[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVBXS5491BXKA08378CXCB":3,"skill-same:01M7EVBXS5491BXKA08378CXCB":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EVBXS5491BXKA08378CXCB","fill-in-prototype",null,"Complete a coherent presentation from a prototype and selected research evidence, composing writers for supported material and targeted prove\u002Frefute attempts for genuine gaps. Use for \"fill in the prototype\", \"complete this exposition\", or narrowly \"work these conjectures\". Requires doubt before promotion and returns actual artifacts and unresolved obligations to the synthesis coordinator; a fill request authorizes execution, not just recommendations.","tdupu\u002Fagent-skills-public","tdupu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3440403?v=4","01M7EV32X9J0EFE5T4P8TKQTCQ","Taylor Dupuy","01M7EV32XZ1Z4MDBYAFRCJD3BP",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Ffill-in-prototype\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: fill-in-prototype\ndescription: Complete a coherent presentation from a prototype and selected research evidence, composing writers for supported material and targeted prove\u002Frefute attempts for genuine gaps. Use for \"fill in the prototype\", \"complete this exposition\", or narrowly \"work these conjectures\". Requires doubt before promotion and returns actual artifacts and unresolved obligations to the synthesis coordinator; a fill request authorizes execution, not just recommendations.\n---\n\n# fill-in-prototype\n\nThe [synthesis contract](..\u002F..\u002F..\u002F..\u002Fskills\u002Fmath-workflow\u002Freferences\u002Fsynthesis.md)\nowns the end-to-end stages, reviews and integration. This leaf executes the\nrequested fill, then returns to that coordinator. A direct request to work\nnamed conjectures stays confined to those items; a request to fill the\npresentation includes its definitions, proofs, examples and explanatory prose.\n\n## Fill from evidence, then resolve gaps\n\n1. Read the prototype, spec, selected originals and relevant live text;\n   reconcile touched rows under [LEDGER.md](..\u002F..\u002F..\u002Frepo-docs\u002FLEDGER.md).\n   Resolve audience, depth and target through\n   [RESOLUTION.md](..\u002F..\u002F..\u002Frepo-docs\u002FRESOLUTION.md). Inventory missing content\n   and genuine research obligations separately, with source locators and\n   dependencies; report their counts. If the spec or structure is missing,\n   compose `create-exposition` or `rapid-prototype` and the applicable outline\n   review within the fill scope.\n2. Fill supported material in dependency order from the actual arguments,\n   not the dump's status labels. Complete the topic introduction, definitions,\n   statements, required proofs, worked examples and connective explanation\n   to the audience's declared level. Preserve hypotheses, computational range,\n   qualifications and counterexamples. Verify imported results through\n   `track-down-reference`; a source citation does not replace a required\n   self-contained proof.\n3. Resolve undetermined mathematics through `using-mathpowers` under the shared\n   [execution contract](..\u002F..\u002F..\u002F..\u002Fskills\u002Fmath-workflow\u002Freferences\u002Fexecution.md):\n   supply exact statement, prerequisites and selected evidence; execute and\n   consume attempts. Its backend\u002Fpath preflight, delegation limits, persistent\n   allowance, deadlines and loud failure gate govern every retry\u002Freview.\n   Preserve packages, partial proofs, reductions and failed expectations; update\n   spec\u002Fledger links without silently expanding selection.\n4. Apply that contract's conflict investigation\u002Fadoption gate through\n   `contradiction-check`; never silently replace an earlier claim. Run `doubt`\n   before promotion and collect its verdict while independent work continues.\n   Only SOUND on the actual statement\u002Fargument\u002Fdependencies satisfies the gate;\n   changed evidence needs renewed scrutiny. WEAK, SUSPECT or absent verdicts\n   block affected promotion, including computational or negative claims.\n5. Compose `write-definition`, `write-proposition`, `write-example` and\n   `write-remark` for their respective content; use `explain-experiment` for\n   computational exposition when needed. Supply each writer its evidence,\n   prerequisites and concrete planned location. Produce the complete content,\n   not a list of recommended writer calls. Scratch workers apply the writers'\n   content disciplines and return candidate text\u002Fevidence only: no canonical\n   mutation or canonical postamble during drafting. Reasonable reordering and\n   insertion within the selected target are authorized unless a repository\n   rule reserves them; retain relocations and recheck dependencies. Claims\n   inside explanatory prose still require the proposition gates.