[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DXV5PDSP0VSST9WN26E46Z":3,"skill-same:01M6DXV5PDSP0VSST9WN26E46Z":59},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":45,"install":46,"resources":58},"01M6DXV5PDSP0VSST9WN26E46Z","finding-outputter",null,"Output contract for a research finding. Owns the finding's frontmatter, sections, tier-tagged sources, and write sink. Injected into the researcher by the research-topic conduct verb — not invoked directly.","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\u002Fresearch\u002Foutputters\u002Ffinding-outputter\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"finding outputter","research","researcher","write","contract","false","sources","output","true","for","frontmatter","conduct","tagged","2026-11-10 10:12:30",false,"---\nname: finding-outputter\ndescription: Output contract for a research finding. Owns the finding's\n  frontmatter, sections, tier-tagged sources, and write sink. Injected into the\n  researcher by the research-topic conduct verb — not invoked directly.\nuser-invocable: false\ndisable-model-invocation: true\n---\n\n# Finding Outputter\n\nYou write **one finding** for a single focus area. This document owns the\nfinding's shape end to end: what it is, where it goes, and what it must never do.\n\n## Sink\n\nWrite the finding to the **single output path injected into your task prompt**,\nand to no other path.\n\n## Injected Values\n\nYour task prompt injects everything the frontmatter needs — do not invent or\nderive it:\n\n- **finding template** — the resolved `topic-research-finding` template to render.\n- **output path** — where to write the finding.\n- **round** — the round number this finding belongs to.\n- **depth** — the resolved depth the finding was researched or composed under.\n- **question** — the focus area's question.\n- **source profile** — the profile this finding was researched through.\n- **timestamp** — the ISO datetime for `date` and `last_updated`.\n- **author** — the value for `author` and `last_updated_by`.\n\n## Shape\n\nThe `topic-research-finding` template is the finding's shape — frontmatter and\nbody skeleton both — and is injected into your task prompt. Fill its\nplaceholders from the injected values. If no template was injected, refuse\nrather than improvise a shape.\n\nFill the template from the injected values, observing the deltas it cannot\nexpress on its own:\n\n- `status` is always `complete`.\n- `source_profile` is always the injected source profile, and `question` the\n  injected question byte for byte, each overriding any value the template\n  carries.\n- Omit the `revision`\u002F`repository` pair entirely — a finding is not\n  code-state-anchored.\n- The typed-linkage slots (`parent`, `relates_to`) are **omit-when-empty**: emit\n  a key only when it carries a value. Never write `parent: \"\"` or\n  `relates_to: []` — the validator rejects those literal empties.\n\n## Body\n\nThe template you loaded is authoritative for the finding's sections — follow\nits structure. The guidance below is about the *content* to write, not a fixed\nset of headings: where the template has a matching section, fill it out this\nway, and use your judgement for any section the template shapes differently.\n\n- **Question** — the focus area's question, restated.\n- **Findings** — standalone research prose that answers the question. It reads\n  on its own: **no round narration**, no \"in this round\", no changelog of what\n  you did. A reader who opens only this finding must understand it.\n- **Sources** — one bullet per source, each carrying its reputation tier and\n  recorded domain or venue, and the source's metadata block when it has one\n  (see **Sources Metadata Block**):\n\n  ```text\n  - [Title](url) — tier-1 — {source domain\u002Fvenue}\n    - doi: 10.7717\u002Fpeerj.4375\n    - openalex_id: W2741809807\n    - published: 2018-02-13\n    - accessed: 2026-10-24\n  ```\n\n  When the profile's sources held nothing relevant, Sources reads\n  `None found.` instead.\n\nTier every source `tier-1`\u002F`tier-2`\u002F`tier-3` by the source profile's vocabulary,\nfrom venue identity alone. The tier text carries any suffix the profile\nprescribes, such as `tier-3 (retracted)`.\n\nA source cited at several tiers lists the others in an `also` suffix, after\nany `retracted` or `withdrawn` mark: `tier-3 (also tier-2, tier-1)`,\n`tier-3 (retracted; withdrawn; also tier-1)`.\n\n## Sources Metadata Block\n\nA Sources entry may carry a **metadata block**: a nested `  - key: value`\nlist directly under its line. The block is optional, and an entry without one\nis valid. A researcher writes each block from the CLI's output, under the\nrules below.\n\n- Block lines are the CLI's `metadata` entries for the cited source, copied\n  unchanged and in emitted order. Never write a block line from anywhere\n  else: not from a page, an abstract, a record's other fields, or memory.\n- Keys are lowercase `snake_case`, values are single-line, and a key with no\n  value is omitted.\n- `url`, title and venue never appear in the block: they stay on the entry\n  line.\n- The CLI emits only recommended keys, in table order. Copying in emitted\n  order keeps that order.