一键导入
agent-config
agent-config 收录了来自 yzhao062 的 17 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。
这个仓库中的 skills
Context-aware router that detects work type (papers, proposals, code, figures, admin) and dispatches to the right domain skill. Works within superpowers' execution phase as the inner decision loop.
Use when auditing a paper's existing .bib for hallucinated citations or stale metadata before submission, especially when bib entries came from co-authors or automated tools and may include fabricated authors, future arXiv IDs, or preprints already published in peer-reviewed venues. Companion to bibref-filler (which adds new citations); this skill audits existing ones.
Build copy-ready prompts for downstream LLM figure generation from source text, figure ideas, prior examples, or rough drafts. Use when Codex needs to decide whether a section needs a figure, distill the figure's core message and required visual elements, draft a model-neutral prompt pack for image-generation models, adapt prompts to a requested tool, or recommend limited cleanup after external generation.
Compose NSF proposal outlines and section drafts from a project idea, prior proposal examples, and solicitation requirements. Use when Codex needs to choose between ecosystem-building and methodology-driven proposal families, turn a brief into a proposal structure, draft or refresh LaTeX sections, introduce an optional cross-section running example for abstract infrastructure proposals, or keep summary, aims, evaluation, and impact sections aligned during proposal writing.
Unified NSF proposal requirements, question-answering, and preflight checking for a single proposal repository. Use when a user has an NSF solicitation PDF/text and needs to (1) ingest and normalize proposal requirements, (2) ask drafting-time questions such as "do we need X?" or "where does this go?", or (3) run a pre-submission gap check against the current proposal files.
Refine one or more NSF thrust, aim, or study files after the initial scaffold exists. Use when Codex needs to deepen a core proposal unit with sharper gaps, local literature grounding, concrete technical measures, evaluation hooks, reviewer-facing running examples or artifact sketches, figure ideas, or visible TODO placeholders while preserving alignment with the current intro, summary, and evaluation plan.
Create 1-page or 2-page CV variants from a longer master LaTeX CV. Use when the user asks for a short CV, concise CV, one-page CV, two-page CV, resume-style version, or a role-specific application CV derived from `Latex/sample_cv.tex` or another master CV source.
Draft grounded area chair, senior area chair, or editor style meta reviews for computer science and machine learning papers from the paper PDF, external reviews, reviewer discussion, rebuttal, and venue decision scale. Use when Codex needs to synthesize reviewer consensus, summarize rebuttal impact, recommend a final decision, or write venue-specific meta reviews for venues such as TNNLS, ICML, NeurIPS, or similar.
Draft grounded peer reviews for computer science and machine learning papers from a paper PDF, extracted text, venue form, and user notes. Use when Codex needs to write, rewrite, or refine a conference or journal review with strengths, weaknesses, author questions, score justification, rebuttal follow-up, or ethics comments for venues such as IJCAI, NeurIPS, ICML, TNNLS, or similar.
Assemble a coherent USC Beamer talk from the reusable Yue Zhao intro module and one or more existing paper decks in this repo. Use when the user wants a merged deck with light bridge slides, trimmed duplicate wrappers, and one throughline, without regenerating each paper talk from scratch.
Add or tighten bibliography citations in NSF proposal sections such as the intro, summary, team qualification, evaluation, and thrust files. Use when Codex needs to place bibrefs conservatively, prefer existing local cite keys for the team's own work, respect user-specified citation density, verify every inserted citation against local .bib files or primary-source metadata, and leave visible TODOs instead of guessing.
Convert an academic paper's LaTeX source, figures, and bibliography into a complete 20-25 minute Beamer presentation using the local USC Moloch template. Use when the user wants a paper turned into a reusable technical deck with core, optional, and backup paths, especially from `.tex`, figure, and `.bib` files in this repo.
Generate a reusable 2-3 slide Yue Zhao / FORTIS Lab intro insert from local website-first sources in this repo. Use when the user wants a stable identity, agenda, and representative-systems module that can be merged into other decks. Do not use this skill for full paper talks, mini-CV decks, or automatic deck insertion.
Standardize intake, evidence collection, precheck, packet assembly, and status tracking for USC reimbursement and expense-report workflows. Use when Codex needs to turn scattered USC reimbursement materials such as receipts, emails, approvals, travel details, and policy notes into a clean case folder, identify missing information, prepare a submission checklist, or maintain repeatable administrative workflows in this repo.
Build copy-ready prompts for explanatory figures such as overviews, architectures, mechanisms, workflows, timelines, and conceptual illustrations from source text, figure ideas, reference figures, or rough drafts. Use when Codex needs to decide whether a section needs an explanatory figure, distill the figure's core message and required visual elements, select a small number of structural or style donors from a reference bank, draft a model-neutral prompt pack for image-generation models, adapt prompts to a requested tool, or recommend limited cleanup after external generation.
Add new external bibliography citations in existing prose without inventing support. Use when Codex needs to find real papers from canonical sources, verify exact metadata before citation, add machine-generated entries into a separate working bibliography next to the active main bib files, avoid polluting curated bibs, and leave visible TODOs instead of guessing. Useful for proposals, papers, slides, rebuttals, and other technical writing where the prose mostly exists and the main task is safe external citation support.
Structure a task into a first pass and an optional second pass without replacing the domain skill. Use when Codex or Claude Code should collaborate on paper reviews, bug fixes, writing, website edits, research memos, or other tasks where one pass produces the main artifact and a later pass may check or refine it.