\n6. Keep pre-integration candidates in permitted scratch Markdown, including\n   LaTeX excerpts where useful; do not invent an undeclared `.tex` target.\n   At requested integration, follow the [manuscript-return gate](..\u002F..\u002F..\u002F..\u002Fskills\u002Fmath-workflow\u002Freferences\u002Fexecution.md#manuscript-return),\n   including its partial-stub restriction. The coordinator invokes\n   [WRITERS.md](..\u002F..\u002F..\u002Flatex\u002FWRITERS.md) and the composed leaves in full at\n   the declared canonical\u002Faspirational destination. Preserve human markers\n   and tagged history; keep statuses in the ledger.\n   Drafting an introduction to the topic does not invoke or bypass\n   `write-introduction`'s finished-paper\u002Fabstract gates.\n7. Assemble the returns into one readable presentation, checking notation,\n   transitions, labels and dependency coverage. Carry negative findings as\n   substantive results with the expectation they correct (LX11\u002FLX12); count\n   those carried and exclusions with authorized reasons. Missing proofs stay\n   explicit questions\u002Fconjectures, never theorem\u002Fproof placeholders presented\n   as completed mathematics. Identify any unmet presentation requirement.\n\n## Return and continue\n\nReturn the exact candidate\u002Fedited regions, source and relocation map, evidence\nand doubt records, writer checks, and unresolved obligations with their blocked\ndependents. The coordinator consumes these artifacts and continues the shared\npresentation review\u002Fintegration sequence; a writer's return is not a reason\nto end the synthesis. For direct fill requests, the invoking agent carries out\nthe applicable review and requested delivery from that contract. Report actual\ncompletion or incompleteness. Source-candidate acceptance is not final manuscript\nacceptance: the coordinator must obtain the shared contract's final independent\nreview of the integrated diff, its interfaces\u002Fdependency closure and compiled\nPDF. Neither outline acceptance nor a successful compile establishes a proof.\n","# fill-in-prototype\n\nThe [synthesis contract](..\u002F..\u002F..\u002F..\u002Fskills\u002Fmath-workflow\u002Freferences\u002Fsynthesis.md)\nowns the end-to-end stages, reviews and integration. This leaf executes the\nrequested fill, then returns to that coordinator. A direct request to work\nnamed conjectures stays confined to those items; a request to fill the\npresentation includes its definitions, proofs, examples and explanatory prose.\n\n## Fill from evidence, then resolve gaps\n\n1. Read the prototype, spec, selected originals and relevant live text;\n   reconcile touched rows under [LEDGER.md](..\u002F..\u002F..\u002Frepo-docs\u002FLEDGER.md).\n   Resolve audience, depth and target through\n   [RESOLUTION.md](..\u002F..\u002F..\u002Frepo-docs\u002FRESOLUTION.md). Inventory missing content\n   and genuine research obligations separately, with source locators and\n   dependencies; report their counts. If the spec or structure is missing,\n   compose `create-exposition` or `rapid-prototype` and the applicable outline\n   review within the fill scope.\n2. Fill supported material in dependency order from the actual arguments,\n   not the dump's status labels. Complete the topic introduction, definitions,\n   statements, required proofs, worked examples and connective explanation\n   to the audience's declared level. Preserve hypotheses, computational range,\n   qualifications and counterexamples. Verify imported results through\n   `track-down-reference`; a source citation does not replace a required\n   self-contained proof.\n3. Resolve undetermined mathematics through `using-mathpowers` under the shared\n   [execution contract](..\u002F..\u002F..\u002F..\u002Fskills\u002Fmath-workflow\u002Freferences\u002Fexecution.md):\n   supply exact statement, prerequisites and selected evidence; execute and\n   consume attempts. Its backend\u002Fpath preflight, delegation limits, persistent\n   allowance, deadlines and loud failure gate govern every retry\u002Freview.\n   Preserve packages, partial proofs, reductions and failed expectations; update\n   spec\u002Fledger links without silently expanding selection.