[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EW01RY6SWFBM1PX7NG3B1K":3,"skill-same:01M7EW01RY6SWFBM1PX7NG3B1K":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},"01M7EW01RY6SWFBM1PX7NG3B1K","using-pdpowers",null,"Routing skill for writing, revising, walking, fact-checking and checking an NSF Project Description (and its Project Summary). Use for \"write the project description\", \"revise the proposal\", \"walk the description with me\", \"fact-check the proposal\", \"write the prior support \u002F broader impacts \u002F AI statement\", \"fill the remaining pages\", or any request about NSF proposal prose. Routes each request to one pd-* leaf skill or to the grant checkers; the leaves encode how proposal writing differs from manuscript writing.","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\u002Fusing-pdpowers\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: using-pdpowers\ndescription: Routing skill for writing, revising, walking, fact-checking and checking an NSF Project Description (and its Project Summary). Use for \"write the project description\", \"revise the proposal\", \"walk the description with me\", \"fact-check the proposal\", \"write the prior support \u002F broader impacts \u002F AI statement\", \"fill the remaining pages\", or any request about NSF proposal prose. Routes each request to one pd-* leaf skill or to the grant checkers; the leaves encode how proposal writing differs from manuscript writing.\n---\n\n# using-pdpowers\n\nA Project Description is read once, fast, by a panel mostly outside the subject,\nand judged on what it will produce, whether the PI can do it, and whether every\nclaim can be trusted. Announce the route, then follow the leaf; leaves do not re-route.\n\n## Contracts and precedence\n\nBefore any edit, locate the proposal folder and read, in order:\n1. The PI's current instructions in the conversation.\n2. The grants workspace's decision records and contracts when they exist\n   (`CONTEXT.md`, `docs\u002Fadr\u002F`, `GRANT-STYLE.md`, `GRANT-FORMAT.md`).\n3. The proposal folder's `REVIEW.md`, `COMMENTS.md` and `reviews\u002F`.\n4. The solicitation and the PAPPG chapter it defers to. Check page limits\n   there; do not take them from memory.\n\nThe PI's instructions win; then the contracts; then these skills. No leaf\nstates a result the evidence does not support, whatever the instruction.\n\n## Dispatch\n\n| Situation | Route |\n|---|---|\n| New proposal folder from a template | `create-nsf-grant` (scaffold), then the leaves below per section |\n| \"Walk the description with me\", \"show me the next section\", PI annotations | `pd-section-walk` |\n| \"Is this true?\", claim\u002Fnumber\u002Fcitation\u002Fpinpoint checks, \"check the dates\" | `pd-fact-check` — run it before asking the PI anything a file or paper can answer |\n| Decisions the draft depends on (headline, scope, what to cut) | `grill-with-docs`, recording ADRs and glossary terms; then return here |\n| Overview \u002F headline \u002F solicitation framing | `pd-overview` |\n| Background, definitions for the panel, prior literature, classical anchor | `pd-background` |\n| Worked example, table of real records | `pd-data-table` (inside the section that needs it) |\n| Software and AI assistance statement for the proposal itself | `pd-ai-statement` |\n| Results from Prior NSF Support | `pd-prior-support` |\n| One proposed project (foundation, objective, preliminary results, plan, feasibility, risks) | `pd-project` |\n| Method, tools, orchestration, records, due diligence | `pd-method` |\n| Broader Impacts | `pd-broader-impacts` |\n| Project Summary | write last, from the finished description: `pd-overview` rules, one page, three headed parts, third person |\n| Reviewer-perspective pass (one subagent per role or named reviewer) | `pd-review-as`; reviewers from `gp-potential-reviewers` |\n| Apply a comment log or review tables to the draft | `pd-apply-feedback` |\n| “Is this paragraph good?” \u002F paragraph-by-paragraph pass over the description | `check-paragraph` — one subagent per paragraph via its `split_paragraphs.py`, reader = NSF panelist outside the subject; verdicts to `reviews\u002Fparagraphs-\u003Cfile>-\u003Cdate>.md`, no edits |\n| Policy audit (`references\u002FPD-POLICY.md`, P1–P17) | `python3 scripts\u002Fcheck_pd_policy.py \u003Cdescription.tex>` (mechanical rules), then the [J] rules by hand |\n| Style \u002F format audit (pages, fonts, headings, URLs, build) | `check-grant-style` \u002F `check-grant-format` |\n| \"Sounds like AI\", \"too many claudeisms\", de-slop (P17) | `purge-claudisms` — scan, rewrite hits in place, rescan to zero; before the style audit |\n| Mathematics that needs proving or a research gap | `using-mathpowers`, then return here |\n| Any other proposal document (references, data plan, facilities, budget and justification, COA, biosketch, current and pending, mentoring), Research.gov, UVMClick, SPA routing, package review | `using-grantpowers` |\n| A manuscript, not a proposal | `using-latexpowers` |\n\n## Floors every leaf enforces\n\n- **Only verified claims are results.** Published, submitted with the\n  statement untouched by referees, or checked by the PI. Agent output the PI\n  has not checked is \"agents report …\" or is held in `REVIEW.md`.\n- **Prose for the PI's results; environments for the panel's anchors.** Main\n  definitions in `definition`, main conjectures in `conjecture`, at most two\n  `theorem`s; the PI's own results in prose with citations (PD-POLICY P2–P3).\n- **Exact, sourced numbers.** Every number has a `REVIEW.md` row with its\n  source and date.\n- **Register.** Third person (\"the PI\", \"this proposal\"); direct, plain; no\n  hype, no sentence whose only content is importance, no run-in labels or\n  step lists (P1, P4, P5, P12). \"AI-assisted, human-driven\".\n- **Define for the panel.** Every term a non-specialist panelist would not\n  know is defined once, where first used, in one sentence.\n- **Show the data.** Prefer a small table of real, verified records over a\n  description of a schema.\n- **No process in the mathematics.** \"We initially believed\", earlier drafts,\n  and model chatter belong only in the AI statement.\n\n## Finish\n\nAfter each batch of edits: build; run `purge-claudisms`, `check_pd_policy.py`,\n`check-grant-style` and `check-grant-format`; confirm the page limits from the\nsolicitation; update `REVIEW.md`; report what changed, what is unverified, and\nwhat the PI must decide. Never commit, push, or submit unless the PI asks.\n","# using-pdpowers\n\nA Project Description is read once, fast, by a panel mostly outside the subject,\nand judged on what it will produce, whether the PI can do it, and whether every\nclaim can be trusted. Announce the route, then follow the leaf; leaves do not re-route.\n\n## Contracts and precedence\n\nBefore any edit, locate the proposal folder and read, in order:\n1. The PI's current instructions in the conversation.\n2. The grants workspace's decision records and contracts when they exist\n   (`CONTEXT.md`, `docs\u002Fadr\u002F`, `GRANT-STYLE.md`, `GRANT-FORMAT.md`).\n3. The proposal folder's `REVIEW.md`, `COMMENTS.md` and `reviews\u002F`.\n4. The solicitation and the PAPPG chapter it defers to. Check page limits\n   there; do not take them from memory.\n\nThe PI's instructions win; then the contracts; then these skills. No leaf\nstates a result the evidence does not support, whatever the instruction.\n\n## Dispatch\n\n| Situation | Route |\n|---|---|\n| New proposal folder from a template | `create-nsf-grant` (scaffold), then the leaves below per section |\n| \"Walk the description with me\", \"show me the next section\", PI annotations | `pd-section-walk` |\n| \"Is this true?\", claim\u002Fnumber\u002Fcitation\u002Fpinpoint checks, \"check the dates\" | `pd-fact-check` — run it before asking the PI anything a file or paper can answer |\n| Decisions the draft depends on (headline, scope, what to cut) | `grill-with-docs`, recording ADRs and glossary terms; then return here |\n| Overview \u002F headline \u002F solicitation framing | `pd-overview` |\n| Background, definitions for the panel, prior literature, classical anchor | `pd-background` |\n| Worked example, table of real records | `pd-data-table` (inside the section that needs it) |\n| Software and AI assistance statement for the proposal