[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71SDCG15M4TCWCGNMXW7PR9":3,"skill-same:01M71SDCG15M4TCWCGNMXW7PR9":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M71SDCG15M4TCWCGNMXW7PR9","kanban",null,"Use when work has several deliverables, tickets, or delegates: board, WIP 1 writer + 2 review, pull rule, Definition of Done, findings fixed or filed.","iTestFlow\u002FiTestFlow-Agent","iTestFlow","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F302233930?v=4","01M71SCS4TBZ0X377TJ1RBJ3SM","01M71SCS5KSSDZXDRAT9R0FJKP",31,"MIT","https:\u002F\u002Fgithub.com\u002FiTestFlow\u002FiTestFlow-Agent\u002Fblob\u002Fmain\u002F.chaos-engine\u002Fskills\u002Fkanban\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"writer","pull","deliverables","work","definition","delegates","tickets","board","definition of done","use","rule","when","done","review","2026-11-10 13:02:02",false,"---\nname: kanban\ndescription: >-\n  Use when work has several deliverables, tickets, or delegates: board, WIP 1\n  writer + 2 review, pull rule, Definition of Done, findings fixed or filed.\nlicense: MIT\n---\n\n# Kanban task flow\n\nUse when work has more than one deliverable, more than one ticket, or any\ndelegate. Flow beats busyness: finish before starting.\n\n## Board\n\nKeep one board per task as JSON (models corrupt JSON less than prose) in the\nsession state directory, never in tracked files:\n\n```json\n{\"wip\": {\"doing\": 1, \"review\": 2},\n \"cards\": [{\"id\": \"T1\", \"title\": \"...\", \"column\": \"ready\",\n            \"acceptance\": [\"...\"], \"proof\": \"command that proves it\",\n            \"evidence\": null, \"pr\": null}]}\n```\n\nColumns: `backlog` -> `ready` -> `doing` -> `review` -> `done`.\n\n- `ready` requires acceptance criteria and a proof command. No criteria, no pull.\n- `doing` WIP **1 writer** per repository: one card being edited at a time.\n- `review` WIP **2**: at two cards waiting for review or CI, pull nothing new.\n- `done` only when the Definition of Done holds.\n\n## Pull rule\n\nEvery session, turn, and wake starts by draining right to left: open PRs and\n`review` (red or `ACTION_REQUIRED` checks, behind base, conflicts, review\ncomments, auto-merge off), then `doing`, then shipped bugs or red default\nbranch. Pull a new `ready` card only when nothing downstream is actionable, and\nonly while `review` has capacity; waiting on CI counts as idle. Never leave a\nstarted card to start another. Never push work forward. Group related cards\ninto the fewest safe pull requests. Avoid PRs that depend on other open PRs;\nland them in order and merge base once before the final push.\n\n## Definition of Done\n\nA card is done when all hold:\n\n1. Every acceptance criterion is met and its proof command output is attached.\n2. Tests for new behavior were red first, then green.\n3. One fresh-context review is clean; a second round only for blocker findings.\n4. Required checks are green on the exact head after one blocking wait per push\n   (`gh pr checks --watch --fail-fast` or `gh run watch`); retry once, then stop\n   and report. Never re-verify what already passed.\n5. Every finding raised while working is closed (see below), including\n   static-analysis and code-quality review threads (fix or reply, then resolve)\n   before the PR counts as ready.\n6. Merged or handed off as instructed; worktree cleaned.\n7. After any CE harness change merges, every agent and delegate reloads the\n   latest harness from main before continuing. After each completed delivery\n   run `python3 .chaos-engine\u002Ftool.py maintain` (fast-forward with local edits\n   kept, reinstall, doctor, stale-store refresh, reload).\n8. Ship to-deliver items in the fewest pull requests; group related issues.\n\nCheck items 2 and 4 plus labels and links with `python3 .chaos-engine\u002Ftool.py dod \u003CPR>` ([`dod.py`](..\u002F..\u002Fdod.py))\n(table; exit 1 names each gap).\n\n## Findings policy\n\nEvery finding ends as exactly one of:\n\n- **fixed** in the current delivery, or\n- **filed** as an issue, allowed only when it is both outside the task's scope\n  and not critical, blocker, or high severity.