[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F48ZPJQV8A63ZRGPM92PR4":3,"skill-same:01M7F48ZPJQV8A63ZRGPM92PR4":71},{"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":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":13,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7F48ZPJQV8A63ZRGPM92PR4","pycalphad",null,"Computes finite-temperature CALPHAD equilibria, phase fractions, and phase compositions from thermodynamic TDB databases using pycalphad. Use for alloy phase stability, equilibrium temperature sweeps, tie lines, lever-rule checks, or reproducible phase-fraction calculations with explicit components and mole-fraction conditions.","beanspowt\u002Fbeancode","beanspowt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F333943283?v=4","01M7F39F0GDWKS57BCKW8JJH7F","01M7F39F1B1TVPDJMS37BZQHWM",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fconfig\u002Fopencode\u002Fskills\u002Fpycalphad\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: pycalphad\ndescription: Computes finite-temperature CALPHAD equilibria, phase fractions, and phase compositions from thermodynamic TDB databases using pycalphad. Use for alloy phase stability, equilibrium temperature sweeps, tie lines, lever-rule checks, or reproducible phase-fraction calculations with explicit components and mole-fraction conditions.\nlicense: MIT\ncompatibility: Requires Python 3.12+, pycalphad 0.11.2, and NumPy. Installation needs network access; calculations run locally without credentials. Real-material predictions require a suitable licensed thermodynamic database.\nmetadata:\n  version: \"1.1\"\n  skill-author: K-Dense Inc.\n  tested-package-version: \"0.11.2\"\n  last-reviewed: \"2026-10-01\"\n---\n\n# pycalphad: TDB equilibrium calculations\n\n## When to use\n\nUse for equilibrium phase fractions and compositions at a fixed bulk elemental mole\ncomposition, specified pressure, and a list of finite temperatures. The bundled helper\nexecutes real pycalphad equilibria, checks mass balance, repeats at greater sampling\ndensity, and exports each stable composition set separately.\n\nEquilibrium is constrained by the selected database, components, phases, and conditions.\nIt does not predict precipitation rates, retained metastable microstructures, or properties\nof phases missing from the database. Successful numerical checks do not establish the\ndatabase's experimental accuracy.\n\n## Workflow\n\n1. Identify the TDB's source, license, assessment\u002Fpublication, valid temperature\u002Fpressure\n   and composition range, and required elements. Use the user's database for real alloys.\n   The bundled [assets\u002Fideal-cu-ni.tdb](assets\u002Fideal-cu-ni.tdb) is an original hypothetical\n   teaching model, **not an assessed Cu-Ni database**.\n2. Inspect database elements and phases. Select the relevant phases deliberately; record\n   exclusions because they can turn the calculation into a metastable constrained result.\n   Include `VA` where required by sublattice models. Vacancies are not an independent bulk\n   mole fraction. Keep coupled order\u002Fdisorder definitions in the TDB, but do not select\n   both partners as separate candidates when the ordered model already includes the\n   disordered contribution; the helper rejects such filtered candidate lists.\n3. Copy [assets\u002Fequilibrium.json](assets\u002Fequilibrium.json). Specify exactly N-1 elemental\n   mole fractions and one dependent non-vacancy element. The dependent fraction is\n   `1 - sum(independent fractions)`; fractions are not silently normalized. Set K and Pa.\n   Convert weight percentages or mass fractions before using this helper.\n4. Declare the database temperature interval from its assessment if known, or set\n   `database_temperature_range_k` to null if unknown. This is user-supplied evidence,\n   not a range automatically inferred from every TDB function. Requests outside a declared\n   interval fail. Check pressure and composition validity separately.\n5. Run the calculation. Check finite Gibbs energies, phase fractions summing to one,\n   reconstructed bulk composition, and stability to doubled `pdens` (phase-constitution\n   sampling density). Near transitions, refine temperatures and sampling density further.