Featured
AI skills
New 2026
Static analyzer for AI coding-agent context — and an Agent Skill your agent can run. Measures always-on context cost of CLAUDE.md, AGENTS.md and Agent Skills; finds skills that won't load, redundant instructions, stale paths and duplicate names. Claude Code, Codex, Cursor, Gemini CLI. Research project.
New 2026
One-to-one AI teaching skills (Alvar method) for Codex, Claude Code, Grok, Pi, and OpenCode
New 2026
Security-testing methodology as portable, tool-agnostic agent skills for Claude Code and any agent runtime: white-box bug hunting, AI-agent and LLM red-teaming, supply-chain risk, and appsec depth.
New 2026
AI skill for diagnosing, structuring, writing, and evaluating Chinese lead-generation short-video scripts.
New 2026
毛选·战略与矛盾分析：把《毛泽东选集》的战略思维、矛盾分析法、调查研究转译为可直接套用的分析与执行框架（WorkBuddy / Claude Code 等 Agent 可加载的 Skill）。
New 2026
Agent skills for the UE5 decisions that fail silently — authority vs. cosmetic, hit contracts, state ownership, spawn frames, phase bans, and engine feature maturity.
New 2026
Stop repeating yourself to your AI. This MCP auto-discovers your custom coding rules and skills across your device, letting any AI agent (Claude, Cursor, OpenCode) automatically apply your preferred standards.
New 2026
Portable Agent Skill for repository-native Spec programming, informed by public DeepSeek Harness engineering patterns.
New 2026
Measure what a learner can actually do before teaching. Adaptive diagnostic, prerequisite-aware study plans, and evidence-based mastery tracking where deterministic scripts hold every score — not the model. An Agent Skill for Claude Code, Codex, Cursor, and any Agent Skills client.
New 2026
在 DeepSeek Harness 一键安装技能插件，让 AI 通过本地 RESTful API（HTTP/SSE/WebSocket）接管齐治堡垒机里的服务器；任何能发 HTTP 的 AI 均可接入。
Other topics
Browse other topics on Trendshift
A
N