Safer agent skills

Human in the loop evaluation of llm responses for few shot prompting.

Score basis：Clear source · Risk needs review · Universal

Automate adversarial prompt testing on LLMs to identify security weaknesses with an open-source AI red teaming framework.

Score basis：Clear source · Risk needs review · Universal

A working guardrail layer that classifies any LLM prompt as safe or harmful, sits in front of a live LLM, and measures exactly where it passes, where it fails, and why.

Score basis：Clear source · Risk needs review · Universal

Automated engine for testing and refining Large Language Model prompts.

Score basis：Clear source · Risk needs review · Universal

Route prompts efficiently to appropriate modes for large language models using a lightweight, single-header C++ library.

Score basis：Clear source · Risk needs review · Universal

Provide a structured template for Obsidian-style markdown vaults to improve LLM agent navigation and human readability in Git repositories

Score basis：Clear source · Risk needs review · Universal

Package code context into clean markdown for LLM prompts using a minimalist, lightweight tool that respects .gitignore and requires Git installed.

Score basis：Clear source · Risk needs review · Universal

Provide and generate AI agent prompts with industry guides, glossaries, and multi-provider LLM support for scalable, automated content creation.

Score basis：Clear source · Risk needs review · Universal

Enhance long AI conversations with sidebar prompts, quick navigation, and reply outlines for efficient browsing and context tracking across supported sites.

Score basis：Clear source · Risk needs review · Universal

Automate prompt injection testing in Burp Suite to find and analyze vulnerabilities in large language model integrations.

Score basis：Clear source · Risk needs review · Universal

Build LLM-powered AI agents with a minimal FastAPI and Pydantic template featuring async SQLAlchemy, uv for dependencies, and Alembic migrations.

Score basis：Clear source · Risk needs review · Universal

Estimate token usage and API costs for large language models to help developers manage AI prompt expenses before scaling workloads.

Score basis：Clear source · Risk needs review · Universal

Build production-ready LLM system prompts for senior dev workflows, from React and SQL to refactoring and architecture.

Score basis：Clear source · Risk needs review · Universal

Exports source repositories into compact Markdown context files for LLM prompting and codebase review

Score basis：Clear source · Risk needs review · Universal

Automate PhD literature reviews from PDFs with LLM prompts, evidence-linked notes, Excel tracking, and cross-paper synthesis.

Score basis：Clear source · Risk needs review · Universal

Secure LLM prompts with end-to-end encryption for inference examples

Score basis：Clear source · Risk needs review · Universal

Test, analyze, and automate LLM red-team prompt delivery for boundary checks, jailbreak research, and prompt injection testing

Score basis：Clear source · Risk needs review · Universal

GitHub repository kp9696/llm-chat-app-template; metadata recovered from GitHub Search API.

Score basis：Clear source · Risk needs review · Universal

Tutorial and learning report with modern Large Language Model ( LLM ) prompt script.

Score basis：Clear source · Risk needs review · Universal

QuietPrompt is a local-first AI tool for coding.

Score basis：Clear source · Risk needs review · Universal

Prompts are for users, resources are for the application and tools are for the model

Score basis：Clear source · Risk needs review · Universal

A VS Code extension that transforms a given workspace into a notebook with fast scaffolding templates, editing macros, and blueprint‑specific assistants powered by MCP servers.

Score basis：Clear source · Risk needs review · Universal

Inspect and test MCP servers directly inside VS Code and browse Tools, Resources, and Prompts, run tool calls, view history, and syntax-highlighted results.

Score basis：Clear source · Risk needs review · Universal

Anemesis is an Obsidian plugin that turns notes into a structured, queryable memory for AI agents by indexing, enriching, and embedding content into a local vector store, then exposing retrieval via MCP so agents can ac…

Score basis：Clear source · Risk needs review · Universal