\n\nNothing stays only in chat, a report, or a local file. The final report lists\neach finding as fixed (with PR) or filed (with issue).\n\n## Waste checklist\n\nBefore each pull, drop anything that is partially done work, extra process,\nextra features, task switching, waiting, handoffs without context, or defects\npassed downstream (Poppendieck's seven wastes).\n\n## Status\n\nEvery status report is a Markdown table, one row per card\n(`ID | Issue(s) | PR | Status | Proof or blocker`), then Risks. Never prose or\nbullet lists. No separate status rituals. Report only rows that changed since\nthe last report; say nothing when nothing changed.\n","# Kanban task flow\n\nUse when work has more than one deliverable, more than one ticket, or any\ndelegate. Flow beats busyness: finish before starting.\n\n## Board\n\nKeep one board per task as JSON (models corrupt JSON less than prose) in the\nsession state directory, never in tracked files:\n\n```json\n{\"wip\": {\"doing\": 1, \"review\": 2},\n \"cards\": [{\"id\": \"T1\", \"title\": \"...\", \"column\": \"ready\",\n            \"acceptance\": [\"...\"], \"proof\": \"command that proves it\",\n            \"evidence\": null, \"pr\": null}]}\n```\n\nColumns: `backlog` -> `ready` -> `doing` -> `review` -> `done`.\n\n- `ready` requires acceptance criteria and a proof command. No criteria, no pull.\n- `doing` WIP **1 writer** per repository: one card being edited at a time.\n- `review` WIP **2**: at two cards waiting for review or CI, pull nothing new.\n- `done` only when the Definition of Done holds.\n\n## Pull rule\n\nEvery session, turn, and wake starts by draining right to left: open PRs and\n`review` (red or `ACTION_REQUIRED` checks, behind base, conflicts, review\ncomments, auto-merge off), then `doing`, then shipped bugs or red default\nbranch. Pull a new `ready` card only when nothing downstream is actionable, and\nonly while `review` has capacity; waiting on CI counts as idle. Never leave a\nstarted card to start another. Never push work forward. Group related cards\ninto the fewest safe pull requests. Avoid PRs that depend on other open PRs;\nland them in order and merge base once before the final push.\n\n## Definition of Done\n\nA card is done when all hold:\n\n1. Every acceptance criterion is met and its proof command output is attached.\n2. Tests for new behavior were red first, then green.\n3. One fresh-context review is clean; a second round only for blocker findings.\n4. Required checks are green on the exact head after one blocking wait per push\n   (`gh pr checks --watch --fail-fast` or `gh run watch`); retry once, then stop\n   and report. Never re-verify what already passed.\n5. Every finding raised while working is closed (see below), including\n   static-analysis and code-quality review threads (fix or reply, then resolve)\n   before the PR counts as ready.\n6. Merged or handed off as instructed; worktree cleaned.\n7. After any CE harness change merges, every agent and delegate reloads the\n   latest harness from main before continuing. After each completed delivery\n   run `python3 .chaos-engine\u002Ftool.py maintain` (fast-forward with local edits\n   kept, reinstall, doctor, stale-store refresh, reload).\n8. Ship to-deliver items in the fewest pull requests; group related issues.\n\nCheck items 2 and 4 plus labels and links with `python3 .chaos-engine\u002Ftool.py dod \u003CPR>` ([`dod.py`](..\u002F..\u002Fdod.py))\n(table; exit 1 names each gap).\n\n## Findings policy\n\nEvery finding ends as exactly one of:\n\n- **fixed** in the current delivery, or\n- **filed** as an issue, allowed only when it is both outside the task's scope\n  and not critical, blocker, or high severity.\n\nNothing stays only in chat, a report, or a local file. The final report lists\neach finding as fixed (with PR) or filed (with issue).\n\n## Waste checklist\n\nBefore each pull, drop anything that is partially done work, extra process,\nextra features, task switching, waiting, handoffs without context, or defects\npassed downstream (Poppendieck's seven wastes).