\n6. Deliver phase fractions with their **molar** basis, phase compositions, database hash,\n   conditions, excluded phases, and any numerical or assessment limitations.\n\nRead [references\u002Fmodel-and-validation.md](references\u002Fmodel-and-validation.md) for the\nanalytic example, basis conversion, native Model\u002FWorkspace\u002Fproperty\u002Fplot contracts,\nmiscibility-gap handling, and convergence limits.\n\n## Execute the tested example\n\nFrom the collection root:\n\n```bash\nuv run --no-project --python 3.12 --with pycalphad==0.11.2 --with numpy==2.5.3 \\\n  python skills\u002Fpycalphad\u002Fscripts\u002Fequilibrate.py \\\n  skills\u002Fpycalphad\u002Fassets\u002Fideal-cu-ni.tdb \\\n  skills\u002Fpycalphad\u002Fassets\u002Fequilibrium.json equilibrium-result\n```\n\nTested on Python 3.12, pycalphad 0.11.2, and NumPy 2.5.3. Use a new output directory.\nAll thermodynamic calculations are local; the script does not upload a TDB.\n\nFor the supplied hypothetical model at X(Ni)=0.5 and 101325 Pa:\n\n| Temperature | Equilibrium result |\n| --- | --- |\n| 900 K | FCC_A1 only |\n| 1100 K | 0.5 FCC_A1 + 0.5 LIQUID; X(Ni) approximately 0.527307 and 0.472693 respectively |\n| 1300 K | LIQUID only |\n\nThe suite verifies analytic common-tangent compositions, a noncentral lever-rule case,\nGibbs energy, mass balance, both single-phase limits, and actual same-phase miscibility\ngap vertices. These validate the computational workflow, not real Cu-Ni metallurgy.\n\n## Outputs and acceptance\n\n- `report.json`: settings and versions, TDB\u002Fsettings SHA-256, excluded database phases,\n  requested, solver-imposed, and reconstructed bulk compositions, per-temperature\n  baseline\u002Frefined results, and checks. Experimental validity is not evaluated by the helper.\n- `phase-equilibria.csv`: one row per stable vertex per temperature and sampling run,\n  including phase name, molar phase fraction, and elemental mole fractions. Its Gibbs\n  energy column is the **whole-system molar Gibbs energy**, repeated for each vertex;\n  it is not the individual phase energy.\n\nUnused pycalphad vertices have blank names and NaN values; those are omitted. Named\nvertices with invalid values cause failure. Multiple vertices with the same phase name\nare retained because a miscibility gap can contain two composition sets of one phase.\nVertex indices do not track the same physical phase continuously across temperatures.\n\nIn stable 0.11.2, pycalphad clips independent mole fractions to `[1e-10, 1-1e-10]`.\nEach result records `solver_bulk_mole_fractions` and the largest absolute difference\nfrom the requested bulk in `composition_condition_adjustment_absolute_error`.\nMass-balance checks still compare against the **requested** composition; a tighter\ntolerance can therefore fail at an endpoint. Do not claim exact pure-component or\nultratrace results from a clipped multicomponent calculation.\n\n`all_checks_passed` requires each run's phase-sum and bulk-composition residuals within\n`mass_balance_tolerance`, phase totals stable within `phase_fraction_tolerance`, and\nsystem Gibbs energy stable within `gibbs_energy_tolerance_j_per_mol` when `pdens` doubles.\nThis comparison does not certify the global minimum or track individual composition-set\nmovement within a same-phase miscibility gap; inspect their exported compositions too.\nFailed checks remain visible in the report rather than being relabeled as convergence.\n\n## Boundaries and upstream contracts\n\nThe helper handles elemental mole fractions, one composition, one pressure, and up to\n1000 explicit positive temperatures. It validates selected phases through pycalphad's\nphase-compatibility rules; incompatible or automatically filtered order\u002Fdisorder phase\nsets produce an explicit error. It does not silently remove requested phases.\n\nCharged-species constraints, externally imposed chemical potentials, custom models,\nactivity reference-state changes, and database optimization require additional modeling\nand are outside this helper's tested scope. Do not extrapolate the pedagogical asset to\nreal material selection or heat-treatment decisions.