MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
script-kit-next
Durable pattern and tooling for running bounded autonomous audit loops ("Go AFK for N hours") with cadence, budget, and safe stop conditions.
ISC-Bench
Benchmark template for evaluating spam-detection models using anchored spam campaign examples (contains harmful anchoring content).
Hermes Proficiencies
Enforce workspace hygiene and git-aware file-routing to prevent orphaned or destructive file operations by Hermes agents.
dotfiles
Safety-focused workflow for local dbt development that prevents accidental use of production BigQuery schemas by redirecting schemas and enforcing pre-commit ch
claude-skill-registry
Provides a comprehensive set of development principles, safety guidelines, and VibeCoder guidance for AI agents.
awesome-copilot-for-testers
Design and ship deterministic GitHub Copilot hooks for VS Code: fast, documented lifecycle checks that observe, warn, mutate, or deny to enforce safe automation
cc-settings
Create mid-task rollback points to save and restore agent state before performing risky operations like refactors or migrations.
pm-claude-skills
Audit and risk-assess agent skills before installation by identifying red flags, blast radius, and permission surfaces.
wanwu
Extract structured data from images and documents and safely import it into a platform data flow using ontology commands (CSV import only).
GSD Core
Safely revert GSD phase or plan commits with dependency checks and a confirmation gate.
hardstop
A safety layer that blocks dangerous shell commands and warns on risky system operations to prevent accidental damage.