claude-skills

Evaluate agent-generated code against ground truth diff and handwritten file list. Prefer reading GT inputs directly from base_repo via experiment metadata. Trigger on "/diff-eval-local", "evaluate diff", "eval experiment".

Full dev workflow - worktree setup, commit, push, PR, and post-merge cleanup. Use when starting feature work, committing, opening PRs, or cleaning up after merge.

Use when downloading models from Hugging Face, especially large models (LLM, diffusion, VLM) that fail with timeouts or connection drops. Trigger on "download model", "hf download", "pull model from Hugging Face", or when hf download crashes with httpx.ReadTimeout / RemoteProtocolError.

Evaluate agent-generated code changes against a human-approved PR with deterministic file coverage and function-level coverage analysis. Extracts function/symbol changes from diff hunk headers and compares at granular level. Use when evaluating agent code generation quality, benchmarking AI coding tools, or comparing generated patches against human-approved pull requests. Trigger on "/diff-eval-func", "evaluate diff with function coverage", "function-level diff eval".

从论文中提取图片，优先从arXiv源码包获取真正的论文图

深度分析单篇论文，生成详细笔记和评估，图文并茂

在已整理的论文笔记中搜索相关内容

每日研究工作流启动 - 生成论文推荐 + AI 行业动态笔记

Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when: reviewing academic papers, conducting literature reviews, writing research summaries, analyzing methodologies, formatting citations, or when user mentions academic research, scholarly writing, papers, or scientific literature.

Scan git diff incremental code for security vulnerabilities using multi-agent analysis with evolved prompts, RAG retrieval, and heuristic validation

Use when creating LaTeX Beamer presentations in Huawei internal report style, converting Huawei PPT to LaTeX, or building dense technical slides with dark-blue/red color scheme for project proposals (立项报告), technical reports, or competitive analysis decks.

Use when addressing Sourcery AI code review comments on a GitHub PR — iteratively fix comments, push, trigger re-review, poll for results, and repeat until approved. Trigger on "address sourcery comments", "fix review feedback", "sourcery review loop", or when a PR has unresolved Sourcery comments.

Use when analyzing a .pptx file's format, colors, fonts, layout, or design preferences. Trigger on requests like "analyze this PPT", "what colors does this slide use", "extract the style from this presentation".

Evaluate agent-generated code changes against a human-approved PR. Compares the local git diff (modified + untracked files, relative to the PR's merge base commit) with the ground truth PR diff, filters out auto-generated files, scores using a structured rubric (functional correctness, completeness, behavioral equivalence), and provides both semantic and data-based coverage analysis. Use when evaluating agent code generation quality, benchmarking AI coding tools, or comparing generated patches against human-approved pull requests. Trigger on "/diff-eval", "evaluate diff", "compare diff with PR", "score the changes".

Evaluate agent-generated code changes against a human-approved PR. Compares the local git diff (modified + untracked files, relative to the PR's merge base commit) with the ground truth PR diff, filters out auto-generated files, scores using a structured rubric (functional correctness, completeness, behavioral equivalence), and provides both semantic and data-based coverage analysis. Use when evaluating agent code generation quality, benchmarking AI coding tools, or comparing generated patches against human-approved pull requests. Trigger on "/diff-eval", "evaluate diff", "compare diff with PR", "score the changes".

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Use when user says "整理 inbox" or asks to organize, triage, or file notes from the 0-Inbox directory into the knowledge base.

将 SRT 字幕文件整理为结构完整、行文通顺的 Markdown 文档。适用于讲座、直播、访谈等口语转录的结构化整理。