18 skills found
anthropics / Plugin SettingsThis skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable.
google-gemini / behavioral-evalsGuidance for creating, running, fixing, and promoting behavioral evaluations
google-gemini / tui-testerExpert guidance for testing Gemini CLI behavior and visual output using terminal automation.
cjo4m06 / mcp-shrimp-task-managerShrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.
0xwilliamortiz / andrej-karpathy-skillsBehavioral guardrails for Claude Code, distilled from Andrej Karpathy's field notes on where LLMs go wrong when they write software.
bjwanneng / veriflow-ccVeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a stateful, zero-dependency LLM orchestration skill. Features sub-agent nesting for code gen and behavioral-driven verification.
fifidayone / aileron-protocolAileron Protocol: A strict system harness override enforcing deterministic AI behavior through codebase-first execution, strict token economics, and rigorous debugging limits.
MosaicXR-AI / mosaic-bridgeUnity Editor MCP plugin — AI agents drive Unity via Model Context Protocol. Apache 2.0, ~290 domain-specialized tools including procedural generation, simulation, physics, rendering, and AI behavior from published research papers.
zixuantemp / flarevm-mcpMCP server bridging Kali and FlareVM for automated Windows malware analysis. 48 tools, 5 prompts, 5 resources, composite playbooks (triage, behavioral, unpack, persistence audit).
ChainAware / behavioral-prediction-mcpAI-powered tools to analyze wallet behaviour prediction,fraud detection and rug pull prediction.
daseinpbc / SPL-FRAMEWORKSUBSUMPTION PATTERN LEARNING (SPL) MULTI-AGENT FRAMEWORK: Hierarchical foundation model agent architecture that reduces costs by 10-50x through intelligent suppression of expensive foundation model calls. Grounded in R. Arkin's behavior-based robotics and R.
nullablevariant / rust-mcp-coreA config-driven MCP server core built on the official Rust SDK. Define tools, auth, prompts, resources, and HTTP behavior in YAML or JSON configuration -- the library handles execution, validation, and protocol compliance with minimal Rust code.
maojindao55 / botgroup-chatBehavioral rules for lobsters in botgroup.chat group chats. Activates when receiving messages from the botgroup channel.
comzzy-comzzy / filament"name": "filament", "version": "0.1.0", "private": true, "description": "Cross-chain EVM wallet identity stitching MCP server using onchain behavioral heuristics.", "main": "src/server.js", "engines": { "node": ">=18"
assafkip / research-modeAnti-hallucination research mode. Toggle on to enforce citation requirements, source grounding, and "I don't know" behavior. Toggle off for creative work.
EnesMeyzin98 / decision-supportMaintain or extend the advisory decision-support layer that structures signal fusion, external context, AI validation, probabilistic edge, pipeline stage, and supervisor readiness without changing execution behavior
halng / allBehavioral guidelines to reduce common LLM coding mistakes
qyndex / harness-doctorDiagnose the harness itself. Reports version drift vs upstream, plugin staleness, MCP version pins, hook log size, memory growth, settings.json size. Run monthly or when behavior feels off.
