688 boosters for "skill" — open source, verified from GitHub, ready to install
Use this skill as a global-installable, project-level rebuttal workspace assistant. The installed skill provides reusable procedures and assets; each actual paper/rebuttal workspace gets its own state folder for memory, snapshots, template state, and logs. Start by understanding the workspace, then
Build reusable skill packages, not long prompts. Mode rules: Operating Modes, QA Ladder, Resource Boundary Spec, Method. 1. Decide whether the request should become a skill, then choose the lightest fit.
"name": "bundles-forge", "description": "Bundle-plugin engineering toolkit: scaffolding, platform adaptation, version management, and skill lifecycle", "email": "odradekai@outlook.com"
"name": "apple-skills", "description": "Apple development skills for Claude Code and Codex — iOS 26+ APIs, SwiftUI, UIKit, Liquid Glass, SwiftData, and more.", "name": "Prisma Labs"
Lint agent configurations before they break your workflow. Validates Skills, Hooks, MCP, Memory, Plugins across Claude Code, Cursor, GitHub Copilot, and Codex CLI. Invoke when user asks to: If not found, install:
This is the universal AI skills library — 204 production-ready skill packages across 13 professional domains with 559 Python automation tools and 12 sample CI/CD workflows. It works with every major AI coding assistant. This is NOT a traditional application. It's a library of self-contained skill pa
A specialized diagnostic tool for data engineers to systematically investigate Airflow DAG failures, identify root causes, and implement prevention strategies. Ideal for complex pipeline debugging scenarios requiring deep analysis beyond basic log inspection.
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "intellectronica-skills", "description": "A curated collection of agent skills for Claude Code and Cowork",
No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidates when they grow, and recovers anything missed. Five layers of redundancy, zero maintenance. ~$0.00/month (using free-tier models). While other memory skills ask you t
"name": "Jimmy Yao", "email": "dev.jimm.py@gmail.com" "description": "Creative writing agents and skills for Claude Code",
"name": "comfyui-custom-node-skills", "description": "Skills for building ComfyUI custom nodes with the V3 and V1 Python APIs" "name": "comfyui-custom-nodes",
"name": "linus-torvalds-skills", "description": "Aggressive AI coding guidelines recast through Linus Torvalds' blunt, data-first engineering style", "name": "forrestchang"
"name": "qt-development-skills", "description": "Agentic engineering skills for Qt software development, including Qt C++/QML code review, QML coding, and Qt C++/QML code documentation. Bundles the hosted Qt Documentation MCP server for live Qt API lookups. These skills use AI and can make mistakes.
→ 如果用户已提供，直接确认，不重复询问 → JD 可不完整，有多少给多少；简历没有也能出题（基于 JD 理想候选人画像） 将 JD 内容整理为结构化需求清单（内部使用）：
当用户对已有暗恋对象 Skill 说以下内容时，进入进化模式： 当用户说 时列出所有已生成的暗恋对象。 本 Skill 运行在 Claude Code 环境，使用以下工具：
Generate images using ModelScope's Tongyi-MAI/Z-Image-Turbo model. Optional: Set to use your own API key.
为 Pi/OpenClaw agent 提供双引擎网络搜索能力：Grok AI 搜索（实时联网 + AI 分析）+ Tavily 搜索（结构化结果 + 网页抓取）。 在 Bash 中调用以下脚本（确保已加入 PATH 且已 source .env）： 对于 Level 2+ 的复杂搜索，在执行前进行结构化规划：
List installed skills and their status, or create new skills. On invocation, scan skills and present: When user selects a skill:
"name": "agent-session-resume", "description": "Adds the agent-session-resume skill for reconstructing and continuing prior AI coding-agent sessions.", "name": "hacktivist123"
Skyll enables agents to dynamically discover and retrieve skills at runtime. Instead of having all skills pre-loaded, agents can search for relevant skills on-demand and inject them into context. Get a specific skill: The API returns ranked skills with relevance scores (0-100):
"version": "0.46.0", "description": "Build and deploy web apps and agents", "url": "https://github.com/vercel"
"description": "UniFi network management CLI, TUI, and AI agent skill for full infrastructure control", "name": "Stefanie Jane", "url": "https://hyperbliss.tech"
底层原则：先定角色，再拆内容，最后生成图解。 本 Skill 不是头像生成器，也不是自由风格生图器。它的目标是把用户授权提供的个人材料转成一套可长期复用的极简手绘图解角色，再用这个角色和执行 Agent 一起参与内容表达。 推荐在支持图片读取、较高推理强度和图像生成工具的 Agent 环境中使用。这样可以直接完成图片读取、角色建档、三张角色资产生成、内容图解生成和返修。
"name": "sap-skills", "description": "Production-ready skills for SAP development and AI coding assistants", "repository": "https://github.com/secondsky/sap-skills",
