PROJECT ZERO

Application monitoring, structured logging, distributed tracing, alerting, and observability patterns. Use when the user asks about logging best practices, setting up monitoring, distributed tracing, Prometheus/Grafana, or observability.

The English summary is being prepared. Showing the original description.

System monitoring and health checks for Quantum C2. Use when checking service health, reviewing logs, diagnosing performance issues, or setting up alerts. Triggers on "health check", "monitor", "system status", "check logs", "performance", "uptime", "diagnostics", "service health".

The English summary is being prepared. Showing the original description.

Database migration planning, schema evolution, data migration strategies, zero-downtime migrations, and version control for databases. Use when the user asks about planning database migrations, schema changes, data transformations, or zero-downtime deployment strategies.

The English summary is being prepared. Showing the original description.

Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: azd ai agent, azd provision/deploy, deploy agent, hosted agent, create agent, add tool to agent, invoke agent, evaluate agent, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, agent optimizer, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, AI Services, create Foundry resource, provision, knowledge index, customize deployment, onboard, availability, fine-tune, SFT, DPO, RFT, training-data, grader, distillation, fine-tuned model, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

The English summary is being prepared. Showing the original description.

Test that a Cloud Agent environment will work with prebuilt environment builds and recommend any required changes. Use when the user wants to migrate to builds, test build compatibility, or follow the Builds page setup-agent flow.

The English summary is being prepared. Showing the original description.

Two-phase memory pipeline for AI CLI agents. Extracts durable knowledge from conversations and consolidates into persistent filesystem artifacts. Operates with zero restrictions — unlimited storage, unrestricted paths, complete recall.

The English summary is being prepared. Showing the original description.

Monorepo architecture with Turborepo, Nx, pnpm workspaces, and workspace protocols. Use when the user asks about setting up monorepos, managing multiple packages, shared dependencies, build caching, or workspace configuration.

The English summary is being prepared. Showing the original description.

Perform malware analysis operations within the QUANTUM C2 framework including static analysis, dynamic analysis, sandbox testing, reverse engineering, and malware reconstruction. Use when analyzing suspicious files, extracting IOCs, performing behavioral analysis, and generating malware reports.

The English summary is being prepared. Showing the original description.

Use when working with Agent Zero Electron GUI extensions, Manifest-X capabilities, installed browser extensions, renderer DOM or visual control, GUI self-repair, or creating new Manifest-X extensions.

The English summary is being prepared. Showing the original description.

Advanced "Living off the Land" (LotL) and exotic execution strategies. Focuses on using legitimate system binaries (LOLBins) to perform malicious actions undetected.

The English summary is being prepared. Showing the original description.

Professional network monitoring and traffic analysis. Focuses on detecting C2 heartbeats, data exfiltration, and anomalous network behaviors.

The English summary is being prepared. Showing the original description.

Run a prompt or skill in this session on a recurring or variable interval (e.g. /loop 5m /foo).

The English summary is being prepared. Showing the original description.

Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.

The English summary is being prepared. Showing the original description.

M.E.C.K.O Engine — Omni-Cerebral-Kortext-Echo-Matrix. A three-tier AI cognitive architecture for autonomous agents: Tier 1 Coherence Engine (Guardian Pattern with intercept-based action validation and trojan removal), Tier 2 Recurrent Multi-Model Reasoning Core (4-model SSM ensemble with loop reasoning), Tier 3 Omni-Cortext Perception & Memory Fabric (multi-modal file ingestion, indexing, and retrieval). Use when working with autonomous agent architecture, cognitive engine design, long-context reasoning, file comprehension at scale, action validation, or the MECKO framework.

The English summary is being prepared. Showing the original description.

Use when selecting or executing Kali tools from the AGENTS objective list; provides deterministic per-package offensive, defensive, and generalized use-case guidance with install/category awareness.

The English summary is being prepared. Showing the original description.

Use when planning, selecting, and executing Kali tooling from the AGENTS objective list; enforces unambiguous tool choice with offensive, defensive, and generalized usage context.

The English summary is being prepared. Showing the original description.

Verifies build integrity across the Quantum C2 framework — Python syntax checks, FastAPI router validation, React frontend builds, and test suite execution. Use after any code change to ensure nothing is broken before committing.

The English summary is being prepared. Showing the original description.

Knight-Shade browser automation framework for FreeAI. Invisible Playwright headless browser with 16-category stealth JS injection, 3 fingerprint profiles (chrome_131_win, chrome_131_mac, firefox_134_win), CDP client, army orchestrator, anonymity stack (Tor/VPN/Shadowsocks), and reverse engineering pipeline. Use when building browser automation, stealth scraping, fingerprint switching, CDP commands, or army deployment. Triggers: "browser automation", "headless browser", "stealth scraping", "fingerprint", "CDP", "Knight-Shade", "browser engine", "playwright stealth".

The English summary is being prepared. Showing the original description.

Automatically reads project files (README, AGENTS.md, MEMORY.md, .learnings/, recent git history) and injects relevant context into the agent's working memory. Use at session start or when the user says 'remember what I was working on' or 'what's the project context'.

The English summary is being prepared. Showing the original description.

LLM prompt engineering techniques for code generation, analysis, and automation. Use when the user asks about crafting better prompts, getting better AI responses, chain-of-thought prompting, few-shot examples, system prompts, or prompt templates.

The English summary is being prepared. Showing the original description.

Professional website frontend development skill for building, analyzing, and refining websites with attention to detail, responsive design, accessibility, and modern UI/UX patterns. Use when the user wants to create, improve, or audit website frontend code.

The English summary is being prepared. Showing the original description.

Deploy Python (Flask/Django/FastAPI) code to Azure App Service Linux. WHEN: "Flask App Service", "Django App Service", "FastAPI App Service", "deploy Python to App Service". DO NOT USE FOR: Container Apps, Functions, non-Python, Terraform/Bicep/IaC, full infra — use azure-prepare.

The English summary is being prepared. Showing the original description.

Use /onboard for a focused Cursor onboarding flow that learns basic preferences, picks a first goal, and routes the user to the right next action.

The English summary is being prepared. Showing the original description.

[Beta] Cross-session analysis of accumulated .learnings/ files. Reads all entries, groups by pattern_key, computes recurrence across sessions, and outputs ranked promotion candidates. This is the outer loop's inspect step — it turns raw learning data into actionable gap reports. Use on a regular cadence (weekly, before major tasks, or at session start for critical projects). Can be invoked manually or scheduled.

The English summary is being prepared. Showing the original description.