Top Agent Skills

Guide for writing the abstract of an academic economics paper. Use this skill whenever the user asks for help writing, drafting, revising, or structuring an abstract for an economics paper - whether empirical micro, development economics, applied economics, or related fields. Also trigger when the user mentions "abstract," "paper summary," or asks how to compress their findings into a short description. This skill synthesizes best practices from David Evans (CGDev), Marc Bellemare, and patterns observed in top economics journals (AER, QJE, AEJ: Applied, etc.).

Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.

STATA code pattern library for empirical archival accounting research. Provides tested syntax from 126 peer-reviewed JAR (Journal of Accounting Research) replication files (2017-2025). Use when the user asks procedural questions like "How do I implement [method]?" or "Show me code for [technique]" — including: entropy balancing, propensity score matching (PSM), difference-in-differences (DiD), regression discontinuity (RDD), instrumental variables (IV), event studies (CAR/BHAR), survival analysis, Fama-MacBeth regressions, bootstrap, quantile regression, reghdfe/xtreg/areg, clustering standard errors, fixed effects, esttab/outreg2 table formatting, winsorization, leads/lags. Users can specify their variables (e.g., treatment, outcomes, controls) and receive adapted syntax. NOTE: This skill provides code patterns from published papers, not research design advice.

PROACTIVE SKILL — automatically apply whenever writing, generating, or editing any text that is mainly in Chinese. No user trigger needed. Also use when the user explicitly asks to "fix Chinese", "修改中文", "去翻译腔", "去AI味", "fix Chinese formatting", or "review Chinese text". Eliminates AI-sounding expressions and translation artifacts. Enforces Chinese-English mixed formatting rules (spacing, punctuation, bold formatting).

Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

R object-oriented programming guide for S7, S3, S4, and vctrs. Use when designing R classes or choosing an OOP system.

Generate academic referee reports for economics/finance papers, followed by a 150-word letter to the editor with recommendation (Reject / Major Revision) and Kai Wu signature. Two modes (normal / high-level), configurable number of comments; recommendation choice drives evaluation tone (Reject → negative, Major Revision → neutral). Trigger when user says "referee report" / "write referee report" / "审稿报告" / "写审稿意见" / "generate referee report" / "review this paper".

Expert copy editor for Quarto (.qmd) files. Checks grammar, spelling, punctuation, and academic writing quality. Produces a structured markdown report organized by document section — never modifies the source file. Use when asked to proofread, check grammar, fix typos, or review prose in a .qmd document. For APSA style rules (numbers, citations, capitalization, abbreviations, neutral language), use the apsa-style skill instead. Supports an optional output-file argument and an optional @sec-label argument to restrict checking to one section.

Structure responses to referee reports for R&R submissions

Verify references in an academic paper: check whether each BibTeX entry is real, whether in-text citations match the cited paper's actual content, and produce a structured verification report. Use when user says "验证参考文献", "ref verify", "check references", "核实引用", "引用是否正确", or wants to audit citations in a LaTeX manuscript.

Standardized Python & Stata coding practices for empirical research projects

Takes a proofread or apsa-style report file (or any markdown file using **Original:** / **Recommended:** syntax) and rewrites the original source file with git merge conflict markers so the user can accept or reject each suggested edit using VS Code or Positron's built-in merge conflict UI. Branch names are "original" and "claude-edits". Use when asked to apply edits, insert conflict markers, or set up merge resolution for a copy-edit report. Supports an optional @sec-label argument to restrict markers to one section.

Build ultra-fast web APIs and full-stack apps with Hono — runs on Cloudflare Workers, Deno, Bun, Node.js, and any WinterCG-compatible runtime.

Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance.

Documentation and capabilities reference for Daily

Connect to MAXIA AI-to-AI marketplace on Solana. Discover, buy, sell AI services. Earn USDC. 13 MCP tools, A2A protocol, DeFi yields, sentiment analysis, rug detection.

