berlinlatvia-alt

Prevents agents from stopping execution before achieving the goal. Built via trio swarm debate. File system is truth. Plans are not deliverables.

One command loads ALL context into a new agent. Biases, rules, skills, traits, products, signals.

Forces agents to output trading strategies exclusively in a parsable DSL/JSON format, stripping away conversational rhetoric and ensuring deterministic, testable parameters for evolutionary backtesting.

Instructs the agent to avoid sequential brute-forcing, enforce intermediate checks, use parallel subagents, and iteratively debug.

Discover any website's API and create domain plugins with proxy routes. Use when the user wants to create an API for a website, discover a web service's data transport, add a new domain, capture browser traffic, build typed API clients, or integrate with a third-party site. Also use when the user...

Build a complete application from a short description. Asks the developer clarifying questions, generates data requirements, launches discovery agents, and builds a dashboard. Use when the developer describes what they want to build in plain language — "compare tickets", "track prices", "search j...

An autonomous workflow factory that breaks down massive epic goals, spawns specialized background subagents to execute them, and acts as the senior reviewer orchestrator. Use this skill when the user triggers the `/goal` command or explicitly requests long-running, massive, overnight, or fully au...

Autonomous LLM pretraining research loop on single GPU using Karpathy's autoresearch framework. Use when the user wants to: (1) start an autonomous LLM training experiment session, (2) run overnight hyperparameter/architecture search on a single-GPU nanochat setup, (3) iterate on train.py modific...

Discovers new biases in real-time and ADDS them to the bias log, making the checker smarter with every review.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when a service's Management API returns 403/Cloudflare WAF from Python/CLI but works in the browser, or when you need to create tables/execute DDL on Supabase without a service_role key, or when any API requires browser-level TLS trust that CLI cannot provide.

>-

Run local CI checks and verify GitHub Actions status. Use before committing, after pushing, or when asked to check/fix CI.

>-

Build Next.js dashboard pages that consume domain proxy APIs. Use when the user wants to create a dashboard, build a UI page, add a search interface, display data from captured APIs, create comparison views, or build any frontend that calls /api/<domain>/ endpoints.

Iterative debugging with targeted logs. Use when browser connections fail, traffic capture returns empty, proxy routes return errors, WebSocket issues, or any problem that can't be solved on the first attempt. Add logs, read output, narrow the search, repeat until fixed, then clean up.

Validates product demand in 24 hours using real-world signals, not theory.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Deploy to EC2 production server. Use when deploying new code, rebuilding Docker images, wiping and reseeding the database, checking container health, or managing the EC2 instance via AWS CLI.

Trigger phrase: "flatten" / "emergency" / "kill engine" / "stop bleeding"