\n\n- [Equilibrium dataset semantics](https:\u002F\u002Fpycalphad.org\u002Fdocs\u002Flatest\u002Fexamples\u002F3_High_Throughput_Analysis\u002F2_UsingCalculationResults.html)\n- [Phase fractions and composition basis](https:\u002F\u002Fpycalphad.org\u002Fdocs\u002Flatest\u002Fexamples\u002F2_Computing_Properties\u002F1_PhaseCompositions.html)\n- [Equilibrium and sampling API](https:\u002F\u002Fpycalphad.org\u002Fdocs\u002Flatest\u002Fapi\u002Fpycalphad.core.html)\n- [Ordering examples](https:\u002F\u002Fpycalphad.org\u002Fdocs\u002Flatest\u002Fexamples\u002F2_Computing_Properties\u002F4_EquilibriumWithOrdering.html)\n- [Stable 0.11.2 source](https:\u002F\u002Fgithub.com\u002Fpycalphad\u002Fpycalphad\u002Ftree\u002F0.11.2\u002Fpycalphad)\n\nUpstream `latest` documentation currently describes 0.11.3 development builds. The\nbundled helper and the reference's native examples were exercised against stable\n0.11.2 on 2026-10-01; the release's source was checked against the installed wheel.\nNo remote thermodynamic calculation or database-fetch API is used. `Database` loads a\nlocal path, file-like object, or TDB text; a URL is not a supported download shortcut.\n","# pycalphad: TDB equilibrium calculations\n\n## When to use\n\nUse for equilibrium phase fractions and compositions at a fixed bulk elemental mole\ncomposition, specified pressure, and a list of finite temperatures. The bundled helper\nexecutes real pycalphad equilibria, checks mass balance, repeats at greater sampling\ndensity, and exports each stable composition set separately.\n\nEquilibrium is constrained by the selected database, components, phases, and conditions.\nIt does not predict precipitation rates, retained metastable microstructures, or properties\nof phases missing from the database. Successful numerical checks do not establish the\ndatabase's experimental accuracy.\n\n## Workflow\n\n1. Identify the TDB's source, license, assessment\u002Fpublication, valid temperature\u002Fpressure\n   and composition range, and required elements. Use the user's database for real alloys.\n   The bundled [assets\u002Fideal-cu-ni.tdb](assets\u002Fideal-cu-ni.tdb) is an original hypothetical\n   teaching model, **not an assessed Cu-Ni database**.\n2. Inspect database elements and phases. Select the relevant phases deliberately; record\n   exclusions because they can turn the calculation into a metastable constrained result.\n   Include `VA` where required by sublattice models. Vacancies are not an independent bulk\n   mole fraction. Keep coupled order\u002Fdisorder definitions in the TDB, but do not select\n   both partners as separate candidates when the ordered model already includes the\n   disordered contribution; the helper rejects such filtered candidate lists.\n3. Copy [assets\u002Fequilibrium.json](assets\u002Fequilibrium.json). Specify exactly N-1 elemental\n   mole fractions and one dependent non-vacancy element. The dependent fraction is\n   `1 - sum(independent fractions)`; fractions are not silently normalized. Set K and Pa.\n   Convert weight percentages or mass fractions before using this helper.\n4. Declare the database temperature interval from its assessment if known, or set\n   `database_temperature_range_k` to null if unknown. This is user-supplied evidence,\n   not a range automatically inferred from every TDB function. Requests outside a declared\n   interval fail. Check pressure and composition validity separately.\n5. Run the calculation. Check finite Gibbs energies, phase fractions summing to one,\n   reconstructed bulk composition, and stability to doubled `pdens` (phase-constitution\n   sampling density). Near transitions, refine temperatures and sampling density further.\n6. Deliver phase fractions with their **molar** basis, phase compositions, database hash,\n   conditions, excluded phases, and any numerical or assessment limitations.\n\nRead [references\u002Fmodel-and-validation.md](references\u002Fmodel-and-validation.md) for the\nanalytic example, basis conversion, native Model\u002FWorkspace\u002Fproperty\u002Fplot contracts,\nmiscibility-gap handling, and convergence limits.\n\n## Execute the tested example\n\nFrom the collection root:\n\n```bash\nuv run --no-project --python 3.12 --with pycalphad==0.11.2 --with numpy==2.5.3 \\\n  python skills\u002Fpycalphad\u002Fscripts\u002Fequilibrate.py \\\n  skills\u002Fpycalphad\u002Fassets\u002Fideal-cu-ni.tdb \\\n  skills\u002Fpycalphad\u002Fassets\u002Fequilibrium.json equilibrium-result\n```\n\nTested on Python 3.12, pycalphad 0.11.2, and NumPy 2.5.3. Use a new output directory.