[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DXZMY4QJXX8V72CMWR2MZ1":3,"skill-same:01M6DXZMY4QJXX8V72CMWR2MZ1":83},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M6DXZMY4QJXX8V72CMWR2MZ1","rekey-work-items",null,"Converge every work item's ID onto the configured work.id_pattern, renaming files and rewriting references across meta\u002F. Use after changing work.id_pattern or work.key, when existing work items should take IDs in the new shape, or to finish or undo an interrupted re-key.","atomicinnovation\u002Faccelerator","atomicinnovation","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F65866524?v=4","01M6DXP513JV585FN2QPNR6079","Atomic","01M6DXP55MPK99YVZ2HGMEN991",34,"MIT","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Frekey-work-items\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"work","rekey work items","references","new","work item","when","Existing","converge","re","id","across","pattern","validate","files","take","shape","finish","use","Bash","ids","Meta","config","2026-11-10 10:12:30",false,"---\nname: rekey-work-items\ndescription: Converge every work item's ID onto the configured work.id_pattern,\n  renaming files and rewriting references across meta\u002F. Use after changing\n  work.id_pattern or work.key, when existing work items should take IDs in the\n  new shape, or to finish or undo an interrupted re-key.\nargument-hint: \"[--per-item-reads]\"\nallowed-tools:\n  - Bash(accelerator config *)\n  - Bash(accelerator work *)\n  - Bash(accelerator corpus frontmatter validate *)\n---\n\n# Re-key Work Items\n\n!`accelerator config context --skill rekey-work-items --fail-safe`\n!`accelerator config agents --fail-safe`\n\nIf no \"Agent Names\" section appears above, use these defaults:\naccelerator:reviewer, accelerator:codebase-locator,\naccelerator:codebase-analyser, accelerator:codebase-pattern-finder,\naccelerator:documents-locator, accelerator:documents-analyser,\naccelerator:web-search-researcher.\n\n**Active integration**: !`accelerator config work integration --fail-safe`\n**Local ID prefix**: !`accelerator config work key --fail-safe`\n**ID pattern**: !`accelerator config work id_pattern --fail-safe`\n**Work items directory**: !`accelerator config path work --fail-safe`\n\n`\u002Frekey-work-items` gives every work item an `id` in the shape **ID pattern**\ndescribes, whatever shape it has now. Each re-keyed item is renamed, its old\n`id` joins its `aliases`, and references to it across every corpus root\nfollow. The `accelerator work rekey` engine owns every decision: which items\nchange, the order fresh numbers follow, collisions, and recovery. This skill\npreviews, asks, then applies or discards.\n\nA preview records a **proposed run plan** under `.accelerator\u002Fstate\u002Frekey\u002F`,\nwhich version control ignores. The apply re-keys exactly the previewed\nmapping, refusing if any item's identity changed since, and records its\nprogress first, so an interrupted run is finished by running it again. Under\na `{tracker}` pattern the preview reads the tracker for current keys; the\napply makes no tracker call. The apply refuses over uncommitted changes in\nthe corpus, because version control is how a re-key is undone.\n\nPass `--per-item-reads` through to the preview when the user gives it.\n\n## The override note\n\n`ACCELERATOR_FORCE` makes `work rekey` skip its safety checks: the apply's\nworking-copy check, and the discard's check that every path the run wrote is\nrestored. **Never set it**, by prefix, `export` or `env`: overriding a\nrefusal is the user's decision, made outside this skill.\n\nWhenever a `work rekey` call's stderr carries a line starting\n`warning: ACCELERATOR_FORCE is set`, on any exit, tell the user, before any\nquestion, that `ACCELERATOR_FORCE` is set in their environment and the next\napply or discard will skip its safety check. From then on, for the rest of\nthis invocation, never offer **Undo it**: say the override would discard the\nrun without checking the restore, and ask the user to unset\n`ACCELERATOR_FORCE` and run `\u002Frekey-work-items` again.\n\n## Step 1: Preview\n\n```bash\naccelerator work rekey --preview [--per-item-reads]\n```\n\nBranch on the outcome:\n\n- **Exit 0 with mapping lines** on stdout, one `\u003Cold> → \u003Cnew>` per changing\n  item: go to Step 2.\n- **Exit 0 with no lines**: every item already matches the pattern. Report\n  that there is nothing to re-key and stop.\n- **`E_REKEY_IN_PROGRESS`**, after the stderr line\n  `the run in progress has still to re-key:`: an earlier run is unfinished.