[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVCVJEV813S2FN49Z2QD89":3,"skill-same:01M7EVCVJEV813S2FN49Z2QD89":58},{"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},"01M7EVCVJEV813S2FN49Z2QD89","generate-graphics",null,"Generate or regenerate reproducible mathematical graphics with SageMath for a manuscript, retaining source, inputs, numerical conventions, and a provenance manifest. Use for computed graph diagrams, spectra, and plots; pass manuscript insertion to add-figure.","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\u002Fgenerate-graphics\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: generate-graphics\ndescription: Generate or regenerate reproducible mathematical graphics with SageMath for a manuscript, retaining source, inputs, numerical conventions, and a provenance manifest. Use for computed graph diagrams, spectra, and plots; pass manuscript insertion to add-figure.\n---\n\n# generate-graphics\n\nParent: [mathcity-latex](..\u002F..\u002FREADME.md).\n\nProduce a SageMath graphics item, its source, and evidence sufficient to tell\nwhat it depicts. This leaf does not edit a manuscript or establish a theorem.\nReuse the active `using-latexpowers` plan; a bounded assignment stays bounded.\n\n## Preflight and scope\n\n- Resolve the project's layout, computation policy, and requested destination.\n  Find existing scripts, data, and figures first; extend or rerun an existing\n  generator when it covers the task. Do not replace original talk graphics.\n- Check `sage --version` and `sage -python -c 'import sage.all'`; use writable\n  temporary `DOT_SAGE` and `MPLCONFIGDIR` if normal caches are unavailable.\n  Check readable inputs and unused output paths. Missing dependency: stop\n  with \"I'm sorry, I can't do that — \u003Cmissing resource>. \u003CRecovery action>.\n  \u003CWhat it enables>.\" Never invent data.\n- State the question illustrated, input range, and intended audience. Fix\n  vertex\u002Fedge meaning, direction, multiplicity, weights, normalization, field,\n  axes, units, and color meaning as applicable before choosing an attractive\n  layout. A schematic is identified as schematic; its geometry is not data.\n\n## Generation and evidence\n\n1. Keep an editable Sage source file in the project's declared source location\n   and outputs in its declared figure location. Use repository-relative paths\n   and an explicit command; no hidden notebook state or absolute home paths.\n   Record input hashes, software versions, exact versus numerical arithmetic,\n   precision\u002Ftolerance, random seeds, and graph positions or layout seed.\n   See [the manifest contract](references\u002Fprovenance.md).\n2. Compute the quantity before plotting it. Record a small independent check:\n   e.g. vertex\u002Fedge counts and degree sums, row sums, trace\u002Feigenvalue sum,\n   exact characteristic polynomial, or an analytically known special case.\n   Report disconnected pieces, dropped rows, complex eigenvalues, multiplicity,\n   truncation, and sampling explicitly; never silently simplify a multigraph.\n3. Save a vector PDF for a compatible TeX engine and a PNG preview. Use SVG or\n   another format only when the project's build supports it. Use readable\n   labels at publication size and color plus labels\u002Fshapes\u002Fline styles when a\n   distinction matters. Do not use an image generator to fabricate a data plot.\n4. Inspect the rendered image for clipping, collisions, tiny type, misleading\n   scales, lost edge multiplicity, and colors unsupported by the data. Rendering\n   successfully is not a semantic check. Rerun in a fresh output directory and\n   compare the data\u002Finvariants; byte-identical PDFs are not required.\n5. Write the manifest with actual check results and unresolved limitations.\n   Keep its artifact hashes synchronized after every regeneration. An old\n   graphic with missing source is an imported asset with incomplete provenance,\n   not a newly reproduced computation.\n\nThe [runnable cycle template](assets\u002Fcycle_graph.py) demonstrates deterministic\ncoordinates, exact Sage checks, PDF\u002FPNG exports, and the manifest. Run it with\n`sage -python \u003Cskill-dir>\u002Fassets\u002Fcycle_graph.py \u003Cnew-output-dir>`; copy and adapt\nit to the project rather than importing this fixture as project research.\n\nReturn paths to source, inputs, rendered files, manifest, and a short caption\nbrief explaining what the picture supports and what it cannot establish.\nCall `add-figure` only when manuscript insertion is requested or part of the\nactive plan. Use `write-example` for a self-contained finite case, and\n`explain-experiment` for a broader computational investigation. Mathematical\nclaim promotions still require the normal contradiction\u002Fdoubt gates.