技能仓库

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when working with professional documents (.docx files): creating new documents, modifying content, working with tracked changes, adding comments, or handling other document tasks.

Microsoft SkillOpt wrapper for data-driven self-evolving agent skill optimization. Use when the user wants to train, benchmark, evaluate, or systematically improve natural-language skills with validation-gated iterations, best_skill.md artifacts, and trajectory-driven edits using the upstream Microsoft SkillOpt project.

将微信公众号文章转换为整洁的 Markdown 文件，自动去除广告、赞赏、推广等无关内容，处理代码块格式，支持图片和视频处理。当用户提供微信公众号链接或要求保存微信文章时使用此技能。

Optimizes database queries and improves performance across PostgreSQL and MySQL systems. Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for index design, query rewrites, configuration tuning, partitioning strategies, lock contention resolution.

设计精美的视觉艺术（PNG/PDF）Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

智能演示文稿创建工具。需求调研 → JSON 大纲 → 图表生成 → build-ppt.js 一键出稿。

Review Skill changes with structured severity-rated feedback covering frontmatter, routing conflicts, token budgets, references, scripts, tests, and repository conventions. Use when checking Jimu Skill quality before import, release, or pull request review.

Microsoft guidance for authoring high-quality Agent Skills, adapted for Jimu resource repositories. Use when creating new SKILL.md files, reviewing skill structure, checking frontmatter, organizing references/scripts, or aligning skill content with Jimu registry validation.

Microsoft Sensei workflow for iteratively improving skill frontmatter, trigger quality, compliance, token budget, reference integrity, and tests. Use when auditing or improving Jimu Skill metadata, routing behavior, or low-quality imported skills; supports lightweight Ralph-loop review and optional deeper GEPA-style optimization when dependencies are available.

Analyze Markdown and SKILL.md files for token efficiency while preserving clarity and required resources. Use when reducing verbose skill instructions, trimming duplicated Markdown, reviewing token bloat, or making AI-facing documentation more concise without breaking Jimu skill behavior.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Clean up text while preserving the writer's voice - minimal edits only