itself | `pd-ai-statement` |\n| Results from Prior NSF Support | `pd-prior-support` |\n| One proposed project (foundation, objective, preliminary results, plan, feasibility, risks) | `pd-project` |\n| Method, tools, orchestration, records, due diligence | `pd-method` |\n| Broader Impacts | `pd-broader-impacts` |\n| Project Summary | write last, from the finished description: `pd-overview` rules, one page, three headed parts, third person |\n| Reviewer-perspective pass (one subagent per role or named reviewer) | `pd-review-as`; reviewers from `gp-potential-reviewers` |\n| Apply a comment log or review tables to the draft | `pd-apply-feedback` |\n| “Is this paragraph good?” \u002F paragraph-by-paragraph pass over the description | `check-paragraph` — one subagent per paragraph via its `split_paragraphs.py`, reader = NSF panelist outside the subject; verdicts to `reviews\u002Fparagraphs-\u003Cfile>-\u003Cdate>.md`, no edits |\n| Policy audit (`references\u002FPD-POLICY.md`, P1–P17) | `python3 scripts\u002Fcheck_pd_policy.py \u003Cdescription.tex>` (mechanical rules), then the [J] rules by hand |\n| Style \u002F format audit (pages, fonts, headings, URLs, build) | `check-grant-style` \u002F `check-grant-format` |\n| \"Sounds like AI\", \"too many claudeisms\", de-slop (P17) | `purge-claudisms` — scan, rewrite hits in place, rescan to zero; before the style audit |\n| Mathematics that needs proving or a research gap | `using-mathpowers`, then return here |\n| Any other proposal document (references, data plan, facilities, budget and justification, COA, biosketch, current and pending, mentoring), Research.gov, UVMClick, SPA routing, package review | `using-grantpowers` |\n| A manuscript, not a proposal | `using-latexpowers` |\n\n## Floors every leaf enforces\n\n- **Only verified claims are results.** Published, submitted with the\n  statement untouched by referees, or checked by the PI. Agent output the PI\n  has not checked is \"agents report …\" or is held in `REVIEW.md`.\n- **Prose for the PI's results; environments for the panel's anchors.** Main\n  definitions in `definition`, main conjectures in `conjecture`, at most two\n  `theorem`s; the PI's own results in prose with citations (PD-POLICY P2–P3).\n- **Exact, sourced numbers.** Every number has a `REVIEW.md` row with its\n  source and date.\n- **Register.** Third person (\"the PI\", \"this proposal\"); direct, plain; no\n  hype, no sentence whose only content is importance, no run-in labels or\n  step lists (P1, P4, P5, P12). \"AI-assisted, human-driven\".\n- **Define for the panel.** Every term a non-specialist panelist would not\n  know is defined once, where first used, in one sentence.\n- **Show the data.** Prefer a small table of real, verified records over a\n  description of a schema.\n- **No process in the mathematics.** \"We initially believed\", earlier drafts,\n  and model chatter belong only in the AI statement.\n\n## Finish\n\nAfter each batch of edits: build; run `purge-claudisms`, `check_pd_policy.py`,\n`check-grant-style` and `check-grant-format`; confirm the page limits from the\nsolicitation; update `REVIEW.md`; report what changed, what is unverified, and\nwhat the PI must decide. Never commit, push, or submit unless the PI asks.\n",{"name":5,"description":7},"main","8d13efb5e66306aeae6e3b948bc463e7e2db1b65","skills\u002Fusing-pdpowers","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 using-pdpowers",{"tool":38,"command":39},"bunx","bunx skills add tdupu\u002Fagent-skills-public --skill using-pdpowers",{"tool":41,"command":42},"pnpm","pnpm dlx skills add tdupu\u002Fagent-skills-public --skill using-pdpowers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fusing-pdpowers\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002FPD-POLICY.md","REFERENCE","参考文档",6266,"https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fusing-pdpowers\u002Freferences\u002FPD-POLICY.md",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"scripts\u002Fcheck_pd_policy.py","SCRIPT","脚本",6474,"https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fusing-pdpowers\u002Fscripts\u002Fcheck_pd_policy.py",[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",[],[]]