[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDAPC5393RA3DTF3T079H4":3,"skill-same:01M7FDAPC5393RA3DTF3T079H4":45},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M7FDAPC5393RA3DTF3T079H4","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.","l246804\u002Fdsh-pstack","l246804","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F53589602?v=4","01M7FD2TFY24A2KKK55FSQWJ47","leihaohao","01M7FD2TGRS2ZCQ68BRY93D89D",23,"MIT","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fpstack\u002Fskills\u002Fswarm\u002FSKILL.md",[],[],"2026-11-16 10:05:34",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.\"\ndisable-model-invocation: true\n---\n\n# Swarm\n\nIn DeepSeek Harness, read [the DSH adapter](..\u002F..\u002Fdocs\u002Fharness\u002Fdsh.md) once per session before you follow this skill. It maps the Cursor names in pstack skills to DeepSeek Harness.\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. Pick the worker model from the `swarm workers` line in `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc`. If the rule or that line is missing, use `grok-4.7-xhigh-fast`. For `auto` or `inherit-parent`, omit `model` so the workers run on the parent model. If the Task 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. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **poteto-mode** skill.\n4. 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: generalPurpose`, `environment: \"cloud\"`, `run_in_background: true`, and the step 3 model, left unset for `auto` or `inherit-parent`. Use `environment: \"local\"` only when the worker needs access to something on the user's computer.\n\nWhen a worker must start from a non-default pushed branch, pass `cloud_base_branch`.\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\n## Phase D: Report\n\nReturn one consolidated in-chat report with a result table, issue one-liners, gaps or dropouts, and the race rule when used.\n","# Swarm\n\nIn DeepSeek Harness, read [the DSH adapter](..\u002F..\u002Fdocs\u002Fharness\u002Fdsh.md) once per session before you follow this skill. It maps the Cursor names in pstack skills to DeepSeek Harness.\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. Pick the worker model from the `swarm workers` line in `~\u002F.cursor\u002Frules\u002Fpstack-models.mdc`. If the rule or that line is missing, use `grok-4.7-xhigh-fast`. For `auto` or `inherit-parent`, omit `model` so the workers run on the parent model. If the Task 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. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **poteto-mode** skill.\n4. 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: generalPurpose`, `environment: \"cloud\"`, `run_in_background: true`, and the step 3 model, left unset for `auto` or `inherit-parent`. Use `environment: \"local\"` only when the worker needs access to something on the user's computer.\n\nWhen a worker must start from a non-default pushed branch, pass `cloud_base_branch`.\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\n## Phase D: Report\n\nReturn one consolidated in-chat report with a result table, issue one-liners, gaps or dropouts, and the race rule when used.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","df33da1bb4942fbd2761c305edb3785093ec1055","pstack\u002Fskills\u002Fswarm",4,"https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack","https:\u002F\u002Fgithub.com\u002Fl246804","2026-11-15 16:09:02",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add l246804\u002Fdsh-pstack --skill swarm",{"tool":38,"command":39},"bunx","bunx skills add l246804\u002Fdsh-pstack --skill swarm",{"tool":41,"command":42},"pnpm","pnpm dlx skills add l246804\u002Fdsh-pstack --skill swarm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fpstack\u002Fskills\u002Fswarm\u002FSKILL.md",[],[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":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7FDC7PA7ACJ95HW5T1N9ZJ3","setup-project-docs","Bootstrap architecture, glossary, decision-record conventions, and root agent-doc pointers; rerun to fill approved gaps.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fauthored\u002Fsetup-project-docs\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FDC35BXG4PW3HG16BXF5FG","docs-drift","Audit living project documentation for drift and redundancy; repair approved findings.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fauthored\u002Fdocs-drift\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7FDBZ7PP5T1V4Q1MEP95BGM","decision-write","Write, update, land, or supersede decision records. Use for resolved alternatives, missing rationale, reversed decisions, or record-file changes. Land finds and verifies the implementation; Review-only updates keep the current status.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fauthored\u002Fdecision-write\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FDBVXYSHCB2E52HKS2TH2E","decision-audit","Read-only audit of decision records for a PR, local changes, or the whole repository. Report routing, status, scope, anchor, supersession, and overdue-review findings with command evidence.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fauthored\u002Fdecision-audit\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7FDBSF0V6HTFHD5PHDC6BAM","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7FDBQPY2F8PSNJKTGZ6AYD6","retro","Conduct a retrospective on a coding session.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002F.agents\u002Fskills\u002Fretro\u002FSKILL.md",[],[]]