Просмотр:

kstenerud

The Ultimate iOS Crash Reporter

JKHeadley

Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

frmoretto

Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.

issdandavis

AI governance through geometric cost scaling — 14-layer security pipeline using hyperbolic geometry to make adversarial attacks mathematically impossible. Open source. Patent pending. F1=0.813.

copyleftdev

Distributed adversarial behavioral security evaluation framework for LLMs - Swarm-based parallel probing with cryptographic consensus

LEE-SANG-BOK

Prevent i18n regressions for ko/en/vi (missing keys, long Vietnamese text UI breakage). Use when changing messages/*.json or adding user-facing strings. (키워드= 다국어, 번역, i18n, 메시지 키, ko/vi 키 동기화, 베트남어 긴 문장)

minchanpark

Локализованное описание: # Inbox One LLM Safety Use this skill for AI-flow and prompt-boundary review in Inbox One. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

E5presso

Локализованное описание: Build scalable Python apps with the power of DI & AOP # Monitor PR 인자: PR 번호. It covers aspect-oriented-programming, asyncio, dependency-injection workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

corv89

Human-in-the-loop execution for LLM agents

todofixthis

Use when creating Git commits — produces distinctive emoji-adorned commit messages with creative visual metaphors

u9401066

Complete feature development workflow orchestrating multiple skills from planning to deployment. Triggers: FD, 新功能, 開發功能, feature, implement, 實作, 實現, 建立功能, create feature, develop, 開發新, add feature, 加功能, 功能開發.

mims-harvard

Router skill for ToolUniverse tasks. First checks if specialized tooluniverse skills (54 skills covering disease/drug/target research, clinical decision support, genomics, transcriptomics, single-cell analysis, variant analysis, phylogenetics, statistical modeling, image analysis, epigenomics, chemical safety, systems biology, multi-omics integration, proteomics, metabolomics, spatial omics, immune repertoire analysis, and more) can solve the problem, then falls back to general strategies for using 1400+ scientific tools. Covers tool discovery, multi-hop queries, comprehensive research workflows, disambiguation, evidence grading, and report generation. Use when users need to research any scientific topic, find biological data, or explore drug/target/disease relationships.