pd-background
Write the background and foundations section of an NSF Project Description for a mixed panel — the objects, the classical theory being generalized, the definitions a non-specialist needs (one sentence each, at first use), the prior literature on the same objects, and one worked example with real data. Use for "write the background", "they won't know what X is", "explain X", "add an example".
- License 许可
- GPL-3.0
- 最近更新
- 2026-11-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- pd-background
- description
- Write the background and foundations section of an NSF Project Description for a mixed panel — the objects, the classical theory being generalized, the definitions a non-specialist needs (one sentence each, at first use), the prior literature on the same objects, and one worked example with real data. Use for "write the background", "they won't know what X is", "explain X", "add an example".
03 SKILL.md 正文
pd-background
The background exists so that every later section can be read by a panelist outside the subfield. It is not a survey and not a paper's introduction.
Contents, in order
- The objects, with notation fixed once, and a sentence that heads off the most likely misreading (e.g. a group that looks like a familiar one but is not).
- What already exists on these objects: cite earlier work on the same groups/spaces before stating what the PI's work added. Never write as if the objects began with the PI.
- The classical theory and what it predicts, with the named theorems (S12-style classical anchors) and their exact scope: weight, level, field, hypotheses, conditional or not.
- Definitions for the panel: each term the later sections rely on (e.g. cuspidal/Eisenstein, Hecke eigensystem, tempered, Satake parameters, packets, inner forms, real loci) gets one plain sentence where first used.
- One worked example with real, verified data (
pd-data-table): a label unpacked field by field, a small table of values, and the diagnostic it illustrates. - The Software and AI assistance statement at the end
(
pd-ai-statement), when the PI places it here.
Rules
- Cite theorems with pinpoints only after
pd-fact-checkverified them. - Restate at most one classical theorem in an environment; the rest is prose.
- Every definition is used later; delete definitions nothing depends on.
- Do not explain the route to results here (no "we first tried").
04 同仓库更多 Skills
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
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
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
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
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code