[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71EMCE9KK4K8DVVRDG6YNJ5":3,"skill-same:01M71EMCE9KK4K8DVVRDG6YNJ5":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M71EMCE9KK4K8DVVRDG6YNJ5","move-session-here",null,"Ingest a Claude Code, Codex, or T3 Code conversation by thread or session ID and continue it in the current chat. Use when the user asks to move, load, absorb, hand off, or pick up one specific agent session here.","patinaproject\u002Fskills","patinaproject","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F229996889?v=4","01M71E58JKTDNY1138WYZK44TR","Patina Project","01M71E58K5GH4K16MV6A8BQ6NZ",1,"MIT","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fmove-session-here\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"move session here","session","move session","move","chat","one","agent session","when","thread","load","hand","id","codex","conversation","ingest","up","use","pick","continue","code","2026-11-10 10:12:30",false,"---\nname: move-session-here\ndescription: Ingest a Claude Code, Codex, or T3 Code conversation by thread or session ID and continue it in the current chat. Use when the user asks to move, load, absorb, hand off, or pick up one specific agent session here.\n---\n\n# Move a session here\n\nTurn one stored Claude Code or Codex transcript into working context for this\nchat. Resolve a T3 Code thread to its provider transcript when needed. This is\nan ingestion workflow. Preserve the stored database, WAL, and transcript content.\n\n```text\n\u002Fmove-session-here 9e362a1e-b606-4d60-b3fa-4b6a03d2fcf1\n\u002Fmove-session-here codex:\u002F\u002Fthreads\u002F019a1111-2222-7333-8444-555555555555\n\u002Fmove-session-here t3:\u002F\u002Fthreads\u002F11111111-1111-4111-8111-111111111111\n```\n\nRequire exactly one Claude session ID, Codex thread deeplink, or T3 Code thread\ndeeplink. A bare ID means Claude. A `codex:\u002F\u002Fthreads\u002F\u003Cid>` deeplink means Codex.\nA `t3:\u002F\u002Fthreads\u002F\u003Cid>` deeplink means T3 Code. Translate a natural-language\nrequest that names a T3 Code thread ID to the T3 Code form.\n\n## Extract the session\n\nResolve `\u003Cskill-directory>` to this skill's installed directory. Create two\ntemporary files, then run:\n\n```sh\nhandoff_path=\"$(mktemp \"${TMPDIR:-\u002Ftmp}\u002Fmove-session-here.XXXXXX\")\"\nhandoff_error_path=\"$(mktemp \"${TMPDIR:-\u002Ftmp}\u002Fmove-session-here-error.XXXXXX\")\"\nnode \u003Cskill-directory>\u002Fscripts\u002Fsession-handoff.mjs \\\n  '\u003Csession-reference>' >\"$handoff_path\" 2>\"$handoff_error_path\"\n```\n\nThe helper enumerates directory-guarded config homes with `find`, including\n`CLAUDE_CONFIG_DIR`, `CODEX_HOME`, `~\u002F.claude*`, and `~\u002F.codex*`. It normalizes\nthe owning transcript and any Claude subagent sidecars into one JSON document.\nIt scopes Codex lookup to `sessions\u002F**\u002Frollout-*.jsonl`.\n\nFor a T3 Code reference, use a current upstream SQLite CLI (3.33.0 or later,\nwith `-json` support) as `sqlite3` on `PATH`. The helper queries `~\u002F.t3\u002Fuserdata\u002Fstate.sqlite` in one read-only\ntransaction and resolves its exact provider binding. Set `T3_STATE_DB`\nto an absolute regular file to use one custom state database instead. The\nhelper does not scan other T3 stores. It keeps the T3 thread ID and database\npath under `t3`; `format` and `sessionId` still identify the provider transcript.\nSome bundled macOS SQLite builds cannot read a WAL-mode database when its\nsidecars are absent. On macOS, install upstream SQLite with `brew install sqlite`\nand prepend `$(brew --prefix sqlite)\u002Fbin` to `PATH` for the handoff command.\nA version number alone does not establish that a vendor build supports this case.\n\nQuery output is limited to 1 MiB; oversized mappings return `invalid_t3_store`.\nSQLite may create an empty `-wal` file and create or update the database's\n`-shm` WAL index and locking state. The helper leaves that shared bookkeeping\nto SQLite and never checkpoints,\nmigrates, or writes stored database, WAL, or transcript content.\n\nOn a nonzero exit, read the JSON error and stop:\n\n- `not_found` means report the ID and every `searchedHomes` entry.