Results for “prowler”

Detects prompt injection attacks targeting LLM-based applications using regex pattern matching, heuristic scoring, and DeBERTa transformer classification.

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates with evals.

Moves issues and external PRs through a state machine of triage roles, categorizing, verifying, grilling, and writing agent-ready briefs.

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Automate multi-turn adversarial conversations against LLM agents using Microsoft PyRIT, including Crescendo and Tree-of-Attacks-with-Pruning (TAP) attack chains with scorer feedback loops.

Persistent task ledger for agent coordination. Plan multi-step work, checkpoint progress across session boundaries, and coordinate across multiple agents with project pool routing.

Train reinforcement learning agents at millions of steps per second using optimized PPO, vectorized environments, and multi-agent support.

Web Scraper IA — Expert en extraction web (Scrapy, BeautifulSoup, Playwright, anti-bot, proxy rotation, data extraction)

TIGER v2 — Multi-scanner trading system for Hyperliquid perps via Senpi MCP. 5 signal patterns (BB compression breakout, BTC correlation lag, momentum breakout, mean reversion, funding rate arb), DSL v4 trailing stops, goal-based aggression engine, and risk guardrails. Configurable profit target over deadline. 12-cron architecture (10 TIGER + prescreener + ROAR meta-optimizer). Pure Python analysis. Requires Senpi MCP, python3, mcporter CLI, and OpenClaw cron system.

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

Product orchestrator for Prodig Suites that guides product planning, routes work to specialists, and coordinates execution across the product lifecycle. Use when the user is shaping a digital product, deciding next steps, or needs help choosing the right Prodig specialist or workflow. Triggers: 'prodig', 'digital product', 'product idea', 'product planning', 'which product agent should I use', 'SaaS planning', 'course creation', 'template pack', 'productized service'.

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts. Masters prompt patterns and techniques.

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Detect promoter regions in DNA sequences by calling the Genomic Intelligence G0 transformer (GENA-LM BERT Large) hosted API. Returns per-window promoter probabilities and called regions as a report and JSON, from a single FASTA input.

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Analyzes runtime history to identify failures and inefficiencies, then autonomously writes improvements using a protocol-constrained evolution engine. Communicates with EvoMap Hub via a local Proxy mailbox.

Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.

Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.