\nAll thermodynamic calculations are local; the script does not upload a TDB.\n\nFor the supplied hypothetical model at X(Ni)=0.5 and 101325 Pa:\n\n| Temperature | Equilibrium result |\n| --- | --- |\n| 900 K | FCC_A1 only |\n| 1100 K | 0.5 FCC_A1 + 0.5 LIQUID; X(Ni) approximately 0.527307 and 0.472693 respectively |\n| 1300 K | LIQUID only |\n\nThe suite verifies analytic common-tangent compositions, a noncentral lever-rule case,\nGibbs energy, mass balance, both single-phase limits, and actual same-phase miscibility\ngap vertices. These validate the computational workflow, not real Cu-Ni metallurgy.\n\n## Outputs and acceptance\n\n- `report.json`: settings and versions, TDB\u002Fsettings SHA-256, excluded database phases,\n  requested, solver-imposed, and reconstructed bulk compositions, per-temperature\n  baseline\u002Frefined results, and checks. Experimental validity is not evaluated by the helper.\n- `phase-equilibria.csv`: one row per stable vertex per temperature and sampling run,\n  including phase name, molar phase fraction, and elemental mole fractions. Its Gibbs\n  energy column is the **whole-system molar Gibbs energy**, repeated for each vertex;\n  it is not the individual phase energy.\n\nUnused pycalphad vertices have blank names and NaN values; those are omitted. Named\nvertices with invalid values cause failure. Multiple vertices with the same phase name\nare retained because a miscibility gap can contain two composition sets of one phase.\nVertex indices do not track the same physical phase continuously across temperatures.\n\nIn stable 0.11.2, pycalphad clips independent mole fractions to `[1e-10, 1-1e-10]`.\nEach result records `solver_bulk_mole_fractions` and the largest absolute difference\nfrom the requested bulk in `composition_condition_adjustment_absolute_error`.\nMass-balance checks still compare against the **requested** composition; a tighter\ntolerance can therefore fail at an endpoint. Do not claim exact pure-component or\nultratrace results from a clipped multicomponent calculation.\n\n`all_checks_passed` requires each run's phase-sum and bulk-composition residuals within\n`mass_balance_tolerance`, phase totals stable within `phase_fraction_tolerance`, and\nsystem Gibbs energy stable within `gibbs_energy_tolerance_j_per_mol` when `pdens` doubles.\nThis comparison does not certify the global minimum or track individual composition-set\nmovement within a same-phase miscibility gap; inspect their exported compositions too.\nFailed checks remain visible in the report rather than being relabeled as convergence.\n\n## Boundaries and upstream contracts\n\nThe helper handles elemental mole fractions, one composition, one pressure, and up to\n1000 explicit positive temperatures. It validates selected phases through pycalphad's\nphase-compatibility rules; incompatible or automatically filtered order\u002Fdisorder phase\nsets produce an explicit error. It does not silently remove requested phases.\n\nCharged-species constraints, externally imposed chemical potentials, custom models,\nactivity reference-state changes, and database optimization require additional modeling\nand are outside this helper's tested scope. Do not extrapolate the pedagogical asset to\nreal material selection or heat-treatment decisions.\n\n- [Equilibrium dataset semantics](https:\u002F\u002Fpycalphad.org\u002Fdocs\u002Flatest\u002Fexamples\u002F3_High_Throughput_Analysis\u002F2_UsingCalculationResults.html)\n- [Phase fractions and composition basis](https:\u002F\u002Fpycalphad.org\u002Fdocs\u002Flatest\u002Fexamples\u002F2_Computing_Properties\u002F1_PhaseCompositions.html)\n- [Equilibrium and sampling API](https:\u002F\u002Fpycalphad.org\u002Fdocs\u002Flatest\u002Fapi\u002Fpycalphad.core.html)\n- [Ordering examples](https:\u002F\u002Fpycalphad.org\u002Fdocs\u002Flatest\u002Fexamples\u002F2_Computing_Properties\u002F4_EquilibriumWithOrdering.html)\n- [Stable 0.11.2 source](https:\u002F\u002Fgithub.com\u002Fpycalphad\u002Fpycalphad\u002Ftree\u002F0.11.2\u002Fpycalphad)\n\nUpstream `latest` documentation currently describes 0.11.3 development builds. The\nbundled helper and the reference's native examples were exercised against stable\n0.11.2 on 2026-10-01; the release's source was checked against the installed wheel.