Exa MCP Server is a Model Context Protocol server that connects AI agents to Exa's web search and research capabilities. It provides a standardized interface for agents to perform web searches, fetch webpage content, run multi-step research agents, and access other Exa functionalities. The architecture features clear separation of concerns with API handlers for Vercel deployment, core MCP server logic, tool implementations for each Exa capability, and utility functions for authentication, logging, and error handling. Key entry points include stdio CLI for local usage and Vercel HTTP functions for cloud deployment. The system handles authentication via API keys or OAuth, implements rate limiting for free tier users, and includes mechanisms to prevent API key leakage between requests.
This repository provides a two-skill workflow system for academic paper creation designed to work with Claude Code. The 'academic-paper-strategist' skill handles research planning through platform analysis, literature search, gap identification, and outline optimization with quality gates. The 'academic-paper-composer' skill executes systematic writing from outlines with chapter-level quality checks and final evaluation. The system emphasizes quality control through structured rubrics and iterative validation, transforming research ideas into submission-ready manuscripts with comprehensive quality reports. While primarily documentation-heavy, it contains several self-contained, reusable evaluation systems that demonstrate sophisticated assessment frameworks.
FigMirror is a reference-conditioned scientific figure style transfer system that iteratively generates matplotlib scripts matching the visual style of a reference figure. It operates as a multi-agent loop (Drawer/Reviewer) orchestrated by a runner backend (Codex, Claude, or Mock), with a local web UI for upload, iteration browsing, and refinement. The system is packaged as skills for both Claude Code and Codex, plus a standalone web server. While primarily an application, it has a strong research component: the prompts, aesthetic library, and evaluation benchmarks (PlotTwin-Bench) are the result of extensive empirical iteration. The codebase demonstrates high craftsmanship in its runner architecture, atomic file operations, SSE streaming, and deterministic review gates. However, it suffers from dual skill bundles (Claude/Codex) that must stay synchronized, retired artifacts, and some incomplete features (ClaudeRunner, SSE integration).
This is a monorepo of ~100 Claude Code skills — self-contained plugins that extend Claude Code's capabilities across personal automation, research, content creation, development tooling, and communication. Each skill is a directory with a SKILL.md (trigger definition), scripts/, references/, and assets/. The architecture is plugin-based: Claude Code matches user requests to skill triggers and executes the associated scripts. Skills range from simple CLI wrappers (e.g., YouTube transcript extraction) to multi-step pipelines (e.g., PII redaction with confide, release orchestration with cull-release, interview-driven skill design with skill-studio). The codebase demonstrates strong patterns: reversible PII redaction with typed placeholders, exact permutation statistics, weighted scoring with Pareto frontiers, and structured TDD loops. However, it also has technical debt: hardcoded user paths, some deprecated library usage, external API coupling, and a few design-spec-only skills. The dominant character is application (CLI tools and agent plugins), though several skills involve data analysis (health queries, experiment evaluation, evidence grading).
This repository is a curated list (awesome list) of open-source intelligence (OSINT) tools and resources. It is not a software application or a data research pipeline; it is a static markdown document that categorizes and links to hundreds of OSINT-related websites, tools, and services. The list covers a wide range of categories including search engines, social media tools, domain and IP research, people investigations, email search, phone number research, threat intelligence, and more. It is maintained by the community through pull requests and follows the awesome-list format. As a curated list, there is no executable code, no data ingestion, no transformation logic, and no analytical models. The value lies in the curation and organization of resources. The repository is primarily a reference for OSINT practitioners, researchers, and security professionals. While not a traditional software project, the list is well-structured and actively maintained. It can be easily cloned and used offline. However, from a software engineering perspective, there are no reusable components or architectural patterns to evaluate.