Apply improvement plans from skill-quality-reviewer to Claude Skills. Groups edits by file, handles conflicting recommendations by priority, backs up originals, and verifies the updates before producing a report of changes and verification results.
Turn research code and experimental results into ML and AI paper drafts. The skill guides paper structure, related work searches, citation verification, and conference formatting with LaTeX, a document preparation system used for academic papers.
Review code changes and pull requests for correctness, security, performance, and test quality. The skill helps prioritize issues, write specific and constructive feedback, and create shared review checklists and standards for a development team.
Check academic references for existence, accurate publication details, and support for the claims being cited. This guide explains how to verify sources, obtain bibliography entries, and flag references that cannot be confirmed.
Create and configure Claude Code agents using Markdown files with YAML configuration headers. Define when each agent should run, write its responsibilities and workflow, choose models and tools, and check configuration and triggering behavior.
Investigate code errors through a structured process using reproduction steps, logs, and testable explanations. The workflow guides fault isolation, fixes, and follow-up checks, with common error patterns for Python, JavaScript/TypeScript, and Bash/Zsh.
Polish academic English or translate Chinese drafts using Nature and Nature Communications writing patterns. Review section logic before refining sentences, preserve the author's evidence and claims, and provide revised prose with brief notes explaining the main changes.
Create and organize Claude Code plugins with guidance on configuration files, commands, agents, skills, hooks, and MCP servers. Learn where components belong, how automatic loading works, and how to reference files across different installation locations.
Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.
Draft, audit, or revise responses to reviewers for Nature-family journals. Links each reviewer concern to manuscript evidence or a documented change, and identifies unanswered comments, missing author input, and issues that need resolution before submission.
Turn research results into figures and tables for papers using pubfig and pubtab. Choose an appropriate presentation, convert Excel tables to LaTeX, export assets, and check readability, labels, and consistency before submission.
Prepare conference slides, academic posters, and research promotion drafts from an accepted paper. The skill guides presentation timing, visual layout, and platform-specific writing while keeping claims and links tied to verified research materials.
Checks code changes before a pull request by reviewing builds, types, coding rules, tests, potential secrets, and changed files. Produces a report showing results, test coverage, and issues that need fixing.
Create or repair Claude skills in the current local environment. Clarify when each skill should run, streamline SKILL.md, organize supporting files, and check that referenced resources exist so the instructions remain consistent and reusable.
Draft or restructure scientific manuscripts using Nature-style argument patterns, starting from supplied results, figures, notes, or Chinese drafts. It organizes sections, connects claims to evidence, and identifies missing inputs while keeping conclusions within the research's demonstrated limits.
Organize papers from Zotero into an Obsidian project knowledge base. The skill separates source notes, research synthesis, and writing outputs, requiring evidence records and source links before findings become claims used in later work.
Organizes project literature reviews in Obsidian, turning paper notes into linked summaries, method categories, research gaps, and a visual map. Writing drafts and comparison tables follow only when claims meet the required evidence checks.
Inspect a running website at different screen sizes to find layout problems, inconsistent styling, and accessibility issues such as poor contrast. Fix the relevant source code, recheck the results, and report changes with before-and-after screenshots.
Add datasets, models, and other components to machine learning projects using consistent registration and creation patterns. The skill guides file placement, configuration, and automatic module loading so new components fit the project's established architecture.
Turn validated experiment analysis into an internal research report that supports decisions. Organize findings, statistical evidence, figure interpretations, limitations, and next actions, then save the report as Markdown or write it into a connected Obsidian knowledge base.
Co-write proposals, technical specifications, and decision documents through context gathering, section-by-section drafting, and revision. A fresh AI reader then tests the document to reveal unclear explanations, missing context, and contradictions before it is shared.
Prepare conference LaTeX template archives for writing in Overleaf. The skill identifies the main file and dependencies, proposes cleanup for approval, and organizes sections, resources, and a README with submission and compilation guidance.
Format Obsidian notes, repair internal links, and create registry tables and canvas diagrams. The skill handles formatting and derived files while leaving decisions about where knowledge belongs outside its scope.
Develop a vague research interest into a specific question and plan. Use 5W1H prompts, literature reviews, and analysis of unanswered questions to define hypotheses, required evidence, suitable methods, and a concrete next step.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)