[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71EPMY99VPGASFNHR2RC68K":3,"skill-same:01M71EPMY99VPGASFNHR2RC68K":56},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M71EPMY99VPGASFNHR2RC68K","swarm",null,"Fan out N parallel workers, drain them, and return one report. Use for \u002Fswarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.","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\u002Fswarm\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28],"report","parallel","coverage","use","workers","exploration","drain","for","fan out","one","2026-11-10 10:12:30",false,"---\nname: swarm\ndescription: \"Fan out N parallel workers, drain them, and return one report. Use for \u002Fswarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.\"\n---\n\n# Swarm\n\nOn Codex, read the [platform mapping](..\u002Fpatina-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fpatina-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\n\nFan out N parallel workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.\n\n## Start\n\nOpen a todolist with one entry per phase before launching anything.\n\n1. Frame\n2. Fan out\n3. Aggregate\n4. Report\n\n## Phase A: Frame\n\n1. State the done predicate and the artifact or report the swarm must return.\n2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare `first pass`, `rank all`, or `best-of` before spawning.\n3. Set N from the user or derive it from the shape. N is total workers, not the number that run at once.\n4. Pick the worker model from the `swarm workers` line in `pstack-models.md`. If the sheet or that line is missing, use the default in [Models](#models). For `auto` or `inherit-parent`, omit `model` so the workers run on the parent model. If the `Agent` tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. For a model race, name each arm's model up front.\n5. Give each worker its own writable output when it writes. When workers verify or measure commits, each brief names the exact SHAs. A measurement brief also names the method (sample count, what one sample is, order). The worker records both in its result.\n\n## Phase B: Fan out\n\nSpawn all N workers in one message with `subagent_type: \"patina-reader\"` for a worker whose brief writes nothing (coverage, review, exploration) and `subagent_type: \"general-purpose\"` for a worker that writes to its own worktree or output directory, `run_in_background: true`, and the step 4 model, left unset for `auto` or `inherit-parent`. Claude Code subagents all run on this machine, so isolation comes from the worktree or output directory assigned in Phase A, not from a remote environment.\n\nWhen a worker must start from a non-default branch, check that branch out in the worker's own worktree and name the worktree path in its brief.\n\nEvery brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use `PASS`, `ISSUES`, or `BLOCKED` with evidence. A worker that can prove a defect reports `ISSUES` and lists every issue it can prove, not only the first.\n\nIf a worker drops out, proceed with N-1 and note it.\n\n## Phase C: Aggregate\n\nRead the terminal results. Drop a result that does not record the SHAs and method its brief names, and respawn that worker once. After a second miss, record a gap. A gap does not count as a pass. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.\n\nKeep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.\n\n## Phase D: Report\n\nReturn one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.\n\n## Models\n\nRole defaults, stamped from `plugins\u002Fpstack\u002Fmodels.json` (edit there, rerun `tools\u002Fgenerate.mjs`). A matching role line in the `pstack-models.md` override sheet overrides each at runtime; `\u002Fsetup-pstack` writes it and lists its path per runtime.\n\n- swarm workers: `opus`\n\n## Reasoning effort\n\nA role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. `session` sets no effort, so the dispatch is the usual one. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. On Claude Code, a level picks the effort agent from the `subagent_type` you would otherwise use. `patina-agent` becomes `subagent_type: \"patina-agent-\u003Clevel>\"`. `patina-reader` becomes `subagent_type: \"patina-reader-\u003Clevel>\"`. `general-purpose`, or no `subagent_type`, becomes `subagent_type: \"effort-\u003Clevel>\"`. The effort agents set only `effort`, so the model you pass still decides the model. On Codex, pass the level as `spawn_agent`'s `reasoning_effort` and keep the usual instructions.\n","# Swarm\n\nOn Codex, read the [platform mapping](..\u002Fpatina-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fpatina-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\n\nFan out N parallel workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.\n\n## Start\n\nOpen a todolist with one entry per phase before launching anything.\n\n1. Frame\n2. Fan out\n3. Aggregate\n4. Report\n\n## Phase A: Frame\n\n1. State the done predicate and the artifact or report the swarm must return.\n2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare `first pass`, `rank all`, or `best-of` before spawning.\n3. Set N from the user or derive it from the shape. N is total workers, not the number that run at once.