\n- `ambiguous_session` means report every match and ask for a unique source.\n- `t3_store_not_found` or `t3_mapping_not_found` means report the T3 thread and\n  database path.\n- `t3_sqlite_unavailable` means install the SQLite CLI and check `PATH`.\n- `t3_stale_binding` means the mapped provider transcript is missing.\n- `t3_mapping_ambiguous` or `t3_ambiguous_binding` means report the identifying\n  details and ask for one unambiguous source.\n- Any other error means report its code and identifying details.\n\nThe helper's result owns session identity. Do not replace it with substring\nsearch or pick a transcript that merely mentions the ID. Treat a Claude\n`bridgeSessionId` as provenance only. Native bridge and resume mechanisms do\nnot provide a cross-agent handoff.\n\n## Build the continuation brief\n\nRead the normalized document through the final event of every track. Process a\nlarge document in chronological chunks and carry one cumulative brief forward;\nskip no chunk. Tool calls show intent, while tool outputs and later messages\nshow what happened. Prefer the later evidence when they disagree.\n\nBuild one private continuation brief with all of these fields:\n\n- Source format, provider session ID, transcript paths, cwd, branch, and model.\n- T3 Code thread ID and database path when the result contains `t3`.\n- The user's goal and explicit constraints.\n- Decisions already made and their recorded rationale.\n- Files and other artifacts read, changed, created, or proposed, with their\n  last known state.\n- Commands, tests, and external operations already run, with outcomes.\n- Failed approaches, unresolved risks, blockers, and open questions.\n- Active skills, plugins, MCP tools, and subagent findings that affect the work.\n- The last completed step and the single next action.\n\nSeparate transcript facts from your inferences. Resolve contradictions in favor\nof the latest direct result. Replace credentials and other secrets with\n`[redacted]` in anything you show or persist.\n\n## Reconcile live state and continue\n\nInspect the current cwd, branch, worktree status, and every artifact needed for\nthe next action. The transcript is historical evidence, not current state. Name\nany mismatch in the brief and follow the repository's workflow before changing\nbranches or files.\n\nTell the user the recovered goal, current state, and next action in a short\ncapsule. Then continue from that action without asking the user to restate the\nsession. Stop only for a real permission, product-decision, or safety boundary.\n\nRemove the two temporary files after the brief is established. Leave the T3\nstate database, its sidecars, and every source transcript in place. Do not clean\nup SQLite sidecars. Continue from the derived artifact without a native resume\ncommand.\n","# Move a session here\n\nTurn one stored Claude Code or Codex transcript into working context for this\nchat. Resolve a T3 Code thread to its provider transcript when needed. This is\nan ingestion workflow. Preserve the stored database, WAL, and transcript content.\n\n```text\n\u002Fmove-session-here 9e362a1e-b606-4d60-b3fa-4b6a03d2fcf1\n\u002Fmove-session-here codex:\u002F\u002Fthreads\u002F019a1111-2222-7333-8444-555555555555\n\u002Fmove-session-here t3:\u002F\u002Fthreads\u002F11111111-1111-4111-8111-111111111111\n```\n\nRequire exactly one Claude session ID, Codex thread deeplink, or T3 Code thread\ndeeplink. A bare ID means Claude. A `codex:\u002F\u002Fthreads\u002F\u003Cid>` deeplink means Codex.\nA `t3:\u002F\u002Fthreads\u002F\u003Cid>` deeplink means T3 Code. Translate a natural-language\nrequest that names a T3 Code thread ID to the T3 Code form.\n\n## Extract the session\n\nResolve `\u003Cskill-directory>` to this skill's installed directory. Create two\ntemporary files, then run:\n\n```sh\nhandoff_path=\"$(mktemp \"${TMPDIR:-\u002Ftmp}\u002Fmove-session-here.XXXXXX\")\"\nhandoff_error_path=\"$(mktemp \"${TMPDIR:-\u002Ftmp}\u002Fmove-session-here-error.XXXXXX\")\"\nnode \u003Cskill-directory>\u002Fscripts\u002Fsession-handoff.mjs \\\n  '\u003Csession-reference>' >\"$handoff_path\" 2>\"$handoff_error_path\"\n```\n\nThe helper enumerates directory-guarded config homes with `find`, including\n`CLAUDE_CONFIG_DIR`, `CODEX_HOME`, `~\u002F.claude*`, and `~\u002F.codex*`. It normalizes\nthe owning transcript and any Claude subagent sidecars into one JSON document.