\n- The template's `  - {source-metadata}` slot line repeats under every\n  Sources entry. Under each, it becomes one `  - key: value` line per entry\n  of that source's `metadata` map, in emitted order. When the source has no\n  map, delete the whole slot line: never leave it as written, and never fill\n  it from anything else.\n\nA composer writes each block from the notes' blocks instead, under the\nciting-once rule. Every line still comes from a block a note carries.\n\nThe recommended keys, in order:\n\n| Key | Group | Value form |\n|---|---|---|\n| `doi` | identifier | bare and lowercase: `10.7717\u002Fpeerj.4375` |\n| `arxiv_id` | identifier | bare, with the version retrieved: `2305.12345v2` |\n| `openalex_id` | identifier | the bare `W` ID: `W2741809807` |\n| `pmid` | identifier | |\n| `issn` | identifier | |\n| `published` | date | ISO 8601 at the precision the source declares: `2023`, `2023-05` or `2023-05-12` |\n| `updated` | date | as `published` |\n| `accessed` | date | the UTC date of the CLI call the map came from: `2026-10-24` |\n| `type` | bibliographic | |\n| `authors` | bibliographic | |\n| `publisher` | bibliographic | |\n| `volume` | bibliographic | |\n| `issue` | bibliographic | |\n| `pages` | bibliographic | |\n| `license` | bibliographic | |\n| `journal_ref` | source-specific | |\n| `primary_category` | source-specific | |\n| `oa_status` | source-specific | |\n| `pdf_url` | source-specific | |\n\nThe CLI fills the core keys, those with a value form above, wherever the\nsource provides them. `journal_ref` is a citation string, not a venue, so it\ndoes not duplicate the entry line.\n","# Finding Outputter\n\nYou write **one finding** for a single focus area. This document owns the\nfinding's shape end to end: what it is, where it goes, and what it must never do.\n\n## Sink\n\nWrite the finding to the **single output path injected into your task prompt**,\nand to no other path.\n\n## Injected Values\n\nYour task prompt injects everything the frontmatter needs — do not invent or\nderive it:\n\n- **finding template** — the resolved `topic-research-finding` template to render.\n- **output path** — where to write the finding.\n- **round** — the round number this finding belongs to.\n- **depth** — the resolved depth the finding was researched or composed under.\n- **question** — the focus area's question.\n- **source profile** — the profile this finding was researched through.\n- **timestamp** — the ISO datetime for `date` and `last_updated`.\n- **author** — the value for `author` and `last_updated_by`.\n\n## Shape\n\nThe `topic-research-finding` template is the finding's shape — frontmatter and\nbody skeleton both — and is injected into your task prompt. Fill its\nplaceholders from the injected values. If no template was injected, refuse\nrather than improvise a shape.\n\nFill the template from the injected values, observing the deltas it cannot\nexpress on its own:\n\n- `status` is always `complete`.\n- `source_profile` is always the injected source profile, and `question` the\n  injected question byte for byte, each overriding any value the template\n  carries.\n- Omit the `revision`\u002F`repository` pair entirely — a finding is not\n  code-state-anchored.\n- The typed-linkage slots (`parent`, `relates_to`) are **omit-when-empty**: emit\n  a key only when it carries a value. Never write `parent: \"\"` or\n  `relates_to: []` — the validator rejects those literal empties.\n\n## Body\n\nThe template you loaded is authoritative for the finding's sections — follow\nits structure. The guidance below is about the *content* to write, not a fixed\nset of headings: where the template has a matching section, fill it out this\nway, and use your judgement for any section the template shapes differently.\n\n- **Question** — the focus area's question, restated.\n- **Findings** — standalone research prose that answers the question. It reads\n  on its own: **no round narration**, no \"in this round\", no changelog of what\n  you did. A reader who opens only this finding must understand it.\n- **Sources** — one bullet per source, each carrying its reputation tier and\n  recorded domain or venue, and the source's metadata block when it has one\n  (see **Sources Metadata Block**):\n\n  ```text\n  - [Title](url) — tier-1 — {source domain\u002Fvenue}\n    - doi: 10.7717\u002Fpeerj.4375\n    - openalex_id: W2741809807\n    - published: 2018-02-13\n    - accessed: 2026-10-24\n  ```\n\n  When the profile's sources held nothing relevant, Sources reads\n  `None found.` instead.\n\nTier every source `tier-1`\u002F`tier-2`\u002F`tier-3` by the source profile's vocabulary,\nfrom venue identity alone. The tier text carries any suffix the profile\nprescribes, such as `tier-3 (retracted)`.\n\nA source cited at several tiers lists the others in an `also` suffix, after\nany `retracted` or `withdrawn` mark: `tier-3 (also tier-2, tier-1)`,\n`tier-3 (retracted; withdrawn; also tier-1)`.\n\n## Sources Metadata Block\n\nA Sources entry may carry a **metadata block**: a nested `  - key: value`\nlist directly under its line. The block is optional, and an entry without one\nis valid. A researcher writes each block from the CLI's output, under the\nrules below.