Vector-powered CLI for semantic file search with a Claude/Codex skill

Guided interview to Gold Code (100% AI-Readiness). Use when helping users improve their .faf file through questions. Leverages Claude Code's AskUserQuestion for seamless integration. Just type /faf-go and answer questions till done.

AI image generation skill powered by Google Gemini, enabling seamless visual content creation for UI placeholders, documentation, and design assets.

Interactive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization.

Clinically informed wisdom companion blending psychology and philosophy into a structured thinking partner

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Use DeepAPI for supported scraping, research, and email workflows with explicit credentials and approval.

Compact the current conversation into a handoff document for another agent to pick up.

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Write idiomatic PHP code with generators, iterators, SPL data structures, and modern OOP features. Use PROACTIVELY for high-performance PHP applications.

Generate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tone

Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.

Creates a structured design brief covering project overview, problem statement, target audience, goals, scope, context, deliverables, and timeline.

Structure compelling design presentations for stakeholders, reviews, and showcases.

Guides the design of effective, user-friendly, and accessible Power BI reports with optimal chart selection and layout design.

Discovers and installs agent skills from the open ecosystem when users ask for help with specific tasks or express interest in extending capabilities.

Audits iOS app source code and metadata to identify App Store rejection risks and optimization opportunities, producing a structured compliance report.

Define a set of actionable design principles that guide decision-making and resolve trade-offs.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens.

Provides expert guidance on modern Java 21+ development, including virtual threads, Spring Boot 3.x, GraalVM, and cloud-native patterns for building scalable enterprise applications.

Build and manage Supabase projects including Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, and Queues with security best practices.

Read, create, search, and manage notes in an Obsidian vault using the Obsidian CLI, with support for plugin and theme development workflows.

Provides design engineering guidance focused on animation principles, UI review, and interface craftsmanship.

Design high-converting landing pages with layout rules, hero section design, CTA psychology, and AI-generated visuals.

Select a consistent visual design system for PPT slides using radius/spacing style recipes, including Sharp, Soft, Rounded, and Pill variants with component mappings and typography rules.

Provides frontend design direction, design systems, visual philosophy, and production-grade UI styling for web interfaces, including layout critique, usability auditing, and asset generation.

Generates a Playwright test from a user-provided scenario by recording browser interactions via Playwright MCP, then saves and runs the test until it passes.

Formats responses for readers with ADHD by leading with actions, numbering steps, giving time estimates, and making progress visible.

Generate images using AI from OpenAI or Google Gemini, with support for textures, icons, sprites, and visual assets.

Search the web and extract content from URLs using Tavily and Exa APIs via the inference.sh CLI.

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances.

Hardens code against vulnerabilities by applying threat modeling, OWASP Top 10 prevention patterns, and secure coding practices for web applications.

Drafts professional emails that match your personal writing style by analyzing sent emails for tone, greeting, structure, and sign-off patterns.

Design a new PM skill through guided conversation, from raw idea to a structured, repo-compliant SKILL.md draft.

Articulate a compelling north-star product vision that aligns teams and guides strategic design decisions.

Design interfaces that adapt gracefully to multiple languages, writing directions, and cultural contexts.

Audits and upgrades existing websites and apps to premium quality by identifying generic AI patterns and applying high-end design standards without breaking functionality.

Extract clean markdown content from web pages by removing clutter, navigation, and ads to save tokens.

Check a screen's brand expression by comparing it against mood, voice, and design token reference files, flagging divergences and suggesting corrections.

Post-process AI-generated text through the unslop CLI to strip AI writing patterns before publishing.

Review local branch changes for bugs, security vulnerabilities, and code quality issues using a structured checklist-driven process.

Automate spreadsheet operations including creating workbooks, writing data, formatting cells, upserting rows, and managing worksheets across Microsoft Excel and Google Sheets.

Audits web performance by measuring Core Web Vitals (LCP, INP, CLS) and supplementary metrics, identifying render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps using Chrome DevTools MCP.