\nIt scopes Codex lookup to `sessions\u002F**\u002Frollout-*.jsonl`.\n\nFor a T3 Code reference, use a current upstream SQLite CLI (3.33.0 or later,\nwith `-json` support) as `sqlite3` on `PATH`. The helper queries `~\u002F.t3\u002Fuserdata\u002Fstate.sqlite` in one read-only\ntransaction and resolves its exact provider binding. Set `T3_STATE_DB`\nto an absolute regular file to use one custom state database instead. The\nhelper does not scan other T3 stores. It keeps the T3 thread ID and database\npath under `t3`; `format` and `sessionId` still identify the provider transcript.\nSome bundled macOS SQLite builds cannot read a WAL-mode database when its\nsidecars are absent. On macOS, install upstream SQLite with `brew install sqlite`\nand prepend `$(brew --prefix sqlite)\u002Fbin` to `PATH` for the handoff command.\nA version number alone does not establish that a vendor build supports this case.\n\nQuery output is limited to 1 MiB; oversized mappings return `invalid_t3_store`.\nSQLite may create an empty `-wal` file and create or update the database's\n`-shm` WAL index and locking state. The helper leaves that shared bookkeeping\nto SQLite and never checkpoints,\nmigrates, or writes stored database, WAL, or transcript content.\n\nOn a nonzero exit, read the JSON error and stop:\n\n- `not_found` means report the ID and every `searchedHomes` entry.\n- `ambiguous_session` means report every match and ask for a unique source.\n- `t3_store_not_found` or `t3_mapping_not_found` means report the T3 thread and\n  database path.\n- `t3_sqlite_unavailable` means install the SQLite CLI and check `PATH`.\n- `t3_stale_binding` means the mapped provider transcript is missing.\n- `t3_mapping_ambiguous` or `t3_ambiguous_binding` means report the identifying\n  details and ask for one unambiguous source.\n- Any other error means report its code and identifying details.\n\nThe helper's result owns session identity. Do not replace it with substring\nsearch or pick a transcript that merely mentions the ID. Treat a Claude\n`bridgeSessionId` as provenance only. Native bridge and resume mechanisms do\nnot provide a cross-agent handoff.\n\n## Build the continuation brief\n\nRead the normalized document through the final event of every track. Process a\nlarge document in chronological chunks and carry one cumulative brief forward;\nskip no chunk. Tool calls show intent, while tool outputs and later messages\nshow what happened. Prefer the later evidence when they disagree.\n\nBuild one private continuation brief with all of these fields:\n\n- Source format, provider session ID, transcript paths, cwd, branch, and model.\n- T3 Code thread ID and database path when the result contains `t3`.\n- The user's goal and explicit constraints.\n- Decisions already made and their recorded rationale.\n- Files and other artifacts read, changed, created, or proposed, with their\n  last known state.\n- Commands, tests, and external operations already run, with outcomes.\n- Failed approaches, unresolved risks, blockers, and open questions.\n- Active skills, plugins, MCP tools, and subagent findings that affect the work.\n- The last completed step and the single next action.\n\nSeparate transcript facts from your inferences. Resolve contradictions in favor\nof the latest direct result. Replace credentials and other secrets with\n`[redacted]` in anything you show or persist.\n\n## Reconcile live state and continue\n\nInspect the current cwd, branch, worktree status, and every artifact needed for\nthe next action. The transcript is historical evidence, not current state. Name\nany mismatch in the brief and follow the repository's workflow before changing\nbranches or files.\n\nTell the user the recovered goal, current state, and next action in a short\ncapsule. Then continue from that action without asking the user to restate the\nsession. Stop only for a real permission, product-decision, or safety boundary.