\n  Show the entries it still has to re-key, printed on stdout. Use the\n  `AskUserQuestion` tool with **Finish it** (run `accelerator work rekey`,\n  then act on Step 3's outcomes) and **Undo it** (the Undo flow below).\n  Under the override note, offer **Finish it** and **Stop** instead.\n- **`E_REKEY_PLAN_UNREADABLE`**: relay the printed remedy and any\n  half-applied evidence lines as they are. Never offer to finish the run, and\n  never run the forced discard the remedy names. Stop.\n- **Another exit 4**: surface the code, its printed remedy and the paths\n  listed under it. Nothing was recorded. Stop.\n- **Exit 70**: the tracker was unreachable; nothing was recorded. Retry once\n  it is reachable.\n- **Exit 72-74**: the tracker cannot be selected or configured. Relay the\n  printed message, point at `\u002Faccelerator:configure`, and stop; nothing was\n  recorded.\n- **Exit 1** with `E_IDENTITY_RUN_BUSY`, `E_REKEY_STATE_UNWRITABLE`,\n  `E_REKEY_IDENTITY_RUN_LOCK_FAILED`, `E_REKEY_CORPUS_INACCESSIBLE` or\n  `E_DRAFT_ID_EXHAUSTED`: relay the printed remedy and stop.\n\n## Step 2: Confirm\n\nPrint the mapping lines as they are, in a `text` fence, with the override\nnote if it applies.\n\nWith no dirty-path warning, use the `AskUserQuestion` tool:\n\n1. **Yes, re-key** — rename the listed items and rewrite their references\n2. **No, discard** — discard the plan; nothing changes\n\nWhen stderr carries `warning: the working copy has uncommitted changes`,\nname the paths listed under it and say the apply will refuse until they are\ncommitted or reverted. Then use the `AskUserQuestion` tool:\n\n1. **Keep the plan and stop** — commit or revert the paths first\n2. **Discard** — discard the plan; nothing changes\n\nWhen stderr carries ``with ACCELERATOR_FORCE set, `accelerator work rekey`\nwill apply over them``, name the paths listed under it and say the apply\nwill rewrite them over the uncommitted changes, which version control then\ncannot undo. Then use the `AskUserQuestion` tool:\n\n1. **Keep the plan and stop** — commit or revert the paths first\n2. **Yes, re-key over them** — apply despite the uncommitted changes\n\n## Step 3: Apply\n\nOn **Yes, re-key**:\n\n```bash\naccelerator work rekey\n```\n\nOn exit 0, each stdout line is `\u003Cold> → \u003Cnew>` and the re-keyed file's\npath, separated by a tab. Report each re-keyed item, then go to Step 5. On a\nnon-zero exit, act on the outcome table; any lines printed before the\nrefusal are entries that were applied, and they stand.\n\n| Code | What to do |\n|---|---|\n| `E_REKEY_PREVIEW_STALE` | The work items changed since the preview; name what changed and offer to run `\u002Frekey-work-items` again for a fresh preview |\n| `E_REKEY_DIRTY_WORKING_COPY` | Name the paths, say the plan is kept as it was (proposed or in progress), and stop |\n| `E_REKEY_WORKING_COPY_UNPROBEABLE` | Name the failure, say the plan is kept as it was, and stop |\n| `E_REKEY_ENTRY_ROLLED_BACK` | Say an entry was rolled back; offer to run `accelerator work rekey` again to resume |\n| `E_REKEY_ENTRY_REFUSED`, `E_REKEY_RESTORE_INCOMPLETE` | Relay the printed remedy, then offer the Undo flow, unless the override note was shown |\n| `E_REKEY_NOT_REVERTED` | The Undo flow, unless the override note was shown |\n| `E_REKEY_PLAN_UNREADABLE`, `E_IDENTITY_RUN_BUSY` | Relay the printed remedy and stop |\n| Any other code | Surface the code and its printed remedy, and stop |\n\n## Step 4: Discard or keep\n\nOn **No, discard** or **Discard**:\n\n```bash\naccelerator work rekey --discard\n```\n\nReport that no work item changed.\n\nOn **Keep the plan and stop**: say that once the paths are committed or\nreverted, `\u002Frekey-work-items` previews again and asks, or\n`accelerator work rekey` applies this plan if no item's identity changed\nmeanwhile.\n\n## Undo flow\n\nNever offer it under the override note.\n\n```bash\naccelerator work rekey --discard\n```\n\nOn exit 0 the run plan is gone; report that the re-key was undone. On\n`E_REKEY_NOT_REVERTED`, some paths the run wrote still differ from their\nstate when it started. Show the paths under each `restore from \u003Crevision>`\nheading with that revision, and the paths under `remove`. The skill does not\nrestore them: ask the user to restore and remove them, and to say when that\nis done. Then run `--discard` again. If it refuses again, show only the paths\nstill listed and repeat.\n\n## Step 5: Validate\n\nValidate each re-keyed item, using the path each applied line prints:\n\n```bash\naccelerator corpus frontmatter validate --file \u003Ceach re-keyed item path>\n```\n\nIf any invocation exits non-zero, that item violates the canonical\nfrontmatter standard; report the emitted violation before completing.