\n4. Pick the worker model from the `swarm workers` line in `pstack-models.md`. If the sheet or that line is missing, use the default in [Models](#models). For `auto` or `inherit-parent`, omit `model` so the workers run on the parent model. If the `Agent` tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. For a model race, name each arm's model up front.\n5. Give each worker its own writable output when it writes. When workers verify or measure commits, each brief names the exact SHAs. A measurement brief also names the method (sample count, what one sample is, order). The worker records both in its result.\n\n## Phase B: Fan out\n\nSpawn all N workers in one message with `subagent_type: \"patina-reader\"` for a worker whose brief writes nothing (coverage, review, exploration) and `subagent_type: \"general-purpose\"` for a worker that writes to its own worktree or output directory, `run_in_background: true`, and the step 4 model, left unset for `auto` or `inherit-parent`. Claude Code subagents all run on this machine, so isolation comes from the worktree or output directory assigned in Phase A, not from a remote environment.\n\nWhen a worker must start from a non-default branch, check that branch out in the worker's own worktree and name the worktree path in its brief.\n\nEvery brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use `PASS`, `ISSUES`, or `BLOCKED` with evidence. A worker that can prove a defect reports `ISSUES` and lists every issue it can prove, not only the first.\n\nIf a worker drops out, proceed with N-1 and note it.\n\n## Phase C: Aggregate\n\nRead the terminal results. Drop a result that does not record the SHAs and method its brief names, and respawn that worker once. After a second miss, record a gap. A gap does not count as a pass. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.\n\nKeep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.\n\n## Phase D: Report\n\nReturn one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.\n\n## Models\n\nRole defaults, stamped from `plugins\u002Fpstack\u002Fmodels.json` (edit there, rerun `tools\u002Fgenerate.mjs`). A matching role line in the `pstack-models.md` override sheet overrides each at runtime; `\u002Fsetup-pstack` writes it and lists its path per runtime.\n\n- swarm workers: `opus`\n\n## Reasoning effort\n\nA role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. `session` sets no effort, so the dispatch is the usual one. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. On Claude Code, a level picks the effort agent from the `subagent_type` you would otherwise use. `patina-agent` becomes `subagent_type: \"patina-agent-\u003Clevel>\"`. `patina-reader` becomes `subagent_type: \"patina-reader-\u003Clevel>\"`. `general-purpose`, or no `subagent_type`, becomes `subagent_type: \"effort-\u003Clevel>\"`. The effort agents set only `effort`, so the model you pass still decides the model. On Codex, pass the level as `spawn_agent`'s `reasoning_effort` and keep the usual instructions.\n",{"name":5,"description":7},"main","e6ee720f466a8344a52abd87679191fadde3b63f","plugins\u002Fcode\u002Fskills\u002Fswarm","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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add patinaproject\u002Fskills --skill swarm",{"tool":48,"command":49},"bunx","bunx skills add patinaproject\u002Fskills --skill swarm",{"tool":51,"command":52},"pnpm","pnpm dlx skills add patinaproject\u002Fskills --skill swarm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fswarm\u002FSKILL.md",true,[],[57,65,94,106,128,152],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":64},"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":81,"publishedAt":29},"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",[71,76],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[26,82,83,84,85,86,87,88,89,22,90,91,92,93],"pstack","writing","writing for pstack","review","run","mode","write","operator","tighten","prompt","when","revise",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":102,"publishedAt":29},"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",[100,101],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},[103,26,83,104,22,105,92],"writing for agents","editing","documents",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":29},"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",[],[108,113,114,115,28,116,92,117,118,119,120,121,22,122,123,124,26,125,126,127],"interactive","can","credentials","Bash","invoke","dashboard","generate","human","secrets","provisioning infrastructure","ci","up","setting","running","only",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":29},"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",[],[130,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,114,151,28],"more","true","decision","session","time","chunk","as","shared","map","tickets","destination","at","tracker","plan","work","agent session","one at a time",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":29},"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",[],[159,160,161,162,163,164,165,166,136,167],"wait","wait what","stop","it","land","re","pitch","message","last"]