Agent skills for Perplexity

Synchronizes local Claude skills to GitHub with automatic Org-mode to Markdown conversion and documentation validation.

Deep-dive English word mastery tool. Deconstructs a single English word into core semantics and epiphany. Use when user asks to…

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Data framework for building LLM applications with RAG.

Complete LLDB command reference — variable inspection, breakpoints, threads, expression evaluation, process control, memory commands, and…

Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory…

Use when: (1) Entering an LLM-based Kaggle competition (open-source model required, prompt engineering, few-shot), (2) Need to choose…

Configure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptation

Harden an LLM application against unbounded consumption with input/output caps, token budgets, rate limiting, and cost controls.

Poison the data an LLM application trusts — its RAG knowledge base, fine-tuning corpus, or ingestion pipeline — so that later answers…

Abuse an over-privileged LLM agent — excessive tools, permissions, or autonomy — to make it perform actions beyond its intended scope…

LLM integration patterns including API usage, streaming, function calling, RAG pipelines, and cost optimization

Harden an LLM application against sensitive-data leakage by filtering and redacting model output and constraining what reaches the context.

Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and…

Audit and improve public static websites so LLM agents and crawlers can discover, retrieve, and understand their content without depending…

Harden an LLM application's system prompt so it carries no secrets or authorization logic and cannot be trivially extracted.

Gate every document that enters an LLM application's knowledge base or fine-tuning corpus behind source allowlisting, provenance signing…

LLM Tuning Patterns

Enforce tenant and user isolation in a shared vector store by filtering retrieval on an access boundary before ranking, using…

Retrieve another tenant's or another user's documents from a shared vector store by exploiting similarity search that is not bounded by an…

Review and control AI Agent changes to a local Markdown, Obsidian, or Open Knowledge Format wiki.