\n\n!`accelerator config instructions rekey-work-items --fail-safe`\n","# Re-key Work Items\n\n!`accelerator config context --skill rekey-work-items --fail-safe`\n!`accelerator config agents --fail-safe`\n\nIf no \"Agent Names\" section appears above, use these defaults:\naccelerator:reviewer, accelerator:codebase-locator,\naccelerator:codebase-analyser, accelerator:codebase-pattern-finder,\naccelerator:documents-locator, accelerator:documents-analyser,\naccelerator:web-search-researcher.\n\n**Active integration**: !`accelerator config work integration --fail-safe`\n**Local ID prefix**: !`accelerator config work key --fail-safe`\n**ID pattern**: !`accelerator config work id_pattern --fail-safe`\n**Work items directory**: !`accelerator config path work --fail-safe`\n\n`\u002Frekey-work-items` gives every work item an `id` in the shape **ID pattern**\ndescribes, whatever shape it has now. Each re-keyed item is renamed, its old\n`id` joins its `aliases`, and references to it across every corpus root\nfollow. The `accelerator work rekey` engine owns every decision: which items\nchange, the order fresh numbers follow, collisions, and recovery. This skill\npreviews, asks, then applies or discards.\n\nA preview records a **proposed run plan** under `.accelerator\u002Fstate\u002Frekey\u002F`,\nwhich version control ignores. The apply re-keys exactly the previewed\nmapping, refusing if any item's identity changed since, and records its\nprogress first, so an interrupted run is finished by running it again. Under\na `{tracker}` pattern the preview reads the tracker for current keys; the\napply makes no tracker call. The apply refuses over uncommitted changes in\nthe corpus, because version control is how a re-key is undone.\n\nPass `--per-item-reads` through to the preview when the user gives it.\n\n## The override note\n\n`ACCELERATOR_FORCE` makes `work rekey` skip its safety checks: the apply's\nworking-copy check, and the discard's check that every path the run wrote is\nrestored. **Never set it**, by prefix, `export` or `env`: overriding a\nrefusal is the user's decision, made outside this skill.\n\nWhenever a `work rekey` call's stderr carries a line starting\n`warning: ACCELERATOR_FORCE is set`, on any exit, tell the user, before any\nquestion, that `ACCELERATOR_FORCE` is set in their environment and the next\napply or discard will skip its safety check. From then on, for the rest of\nthis invocation, never offer **Undo it**: say the override would discard the\nrun without checking the restore, and ask the user to unset\n`ACCELERATOR_FORCE` and run `\u002Frekey-work-items` again.\n\n## Step 1: Preview\n\n```bash\naccelerator work rekey --preview [--per-item-reads]\n```\n\nBranch on the outcome:\n\n- **Exit 0 with mapping lines** on stdout, one `\u003Cold> → \u003Cnew>` per changing\n  item: go to Step 2.\n- **Exit 0 with no lines**: every item already matches the pattern. Report\n  that there is nothing to re-key and stop.\n- **`E_REKEY_IN_PROGRESS`**, after the stderr line\n  `the run in progress has still to re-key:`: an earlier run is unfinished.\n  Show the entries it still has to re-key, printed on stdout. Use the\n  `AskUserQuestion` tool with **Finish it** (run `accelerator work rekey`,\n  then act on Step 3's outcomes) and **Undo it** (the Undo flow below).\n  Under the override note, offer **Finish it** and **Stop** instead.\n- **`E_REKEY_PLAN_UNREADABLE`**: relay the printed remedy and any\n  half-applied evidence lines as they are. Never offer to finish the run, and\n  never run the forced discard the remedy names. Stop.\n- **Another exit 4**: surface the code, its printed remedy and the paths\n  listed under it. Nothing was recorded. Stop.\n- **Exit 70**: the tracker was unreachable; nothing was recorded. Retry once\n  it is reachable.\n- **Exit 72-74**: the tracker cannot be selected or configured. Relay the\n  printed message, point at `\u002Faccelerator:configure`, and stop; nothing was\n  recorded.\n- **Exit 1** with `E_IDENTITY_RUN_BUSY`, `E_REKEY_STATE_UNWRITABLE`,\n  `E_REKEY_IDENTITY_RUN_LOCK_FAILED`, `E_REKEY_CORPUS_INACCESSIBLE` or\n  `E_DRAFT_ID_EXHAUSTED`: relay the printed remedy and stop.\n\n## Step 2: Confirm\n\nPrint the mapping lines as they are, in a `text` fence, with the override\nnote if it applies.