Explorar skills

Build transformer fine-tuning run plans with task settings, hyperparameters, and model-card outputs. Use for repeatable Hugging Face or PyTorch finetuning workflows.

Retest remediated findings, detect regressions, and generate remediation status and certification artifacts.

Plan and orchestrate authorized Nmap host discovery, port and service enumeration, NSE profiling, and reporting artifacts for in-scope targets.

Collect project brief and stack choices, then output canonical project-config.json for downstream web-builder skills.

Assess Linux and Windows privilege escalation vectors from existing authorized footholds.

Prepare deployment configs, final checks, and pre-launch readiness artifacts for production release.

Generates robust Playwright end-to-end tests for web pages and user flows.

Gate workflow for making a strategic decision under uncertainty when multiple options have merit and the stakes are high. Defines the success criteria first (outcome-orientation), maps what actually drives the outcome (systems-thinking), generates options including uncomfortable ones (creative-problem-solving), stress-tests each for blind spots and hidden assumptions (critical-intuition), assesses

Build incident response timelines and report packs from event logs. Use for detection-to-recovery reporting, phase tracking, and stakeholder-ready incident summaries.

Coordinate autonomous pentest skills with dependency enforcement, deconfliction, and emergency stop controls.

PTrade/SimTradeLab strategy development guardrails. Auto-loads PTrade API reference, enforces platform constraints (no f-string, no import io/sys), validates lifecycle function usage, and prevents common API misuse. Use when writing, editing, or reviewing any PTrade strategy code or SimTradeLab backtest code. TRIGGER: when editing files in strategies/, src/simtradelab/ptrade/, or any .py file that

Reviews existing unit tests for gaps, weak assertions, and missing edge cases, then rewrites them to be more robust.