\n\n- Block lines are the CLI's `metadata` entries for the cited source, copied\n  unchanged and in emitted order. Never write a block line from anywhere\n  else: not from a page, an abstract, a record's other fields, or memory.\n- Keys are lowercase `snake_case`, values are single-line, and a key with no\n  value is omitted.\n- `url`, title and venue never appear in the block: they stay on the entry\n  line.\n- The CLI emits only recommended keys, in table order. Copying in emitted\n  order keeps that order.\n- The template's `  - {source-metadata}` slot line repeats under every\n  Sources entry. Under each, it becomes one `  - key: value` line per entry\n  of that source's `metadata` map, in emitted order. When the source has no\n  map, delete the whole slot line: never leave it as written, and never fill\n  it from anything else.\n\nA composer writes each block from the notes' blocks instead, under the\nciting-once rule. Every line still comes from a block a note carries.\n\nThe recommended keys, in order:\n\n| Key | Group | Value form |\n|---|---|---|\n| `doi` | identifier | bare and lowercase: `10.7717\u002Fpeerj.4375` |\n| `arxiv_id` | identifier | bare, with the version retrieved: `2305.12345v2` |\n| `openalex_id` | identifier | the bare `W` ID: `W2741809807` |\n| `pmid` | identifier | |\n| `issn` | identifier | |\n| `published` | date | ISO 8601 at the precision the source declares: `2023`, `2023-05` or `2023-05-12` |\n| `updated` | date | as `published` |\n| `accessed` | date | the UTC date of the CLI call the map came from: `2026-10-24` |\n| `type` | bibliographic | |\n| `authors` | bibliographic | |\n| `publisher` | bibliographic | |\n| `volume` | bibliographic | |\n| `issue` | bibliographic | |\n| `pages` | bibliographic | |\n| `license` | bibliographic | |\n| `journal_ref` | source-specific | |\n| `primary_category` | source-specific | |\n| `oa_status` | source-specific | |\n| `pdf_url` | source-specific | |\n\nThe CLI fills the core keys, those with a value form above, wherever the\nsource provides them. `journal_ref` is a citation string, not a venue, so it\ndoes not duplicate the entry line.\n",{"name":5,"description":7,"user-invocable":33,"disable-model-invocation":37},true,"main","007b2dd695b63c2f097cdc40e54229b6e8b4596a","skills\u002Fresearch\u002Foutputters\u002Ffinding-outputter",2,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator","https:\u002F\u002Fgo-atomic.io","https:\u002F\u002Fgithub.com\u002Fatomicinnovation","2026-11-12 04:07:28",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":37},[48,51,54],{"tool":49,"command":50},"npx","npx skills add atomicinnovation\u002Faccelerator --skill finding-outputter",{"tool":52,"command":53},"bunx","bunx skills add atomicinnovation\u002Faccelerator --skill finding-outputter",{"tool":55,"command":56},"pnpm","pnpm dlx skills add atomicinnovation\u002Faccelerator --skill finding-outputter","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Foutputters\u002Ffinding-outputter\u002FSKILL.md",[],[60,97,121,143,158,183],{"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":76,"publishedAt":32},"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",[66,71],{"categoryNo":67,"categoryName":68,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96],"explore pr","explore","pr","diagrams","exploration","re","review findings","walkthrough","design","map","when","number","URL","Bash","code","architecture","reviewer","review","notes","change",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":32},"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",[],[104,105,106,107,108,109,110,90,96,111,112,113,114,115,29,116,117,118,119,120],"work","update","update work item","work item","enforcement","manage","use","config","edit","validate","status","transition","Existing","tags","changes","fields","op",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":32},"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",[],[104,128,129,130,131,132,133,90,134,96,135,136,137,138,139,140,141,111,142,29,87],"sync","sync work items","promote","Meta","local","only","preview","active","tracker","max","jira","remote","create","adopt","reconcile",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":32},"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",[],[150,104,151,128,129,152,28,153,154,155,27,24,156,157],"sync work items recovery","recovery","work-items","terminal","read","person","orders","pending",{"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":167,"publishedAt":32},"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",[164],{"categoryNo":165,"categoryName":166,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000008","测试与质量",[168,169,104,170,107,171,172,173,174,175,176,90,177,178,111,113,179,180,181,88,182,29],"stress test","test","stress test work item","stress","scope","issues","edge","stress-test","acceptance","acceptance criteria","dependencies","implementation","grilling","user","gaps",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":32},"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",[],[94,104,190,107,191,192,110,90,193,194,111,113,179,181,195,87,196,197,29,198],"review work item","review work","escalation","file","quality","metadata","iterate","evaluate","path"]