Loading...
Loading...
Found 1,864 Skills
Adversarial robustness engineering for ML/AI—evasion, poisoning, extraction, membership-inference threat models; robust training, sanitization, detectors; ASR/certified evals; lab model attacks; data-pipeline integrity; production I/O guardrails (classical ML and LLM/multimodal). Use for adversarial examples, robustness suites, poison audits, deploy guardrails—not LLM app red team (ai-redteam), governance (ai-risk-governance), safety classifier R&D (ml-research-engineer-safeguards), safeguard serving (ml-infrastructure-engineer-safeguards), privacy research (privacy-research-engineer-safeguards), AppSec pentest (penetration-tester).
Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the local dev build or a published npm version) against a language's repo.
INTERNAL sub-agent for blind 9-dimensional rubric scoring. **NOT a user-facing skill — do NOT invoke from the main conversation.** It is called via the Task tool by cheat-score / cheat-predict / cheat-bump to generate a context-isolated score for a script. It ONLY accepts script_path + rubric_notes_path; any other input will be refused. It outputs strict JSON: 9 dimensions × {score 0-5, confidence enum, one-line reason}. **It strictly refuses to read** .cheat-state.json, predictions/*, retro sections, or any content that may leak post-publish data. This is Channel B in the 3-channel calibration model (A=main, B=blind sub-agent, C=cross-model).
Guardião da arquitetura de software no SynkOS. Use esta skill quando o usuário pedir para propor ou revisar a arquitetura de um sistema, avaliar tradeoffs entre tecnologias ou abordagens, criar um ADR (Architecture Decision Record), desenhar um modelo de dados ou contrato de API, ou fazer perguntas como "qual stack usar para X?", "como estruturar esse serviço?", "quais são os tradeoffs de Y vs Z?", "documente as decisões técnicas", "revise essa arquitetura". Ative também para discovery brownfield (entender o que já existe antes de propor mudanças), para cross-cutting concerns como segurança e performance, e para revisar designs propostos pelas equipes de implementação.
Create and improve agent skills following the Agent Skills specification. Use when asked to create, write, or update skills.
Score a single draft against the rubric. **Output only to the console, no file writing, no prediction**. Trigger phrases: "Score this [path]"/"score this [path]"/"Score this draft"/"Let's score first". It's a lightweight exploratory action before cheat-predict.
Walk through a complete GAIA benchmark→submit flow — from key resolution through HAL-compatible package generation
Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.
Professional Skills and Methodologies for Vulnerability Assessment
Aesthetic assessment and remix partner with trained visual taste. Provides structured design critiques using a 6-dimension scoring system inspired by VisualQuality-R1 chain-of-thought reasoning.
Research domain WHOIS data and check marketplace listings. Use when the user says "domain lookup", "check domain", "WHOIS", "domain availability", "buy domain", "domain research", "who owns this domain", "domain marketplace", or asks about researching or acquiring a domain name.
Use when raising startup capital (pre-seed through Series C+): decide raise vs bootstrap, size a round, build a deck + data room, run investor targeting/outreach, negotiate SAFEs/term sheets, manage diligence, and set investor reporting cadence post-close.