\n\nRemove the two temporary files after the brief is established. Leave the T3\nstate database, its sidecars, and every source transcript in place. Do not clean\nup SQLite sidecars. Continue from the derived artifact without a native resume\ncommand.\n",{"name":5,"description":7},"main","e6ee720f466a8344a52abd87679191fadde3b63f","plugins\u002Fcode\u002Fskills\u002Fmove-session-here","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills","https:\u002F\u002Fgithub.com\u002Fpatinaproject","https:\u002F\u002Fwww.patinaproject.com","The best way to pick your next pair of boots or shoes.","2026-11-12 00:44:02",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add patinaproject\u002Fskills --skill move-session-here",{"tool":58,"command":59},"bunx","bunx skills add patinaproject\u002Fskills --skill move-session-here",{"tool":61,"command":62},"pnpm","pnpm dlx skills add patinaproject\u002Fskills --skill move-session-here","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fmove-session-here\u002FSKILL.md",true,[66,72],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"scripts\u002Fsession-handoff.mjs","SCRIPT","脚本",16265,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fmove-session-here\u002Fscripts\u002Fsession-handoff.mjs",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"scripts\u002Ft3-identity.mjs",7575,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fmove-session-here\u002Fscripts\u002Ft3-identity.mjs",[77,85,114,126,147,169],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":84},"01M72KDQJR99954NE224VB3KZ2","code-review","Review the changes since a fixed point (commit, branch, tag, or merge-base) along five axes: Standards (does the code follow this repo's documented coding standards?), Spec (does the code match what the originating issue\u002Fspec asked for?), Evidence (does each claim in the pull request have evidence that shows it?), Bugs (does the changed code have logic errors, unhandled states, races, or regressions?), and Security (does the change open injection, auth, secret, input, or CI workflow holes?). Runs the reviews in parallel sub-agents, tags every finding Important, Nit, or Pre-existing, and reports them side by side with what blocks merge. Given an earlier reviewed head and its findings, it reviews only the newer commits, rechecks the earlier findings, and never repeats one. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fcode-review\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":101,"publishedAt":39},"01M71ESEDVHD9EXN6787XHP7HD","writing-for-pstack","Write or tighten an operator prompt for a patina-mode run. Use when the operator asks to write, revise, or review a prompt that will be passed to patina-mode.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwriting-for-pstack\u002FSKILL.md",[91,96],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[102,103,104,105,106,107,108,109,110,35,111,112,26,113],"for","pstack","writing","writing for pstack","review","run","mode","write","operator","tighten","prompt","revise",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":122,"publishedAt":39},"01M71ESCJ0SSJFFENF8HYDKBTJ","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[120,121],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},[123,102,104,124,35,125,26],"writing for agents","editing","documents",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":39},"01M71ESA1NN9WVMD2HA5Z1RRDY","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwizard\u002FSKILL.md",[],[128,133,134,135,24,136,26,137,138,139,140,141,35,142,143,34,102,144,145,146],"interactive","can","credentials","Bash","invoke","dashboard","generate","human","secrets","provisioning infrastructure","ci","setting","running","only",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":39},"01M71ES8FAN567N3JEPG8W6AS1","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[149,154,155,156,20,157,158,159,160,161,162,163,164,165,166,167,25,134,168,24],"more","true","decision","time","chunk","as","shared","map","tickets","destination","at","tracker","plan","work","one at a time",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":39},"01M71ES6PWJPKBW8R24YFH4PY6","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[176,177,178,179,180,181,182,183,155,184],"wait","wait what","stop","it","land","re","pitch","message","last"]