9 skills found
pegasi-ai / reinsStop AI agents from doing things you didn't ask for.
team-attention / qaRequirements-first Harness — derive, verify, execute.
bridge-mind / BridgeWardTrust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.
heliohq / qaAn agentic development harness for Claude Code, Codex & Cursor: gated pipeline from spec to green checks.
benjam3n / lpNot all interventions are equal. In any complex system, there are places. Read and execute `/home/ben/Documents/projects/reasoningtool/claude-code-plugin/skills/lp/SKILL.md`, applying it to this input: $ARGUMENTS
davenicoll / cursor-rulesA style guide for Cursor rules—covering clean-code practices, architecture guidelines, language-specific rules and guidelines for tooling usage
sr-ai-dev / qa시스콘 로보틱스 사내 표준 하네스 (hoyeon fork)
SonicBotMan / labor-rights-defense🛡️ 中国劳动维权方法论 AI Agent Skill — 基于 2025 司法解释二 + 2026 最新判例
EzzoHamdan / house-of-wisdom-mcpHouse of Wisdom MCP: Multi-model consultation council. Diverse AI model families investigate independently and return their own perspectives; the orchestrator weighs them. Inspired by the medieval Bayt al-Hikma.
