore rows missing either required reset field—`termination_reason` or `termination_incident`—or\n`terminated_at`. Keep only rows with `termination_reason=\"tmux_restart\"`, then group them by\n`termination_incident`. Use the incident the user names; otherwise choose the group whose maximum\n`terminated_at` is newest. If no complete group exists, say that Theater has no retained tmux-restart\ncandidates and stop.\n\nShow a concise recovery plan before spawning. For every candidate, include its stable id, harness,\ncwd, branch, session_id, resume_state, and the incident id and time. State which rows are expected\nto resume, which need workspace-only review, and which will be skipped.\n\n## Choose recovery and approval\n\nIf the user did not specify a recovery mode, ask exactly once with the host harness's native\nstructured ask-user tool:\n\n1. Best effort (recommended)\n2. Review plan first\n3. Manual per participant\n\nIf the host has no native structured ask-user tool, ask the same question in the normal response and\nstop until the user answers. Do not infer a mode from silence.\n\nObtain one explicit approval choice—`manual`, `edits`, or `yolo`—before any spawn. Reuse a choice\nthe user already gave; otherwise ask once. Theater has no approval default: never invent one.\n\nIn review-plan-first mode, make no spawn until the user approves the shown plan. In manual-per-\nparticipant mode, confirm each candidate before acting on it. Best effort proceeds only within the\nlimits below.\n\n## Recover conservatively\n\nBest effort never deletes, resets, overwrites, kills, invokes GC, or alters worktrees or branches.\nIt neither recreates nor cleans up anything. It only attempts the retained participant context where\nthe current state permits it.\n\nBefore each attempted recovery, re-list that stable id with\n`list_participants(include_dead=True, ids=[id])`. Skip it if it is now live, owned by a live\nparticipant, missing, or its `resume_state` is no longer `resumable`; report the observed state.\n\nFor a resumable row, call `spawn_session` with:\n\n- `resume` set to the stable predecessor participant id;\n- the retained `cwd`;\n- `worktree=False`;\n- the same `harness` and the chosen `approval`.\n\nResume reuses the predecessor's workspace: never combine it with `worktree`. Pass the retained\n`cwd`; a THEATER-owned (named or unique) worktree is rejoined even while other participants share\nit. A path owned by any other non-borrowed workspace is refused with `path_already_owned`.\n\nDo not invent a model or reasoning effort. Pass `model` or `reasoning_effort` only when the row\nactually records that native value; otherwise omit the parameter. Do not change the retained branch\nor request a new worktree.\n\nFor every non-resumable row, explain its `resume_state` rather than claiming conversational recovery:\n`live` (still running), `no_session_id` (Theater has not recorded the harness session id),\n`harness_cannot_resume` (the adapter does not support resume), `untrusted` (transcript provenance\nis below operator-level), `owned_by_live` (a live participant holds the trusted session or claims\nthis predecessor as a recovery successor), `harness_resume_rejected` (the harness preflight refused\nthe session).\nWorkspace-only recovery can spawn a replacement auditor only when it is safe and the selected\nrecovery mode or user confirmation explicitly permits the fallback. Use the same retained harness and\ncwd with `worktree=False` unless the user explicitly chooses otherwise. Approval is execution policy,\nnot authorization for the fallback. Describe it as workspace review, not a resumed conversation; apply\nthe same duplicate check first.\n\nVerify every spawn using its returned record and, when needed, `list_participants`. Summarize each\ncandidate as recovered, skipped, or failed, with its stable predecessor id and the reason. Do not\nperform cleanup after the summary.\n",{"name":5,"description":7},"main","8ff9aa9ce8393ccad496ed8806324b7b4b6c2314","theater\u002Fskills\u002Fbuiltin\u002Ftheater-recover-tmux",0,"https:\u002F\u002Fgithub.com\u002Fmana-byte\u002Ftheater","https:\u002F\u002Fgithub.com\u002Fmana-byte","Always learning","2026-11-14 20:40:25",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add mana-byte\u002Ftheater --skill theater-recover-tmux",{"tool":37,"command":38},"bunx","bunx skills add mana-byte\u002Ftheater --skill theater-recover-tmux",{"tool":40,"command":41},"pnpm","pnpm dlx skills add mana-byte\u002Ftheater --skill theater-recover-tmux","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmana-byte\u002Ftheater\u002Fblob\u002Fmain\u002Ftheater\u002Fskills\u002Fbuiltin\u002Ftheater-recover-tmux\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M7AX3M8JZ8FPRCP4F3CFWDN7","theater-delegate","Hand a scoped task to a suitable existing Theater peer, or start a builder and independent reviewer pair when the work needs one. Stay or run in the background as the user requested.","https:\u002F\u002Fgithub.com\u002Fmana-byte\u002Ftheater\u002Fblob\u002Fmain\u002Ftheater\u002Fskills\u002Fbuiltin\u002Ftheater-delegate\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M7AX3FDEF136J646DZWVW3K6","theater-debate","Debate a review, design, or architecture decision with one specified Theater participant when the user asks to debate with a harness, model, and reasoning effort. Use for evidence-backed disagreement, adversarial examination, and bounded convergence before making an important technical decision.","https:\u002F\u002Fgithub.com\u002Fmana-byte\u002Ftheater\u002Fblob\u002Fmain\u002Ftheater\u002Fskills\u002Fbuiltin\u002Ftheater-debate\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7AX3AEFDJHJJMVYTPF79P61","theater-configure","Configure or personalize Theater interactively when the user wants to set up, review, or change their Theater settings — favourite CLI, régie theme and behaviour, which models and thinking levels agents may use, plugin enablement, safety limits, retention, and observability. Use for a guided question-by-question walkthrough of config.toml that discovers what it can from the machine and asks the rest in plain language, including first-time setup on a new machine.","https:\u002F\u002Fgithub.com\u002Fmana-byte\u002Ftheater\u002Fblob\u002Fmain\u002Ftheater\u002Fskills\u002Fbuiltin\u002Ftheater-configure\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7AX36NADMJ5ZCAQC5T05ZM8","reviewer","Master of a pair play. Spawn one builder, review its work read-only, debate with evidence until you both agree, verify, and report. Attach this card when spawning a reviewer; never load it in your own chat.","https:\u002F\u002Fgithub.com\u002Fmana-byte\u002Ftheater\u002Fblob\u002Fmain\u002Ftheater\u002Fskills\u002Fbuiltin\u002Fpair\u002Freviewer\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7AX34K85MAFMSA3CV0X8RW2","builder","Builder in a pair play. Implement the brief in the shared worktree, defend your choices with evidence, and iterate with the reviewer until you both agree.","https:\u002F\u002Fgithub.com\u002Fmana-byte\u002Ftheater\u002Fblob\u002Fmain\u002Ftheater\u002Fskills\u002Fbuiltin\u002Fpair\u002Fbuilder\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7AX32XR0X6XDRXVK7FKYYN1","worker","Task role for a lead or member in a hierarchy play. Implement the assigned change inside the paths you own and report what you verified.","https:\u002F\u002Fgithub.com\u002Fmana-byte\u002Ftheater\u002Fblob\u002Fmain\u002Ftheater\u002Fmcp_plugins\u002Fbuiltin\u002Fbeads\u002Fskills\u002Fhierarchy\u002Fworker\u002FSKILL.md",[],[]]