\nNo remote thermodynamic calculation or database-fetch API is used. `Database` loads a\nlocal path, file-like object, or TDB text; a URL is not a supported download shortcut.\n",{"name":5,"license":14,"metadata":23,"description":7,"compatibility":28},{"version":24,"skill-author":25,"last-reviewed":26,"tested-package-version":27},"1.1","K-Dense Inc.","2026-10-01","0.11.2","Requires Python 3.12+, pycalphad 0.11.2, and NumPy. Installation needs network access; calculations run locally without credentials. Real-material predictions require a suitable licensed thermodynamic database.","main","66c9bd32ac14a921980362cf85872a1c402101c2","config\u002Fopencode\u002Fskills\u002Fpycalphad","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode","https:\u002F\u002Fgithub.com\u002Fbeanspowt","2026-11-10 23:22:33",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add beanspowt\u002Fbeancode --skill pycalphad",{"tool":41,"command":42},"bunx","bunx skills add beanspowt\u002Fbeancode --skill pycalphad",{"tool":44,"command":45},"pnpm","pnpm dlx skills add beanspowt\u002Fbeancode --skill pycalphad","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fconfig\u002Fopencode\u002Fskills\u002Fpycalphad\u002FSKILL.md",true,[49,55,59,65],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"assets\u002Fequilibrium.json","ASSET","资产文件",443,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fconfig\u002Fopencode\u002Fskills\u002Fpycalphad\u002Fassets\u002Fequilibrium.json",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"assets\u002Fideal-cu-ni.tdb",702,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fconfig\u002Fopencode\u002Fskills\u002Fpycalphad\u002Fassets\u002Fideal-cu-ni.tdb",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fmodel-and-validation.md","REFERENCE","参考文档",10048,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fconfig\u002Fopencode\u002Fskills\u002Fpycalphad\u002Freferences\u002Fmodel-and-validation.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fequilibrate.py","SCRIPT","脚本",11112,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fconfig\u002Fopencode\u002Fskills\u002Fpycalphad\u002Fscripts\u002Fequilibrate.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7F6BB3VS43C65P23JR4ZN5G","venue-templates","Prepares journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Supports selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fvenue-templates\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7F6B4CBVEHY1RKVW55X8484","scientific-writing","Drafts, revises, and audits scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency checks. Use for manuscript sections, references, declarations, tables, figures, or submission preparation when scientific accuracy and traceability matter.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-writing\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7F6AXKSP5AXE8B7RCE1KP0C","scientific-visualization","Creates and audits truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use it for figure design, multi-panel layouts, uncertainty and missing-data displays, color\u002Fcontrast review, image metadata validation, and journal export planning.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-visualization\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M7F6AMRHS0QH64CMKE8TP9Y7","scientific-slides","Builds slide decks and presentations for research talks. Used for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-slides\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M7F6ACZ7GQJNNW0682235MC3","scientific-schematics","Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when the review requests improvement, with at most two generations. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-schematics\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M7F6A2JDHTYABYSA4NCE82VG","research-grants","Supports research proposal preparation and review for NSF, NIH, DOE, DARPA, and Taiwan NSTC, including opportunity-specific requirements, aims, review criteria, budgets, broader impacts, forms, and resubmissions. Use for investigator-authored grant development, compliance matrices, and proposal critiques.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fresearch-grants\u002FSKILL.md",[],[]]