\n\n## Status\n\nEvery status report is a Markdown table, one row per card\n(`ID | Issue(s) | PR | Status | Proof or blocker`), then Risks. Never prose or\nbullet lists. No separate status rituals. Report only rows that changed since\nthe last report; say nothing when nothing changed.\n",{"name":5,"license":14,"description":7},"main","5f05d598699505258667e2cc8bd4c2d9bfffb695",".chaos-engine\u002Fskills\u002Fkanban",4,"https:\u002F\u002Fgithub.com\u002FiTestFlow\u002FiTestFlow-Agent","https:\u002F\u002Fgithub.com\u002FiTestFlow","2026-10-20 06:14:55",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add iTestFlow\u002FiTestFlow-Agent --skill kanban",{"tool":50,"command":51},"bunx","bunx skills add iTestFlow\u002FiTestFlow-Agent --skill kanban",{"tool":53,"command":54},"pnpm","pnpm dlx skills add iTestFlow\u002FiTestFlow-Agent --skill kanban","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FiTestFlow\u002FiTestFlow-Agent\u002Fblob\u002Fmain\u002F.chaos-engine\u002Fskills\u002Fkanban\u002FSKILL.md",true,[],[59,83,103,115,132,144],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":32},"01M71SEHZEDJFKAWP8ZH28P2GF","ponytail","Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use on any coding task (writing, fixing, refactoring, reviewing, choosing dependencies) and when the user says \"ponytail\", \"be lazy\", \"simplest solution\", \"yagni\", or complains about over-engineering or bloat. Levels: lite, full (default), ultra.","https:\u002F\u002Fgithub.com\u002FiTestFlow\u002FiTestFlow-Agent\u002Fblob\u002Fmain\u002Fplugins\u002Fponytail\u002Fskills\u002Fponytail\u002FSKILL.md",[],[61,66,67,68,27,69,70,71,72,73,74,75,29,76,77,78,79,80,81,82],"dependencies","read","lite","human","senior","yagni","solution","change","task","one","refactoring","writing","dev","default","about","mode","lazy",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":32},"01M71SEFG09MB8192GZKYY7J6Z","icm-architect","Advisory ICM workspace architect (folder structure as agent architecture). Use only when the task is ICM, workspace structure, or 'ICM this' design work.","https:\u002F\u002Fgithub.com\u002FiTestFlow\u002FiTestFlow-Agent\u002Fblob\u002Fmain\u002Fplugins\u002Ficm-architect\u002Fskills\u002Ficm-architect\u002FSKILL.md",[],[90,91,92,93,94,29,27,95,96,97,98,74,99,21,100,101,102],"architect","icm architect","folder","architecture","icm workspace","only","folder structure","design","workspace","agent architecture","structure","advisory","as",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":32},"01M71SEDBH592ZVNPHEX0H5VRC","chaos-engine","Load the canonical installed ChaosEngine before every task.","https:\u002F\u002Fgithub.com\u002FiTestFlow\u002FiTestFlow-Agent\u002Fblob\u002Fmain\u002Fplugins\u002Fchaos-engine\u002Fskills\u002Fchaos-engine\u002FSKILL.md",[],[110,111,112,74,113,114],"chaos","chaos engine","engine","load","canonical",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":32},"01M71SEAYX4X10N9EHC5GKP6DW","ultracave","Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with \u002Fultracave or \u002Fcaveman ultra. Stays on until \"stop caveman\" or \"normal mode\".","https:\u002F\u002Fgithub.com\u002FiTestFlow\u002FiTestFlow-Agent\u002Fblob\u002Fmain\u002Fplugins\u002Fcaveman\u002Fskills\u002Fultracave\u002FSKILL.md",[],[117,122,95,123,75,29,124,125,126,127,128,81,129,130,131],"with","stop","invoke","caveman","true","ultra","compression","at","normal","Word",{"skillNo":133,"name":125,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":32},"01M71SE7GAV24EJFR18HMJVP3F","Ultra-compressed communication companion. Use on every reply at ultra intensity; mandatory on the implementation path. Stop only with 'stop caveman' or 'normal mode'.","https:\u002F\u002Fgithub.com\u002FiTestFlow\u002FiTestFlow-Agent\u002Fblob\u002Fmain\u002Fplugins\u002Fcaveman\u002Fskills\u002Fcaveman\u002FSKILL.md",[],[125,127,138,139,123,27,140,95,141,142,81,129,130,143,122],"reply","path","implementation","intensity","companion","communication",{"skillNo":145,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":32},"01M71SE5VN9TY9XBZYK7Z5DQT1","https:\u002F\u002Fgithub.com\u002FiTestFlow\u002FiTestFlow-Agent\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fchaos-engine\u002FSKILL.md",[],[111,110,112,74,113,114]]