\n","# generate-graphics\n\nParent: [mathcity-latex](..\u002F..\u002FREADME.md).\n\nProduce a SageMath graphics item, its source, and evidence sufficient to tell\nwhat it depicts. This leaf does not edit a manuscript or establish a theorem.\nReuse the active `using-latexpowers` plan; a bounded assignment stays bounded.\n\n## Preflight and scope\n\n- Resolve the project's layout, computation policy, and requested destination.\n  Find existing scripts, data, and figures first; extend or rerun an existing\n  generator when it covers the task. Do not replace original talk graphics.\n- Check `sage --version` and `sage -python -c 'import sage.all'`; use writable\n  temporary `DOT_SAGE` and `MPLCONFIGDIR` if normal caches are unavailable.\n  Check readable inputs and unused output paths. Missing dependency: stop\n  with \"I'm sorry, I can't do that — \u003Cmissing resource>. \u003CRecovery action>.\n  \u003CWhat it enables>.\" Never invent data.\n- State the question illustrated, input range, and intended audience. Fix\n  vertex\u002Fedge meaning, direction, multiplicity, weights, normalization, field,\n  axes, units, and color meaning as applicable before choosing an attractive\n  layout. A schematic is identified as schematic; its geometry is not data.\n\n## Generation and evidence\n\n1. Keep an editable Sage source file in the project's declared source location\n   and outputs in its declared figure location. Use repository-relative paths\n   and an explicit command; no hidden notebook state or absolute home paths.\n   Record input hashes, software versions, exact versus numerical arithmetic,\n   precision\u002Ftolerance, random seeds, and graph positions or layout seed.\n   See [the manifest contract](references\u002Fprovenance.md).\n2. Compute the quantity before plotting it. Record a small independent check:\n   e.g. vertex\u002Fedge counts and degree sums, row sums, trace\u002Feigenvalue sum,\n   exact characteristic polynomial, or an analytically known special case.\n   Report disconnected pieces, dropped rows, complex eigenvalues, multiplicity,\n   truncation, and sampling explicitly; never silently simplify a multigraph.\n3. Save a vector PDF for a compatible TeX engine and a PNG preview. Use SVG or\n   another format only when the project's build supports it. Use readable\n   labels at publication size and color plus labels\u002Fshapes\u002Fline styles when a\n   distinction matters. Do not use an image generator to fabricate a data plot.\n4. Inspect the rendered image for clipping, collisions, tiny type, misleading\n   scales, lost edge multiplicity, and colors unsupported by the data. Rendering\n   successfully is not a semantic check. Rerun in a fresh output directory and\n   compare the data\u002Finvariants; byte-identical PDFs are not required.\n5. Write the manifest with actual check results and unresolved limitations.\n   Keep its artifact hashes synchronized after every regeneration. An old\n   graphic with missing source is an imported asset with incomplete provenance,\n   not a newly reproduced computation.\n\nThe [runnable cycle template](assets\u002Fcycle_graph.py) demonstrates deterministic\ncoordinates, exact Sage checks, PDF\u002FPNG exports, and the manifest. Run it with\n`sage -python \u003Cskill-dir>\u002Fassets\u002Fcycle_graph.py \u003Cnew-output-dir>`; copy and adapt\nit to the project rather than importing this fixture as project research.\n\nReturn paths to source, inputs, rendered files, manifest, and a short caption\nbrief explaining what the picture supports and what it cannot establish.\nCall `add-figure` only when manuscript insertion is requested or part of the\nactive plan. Use `write-example` for a self-contained finite case, and\n`explain-experiment` for a broader computational investigation. Mathematical\nclaim promotions still require the normal contradiction\u002Fdoubt gates.\n",{"name":5,"description":7},"main","8d13efb5e66306aeae6e3b948bc463e7e2db1b65","skills\u002Fgenerate-graphics","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 generate-graphics",{"tool":38,"command":39},"bunx","bunx skills add tdupu\u002Fagent-skills-public --skill generate-graphics",{"tool":41,"command":42},"pnpm","pnpm dlx skills add tdupu\u002Fagent-skills-public --skill generate-graphics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fgenerate-graphics\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"assets\u002Fcycle_graph.py","SCRIPT","脚本",5886,"https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fgenerate-graphics\u002Fassets\u002Fcycle_graph.py",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fprovenance.md","REFERENCE","参考文档",2623,"https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fgenerate-graphics\u002Freferences\u002Fprovenance.md",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]