\n4. Apply that contract's conflict investigation\u002Fadoption gate through\n   `contradiction-check`; never silently replace an earlier claim. Run `doubt`\n   before promotion and collect its verdict while independent work continues.\n   Only SOUND on the actual statement\u002Fargument\u002Fdependencies satisfies the gate;\n   changed evidence needs renewed scrutiny. WEAK, SUSPECT or absent verdicts\n   block affected promotion, including computational or negative claims.\n5. Compose `write-definition`, `write-proposition`, `write-example` and\n   `write-remark` for their respective content; use `explain-experiment` for\n   computational exposition when needed. Supply each writer its evidence,\n   prerequisites and concrete planned location. Produce the complete content,\n   not a list of recommended writer calls. Scratch workers apply the writers'\n   content disciplines and return candidate text\u002Fevidence only: no canonical\n   mutation or canonical postamble during drafting. Reasonable reordering and\n   insertion within the selected target are authorized unless a repository\n   rule reserves them; retain relocations and recheck dependencies. Claims\n   inside explanatory prose still require the proposition gates.\n6. Keep pre-integration candidates in permitted scratch Markdown, including\n   LaTeX excerpts where useful; do not invent an undeclared `.tex` target.\n   At requested integration, follow the [manuscript-return gate](..\u002F..\u002F..\u002F..\u002Fskills\u002Fmath-workflow\u002Freferences\u002Fexecution.md#manuscript-return),\n   including its partial-stub restriction. The coordinator invokes\n   [WRITERS.md](..\u002F..\u002F..\u002Flatex\u002FWRITERS.md) and the composed leaves in full at\n   the declared canonical\u002Faspirational destination. Preserve human markers\n   and tagged history; keep statuses in the ledger.\n   Drafting an introduction to the topic does not invoke or bypass\n   `write-introduction`'s finished-paper\u002Fabstract gates.\n7. Assemble the returns into one readable presentation, checking notation,\n   transitions, labels and dependency coverage. Carry negative findings as\n   substantive results with the expectation they correct (LX11\u002FLX12); count\n   those carried and exclusions with authorized reasons. Missing proofs stay\n   explicit questions\u002Fconjectures, never theorem\u002Fproof placeholders presented\n   as completed mathematics. Identify any unmet presentation requirement.\n\n## Return and continue\n\nReturn the exact candidate\u002Fedited regions, source and relocation map, evidence\nand doubt records, writer checks, and unresolved obligations with their blocked\ndependents. The coordinator consumes these artifacts and continues the shared\npresentation review\u002Fintegration sequence; a writer's return is not a reason\nto end the synthesis. For direct fill requests, the invoking agent carries out\nthe applicable review and requested delivery from that contract. Report actual\ncompletion or incompleteness. Source-candidate acceptance is not final manuscript\nacceptance: the coordinator must obtain the shared contract's final independent\nreview of the integrated diff, its interfaces\u002Fdependency closure and compiled\nPDF. Neither outline acceptance nor a successful compile establishes a proof.\n",{"name":5,"description":7},"main","8d13efb5e66306aeae6e3b948bc463e7e2db1b65","skills\u002Ffill-in-prototype","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public","https:\u002F\u002Fgithub.com\u002Ftdupu","https:\u002F\u002Ftdupu.github.io\u002Findex.html","Associate Professor, Department of Mathematics and Statistics, University of Vermont --- last updated Fall 2019","2026-11-13 09:07:19",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add tdupu\u002Fagent-skills-public --skill fill-in-prototype",{"tool":38,"command":39},"bunx","bunx skills add tdupu\u002Fagent-skills-public --skill fill-in-prototype",{"tool":41,"command":42},"pnpm","pnpm dlx skills add tdupu\u002Fagent-skills-public --skill fill-in-prototype","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Ffill-in-prototype\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7EW4PT586KKE7VRCAD80Z9K","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7EW4HV5V74AF3PTV8N4T0PS","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7EW4DNKGP5CR1RAJP2J9PHA","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7EW4BA2QP88VBFVXDVJM7XQ","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-superpowers\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EW47F2JG5FBESDJNP3PKMV","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7EW44N8556Y556NX9HJT4KP","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[]]