ShadyUnderLight/deep-research-skill
面向 OpenClaw / Codex Agent 的决策导向 deep research skill，强调任务路由、证据可追溯、current-state verification、反证约束与可审计交付。
面向 OpenClaw / Codex Agent 的决策导向 deep research skill，强调任务路由、证据可追溯、current-state verification、反证约束与可审计交付。
npx skills add ShadyUnderLight/deep-research-skill面向 OpenClaw / Codex Agent 的决策导向 deep research skill，强调任务路由、证据可追溯、current-state verification、反证约束与可审计交付。
Claude Code skill plugin for safe, automated GitHub releases with supply chain security
图形学与3DGS、空间智能持续更新论文；AI Agent Skills for 3D Gaussian Splatting, NeRF & Computer Graphics Research. 660+ methods, 25categories, 12skills. OpenClaw / Claude Code compatible.
Versioned AI development workflow standard for BDA teams: neutral commands, verification, feedback loop, Codex and Claude support
Codex-native engineering workflow skills plugin marketplace
Provide AI-driven CLI control for Things 3 on macOS using AppleScript, URL schemes, and secure SQLite access to automate task management.
Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.