893 boosters for "ci" — open source, verified from GitHub, ready to install
Pipeline for downloading academic paper full-text at scale. Handles the three classes of sources that exist in 2026: 1. Publisher TDM APIs (Elsevier / Wiley / Springer) — for paywalled content where the institution has a subscription 2. OA aggregators (Unpaywall / OpenAlex / Crossref) — for Open Acc
"description": "LLM-powered personal wiki — autonomous knowledge base with research-on-miss, ingestion, search, a browsable web UI, and universal data gravity. Saves and retrieves knowledge automatically whenever relevant.", "repository": "https://github.com/Oshayr/llm-wiki", "agents/backlink-manage
WRAP is a decision-making framework that helps developers and AI systems work through major decisions by countering cognitive biases (narrow framing, confirmation bias, emotion, overconfidence). Best suited for product decisions, system design choices, or when stuck between technical approaches.
"name": "claude-mem-lite", "description": "Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-me
Treat the input file as the content source and the Word template as the formatting source. Do not expect pandoc or PDF import to infer template semantics. Build a project-specific Python postprocessor after inspecting the template and the converted body document. Do not treat the bundled starter pip
Named in homage to Tagore, whose prose carried what frontier models reach for and miss: a point of view, specificity over abstraction, and restraint over puffery. The skill exists to bring those qualities back to AI-drafted text. You are a writing editor whose job is to make prose sound like a human
Ozma is cursor-optimized rules for rapidly building customizable CRM/ERP systems with low-code development and full PostgreSQL integration. It benefits enterprises and developers needing quick enterprise-system deployment with minimal coding overhead.
Grasp is a metacognitive verification protocol that helps users achieve confirmed understanding of AI-generated results through structured dialogical verification. It benefits developers and collaborators who need to validate their comprehension of complex AI outputs.
"name": "agent-reachout", "description": "Multi-provider notification plugin for Claude Code", "name": "vibe-with-me-tools",
The user provides a sentence or paragraph that needs verification. The AI must NOT "run a quick search, glance at a few web snippets, and improvise a conclusion." It must dig down to original trustworthy sources, or honestly admit it cannot. Five scenarios are covered: 1. Basic truthfulness check: w
<!-- Bilingual skill: this SKILL.md is the English primary; the Chinese mirror is SKILL.zh.md. Each references/.md has a Chinese mirror references/.zh.md (same content, two languages). The .md files are authoritative for the agent; the .zh.md files are for human readers. -->
Generate a public-news-based information briefing for any subject (region / industry / policy issue / institution) and produce a single self-contained HTML file ready to paste into the 微信公众号 / WeChat Official Account editor. User says something like: Any descriptive request such as "make a briefing
Turn a folder of raw files into a Markdown vault that an LLM can grep, and then answer questions over that vault responsibly. source file, carrying retrieval frontmatter (abstract / tags / synonyms) + a
"name": "amplihack", "description": "AI-powered development framework with specialized agents and automated workflows for Claude Code", "name": "Microsoft Amplihack Team",
"name": "workflow-orchestrator", "version": "1.14.0", "description": "Delegation system with workflow orchestration, specialized agents, and parallel execution for Claude Code",
"name": "a11y-specialist-skills", "description": "Accessibility specialist skills for Claude Code. WCAG 2.2 review, conformance auditing, and improvement planning tools.", "url": "https://github.com/masuP9"
"name": "frontend-design-audit", "description": "Audit and improve front-end usability using 15 established design principles. Acts as a Senior UX designer/engineer reviewing your interface end-to-end.", "url": "https://github.com/mistyhx"
Heuristic scoring (no AI key configured).
"name": "claude-context-optimizer", "description": "ContextShield, CLAUDE.md analyzer, interactive dashboard, confidence learning, and token optimization for Claude Code", "name": "Egor Fedorov"
"name": "project-boundary", "description": "Blocks destructive commands outside the project directory. Allows file operations within the project (refactoring, cleanup) but prevents accidental damage outside it.", "name": "Justyna Wojtczak",
nano-spec is a lightweight, four-document specification methodology designed to help developers plan and document AI-assisted tasks in Windsurf through structured README, TODO, technical docs, and progress logs. It benefits teams wanting rapid, spec-driven development without heavyweight documentation overhead.
You are an AI Financial Coach. Not a calculator, not a chatbot that regurgitates generic tips. You know (or will learn) your user's complete financial picture and you work on their behalf — coaching them through every decision from a $7 coffee to a retirement plan.
当用户对已有导师 Skill 说以下内容时，进入进化模式： 本 Skill 运行在 Claude Code 环境，使用以下工具： 1. 不主动给出学术不端建议：不伪造数据、不抄袭、不代写造假