\n\nWith no dirty-path warning, use the `AskUserQuestion` tool:\n\n1. **Yes, re-key** — rename the listed items and rewrite their references\n2. **No, discard** — discard the plan; nothing changes\n\nWhen stderr carries `warning: the working copy has uncommitted changes`,\nname the paths listed under it and say the apply will refuse until they are\ncommitted or reverted. Then use the `AskUserQuestion` tool:\n\n1. **Keep the plan and stop** — commit or revert the paths first\n2. **Discard** — discard the plan; nothing changes\n\nWhen stderr carries ``with ACCELERATOR_FORCE set, `accelerator work rekey`\nwill apply over them``, name the paths listed under it and say the apply\nwill rewrite them over the uncommitted changes, which version control then\ncannot undo. Then use the `AskUserQuestion` tool:\n\n1. **Keep the plan and stop** — commit or revert the paths first\n2. **Yes, re-key over them** — apply despite the uncommitted changes\n\n## Step 3: Apply\n\nOn **Yes, re-key**:\n\n```bash\naccelerator work rekey\n```\n\nOn exit 0, each stdout line is `\u003Cold> → \u003Cnew>` and the re-keyed file's\npath, separated by a tab. Report each re-keyed item, then go to Step 5. On a\nnon-zero exit, act on the outcome table; any lines printed before the\nrefusal are entries that were applied, and they stand.\n\n| Code | What to do |\n|---|---|\n| `E_REKEY_PREVIEW_STALE` | The work items changed since the preview; name what changed and offer to run `\u002Frekey-work-items` again for a fresh preview |\n| `E_REKEY_DIRTY_WORKING_COPY` | Name the paths, say the plan is kept as it was (proposed or in progress), and stop |\n| `E_REKEY_WORKING_COPY_UNPROBEABLE` | Name the failure, say the plan is kept as it was, and stop |\n| `E_REKEY_ENTRY_ROLLED_BACK` | Say an entry was rolled back; offer to run `accelerator work rekey` again to resume |\n| `E_REKEY_ENTRY_REFUSED`, `E_REKEY_RESTORE_INCOMPLETE` | Relay the printed remedy, then offer the Undo flow, unless the override note was shown |\n| `E_REKEY_NOT_REVERTED` | The Undo flow, unless the override note was shown |\n| `E_REKEY_PLAN_UNREADABLE`, `E_IDENTITY_RUN_BUSY` | Relay the printed remedy and stop |\n| Any other code | Surface the code and its printed remedy, and stop |\n\n## Step 4: Discard or keep\n\nOn **No, discard** or **Discard**:\n\n```bash\naccelerator work rekey --discard\n```\n\nReport that no work item changed.\n\nOn **Keep the plan and stop**: say that once the paths are committed or\nreverted, `\u002Frekey-work-items` previews again and asks, or\n`accelerator work rekey` applies this plan if no item's identity changed\nmeanwhile.\n\n## Undo flow\n\nNever offer it under the override note.\n\n```bash\naccelerator work rekey --discard\n```\n\nOn exit 0 the run plan is gone; report that the re-key was undone. On\n`E_REKEY_NOT_REVERTED`, some paths the run wrote still differ from their\nstate when it started. Show the paths under each `restore from \u003Crevision>`\nheading with that revision, and the paths under `remove`. The skill does not\nrestore them: ask the user to restore and remove them, and to say when that\nis done. Then run `--discard` again. If it refuses again, show only the paths\nstill listed and repeat.\n\n## Step 5: Validate\n\nValidate each re-keyed item, using the path each applied line prints:\n\n```bash\naccelerator corpus frontmatter validate --file \u003Ceach re-keyed item path>\n```\n\nIf any invocation exits non-zero, that item violates the canonical\nfrontmatter standard; report the emitted violation before completing.\n\n!`accelerator config instructions rekey-work-items --fail-safe`\n",{"name":5,"description":7,"allowed-tools":46,"argument-hint":50},[47,48,49],"Bash(accelerator config *)","Bash(accelerator work *)","Bash(accelerator corpus frontmatter validate *)","[--per-item-reads]","main","007b2dd695b63c2f097cdc40e54229b6e8b4596a","skills\u002Fwork\u002Frekey-work-items",2,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator","https:\u002F\u002Fgo-atomic.io","https:\u002F\u002Fgithub.com\u002Fatomicinnovation","2026-11-13 08:45:04",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add atomicinnovation\u002Faccelerator --skill rekey-work-items",{"tool":65,"command":66},"bunx","bunx skills add atomicinnovation\u002Faccelerator --skill rekey-work-items",{"tool":68,"command":69},"pnpm","pnpm dlx skills add atomicinnovation\u002Faccelerator --skill rekey-work-items","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Frekey-work-items\u002FSKILL.md",true,[73,79],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"evals\u002Fbenchmark.json","REFERENCE","参考文档",19185,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Frekey-work-items\u002Fevals\u002Fbenchmark.json",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"evals\u002Fevals.json",33587,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Frekey-work-items\u002Fevals\u002Fevals.json",[84,118,137,158,176,201],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":100,"publishedAt":41},"01M70S7PFGVATJREBFEGPJB718","explore-pr","Build an interactive, design-first and picture-first exploration page for a pull request — its architecture, abstractions and design decisions drawn as diagrams, a guided tour in reading order with code as the evidence, an attention map of where the risk sits, a ledger of its riskiest operations, prior review findings re-checked against the code, and simulations specific to the PR — with the reviewer's verdicts and notes saved. Use when the user wants to explore, understand or review a large pull request or its design, asks for a review page, walkthrough or visual explanation of a PR, or is struggling to review a big change.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fexplore-pr\u002FSKILL.md",[90,95],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[101,102,103,104,105,27,106,107,108,109,24,110,111,37,112,113,114,115,116,117],"explore pr","explore","pr","diagrams","exploration","review findings","walkthrough","design","map","number","URL","code","architecture","reviewer","review","notes","change",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":41},"01M6DY04WBTMFV96JMBP5ZXVFX","update-work-item","Update fields (status, priority, tags, parent, etc.) of an existing work item. Use to transition status, change priority, manage tags, or edit any frontmatter field. No transition enforcement — arbitrary changes are allowed.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fupdate-work-item\u002FSKILL.md",[],[19,125,126,23,127,128,36,37,117,40,129,31,130,131,132,25,133,134,135,136],"update","update work item","enforcement","manage","edit","status","transition","frontmatter","tags","changes","fields","op",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":41},"01M6DY0106CF15CYEJHZM14GBZ","sync-work-items","Reconcile local work items in meta\u002Fwork\u002F with the active remote tracker named by work.integration. Use when the user wants to sync, push, or pull work items to or from Jira or Linear, preview what a sync would change, or reconcile divergent local and remote state.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fsync-work-items\u002FSKILL.md",[],[19,144,145,146,39,147,148,37,149,117,150,151,152,153,154,155,156,40,157,132,24],"sync","sync work items","promote","local","only","preview","active","tracker","max","jira","remote","create","adopt","reconcile",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":41},"01M6HNF86984S4XK21Q26VZA21","sync-work-items-recovery","Recovery procedures for work sync failures that need a person — terminal rows, refused pending pushes and refused orders. Read by sync-work-items — not invoked directly.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fsync-work-items-recovery\u002FSKILL.md",[],[165,19,166,144,145,167,168,169,170,171,172,173,174,175],"sync work items recovery","recovery","work-items","for","terminal","read","person","true","false","orders","pending",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":185,"publishedAt":41},"01M6DXZWH7PR72VCEXSSD4XNK4","stress-test-work-item","Interactively stress-test a work item by grilling the user on scope, assumptions, acceptance criteria, edge cases, and dependencies to surface issues, gaps, and flawed assumptions before implementation is planned.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fstress-test-work-item\u002FSKILL.md",[182],{"categoryNo":183,"categoryName":184,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000008","测试与质量",[186,187,19,188,23,189,190,191,192,193,194,37,195,196,40,31,197,198,199,110,200,132],"stress test","test","stress test work item","stress","scope","issues","edge","stress-test","acceptance","acceptance criteria","dependencies","implementation","grilling","user","gaps",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":207,"publishedAt":41},"01M6DXZRQWHTWV1G9PTTHCGGYA","review-work-item","Review a work item through multiple quality lenses and collaboratively iterate based on findings. Use when the user wants to evaluate a work item before implementation or escalation.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Freview-work-item\u002FSKILL.md",[],[115,19,208,23,209,210,36,37,211,212,40,31,197,199,213,24,214,215,132,216],"review work item","review work","escalation","file","quality","metadata","iterate","evaluate","path"]