Results for “base”

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

Secure and powerful Playwright browser automation for testing websites, checking deploys, taking screenshots, filling forms, validating login flows, responsive QA, deploy QA, accessibility smoke checks, and browser-based verification. Use when Nick asks to test a page, verify a deployment, automate browser interactions, capture screenshots, inspect console errors, check mobile/desktop rendering, or run real Chromium-based browser checks.

This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

Application architecture patterns and code organization — clean architecture, hexagonal architecture, feature-based structure, dependency inversion, module boundaries, SOLID principles at module scale. Activate on "clean architecture", "hexagonal architecture", "feature-based structure", "dependency inversion", "module boundaries", "architecture pattern", "folder structure", "fat controller", "circular dependency", "IoC container". NOT for microservice decomposition (use microservices-patterns) or database schema design (use database-design-patterns).

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

You are an expert in MobX, the simple and scalable state management library based on transparent reactive programming. You help developers build React applications with observable state, automatic tracking of dependencies, computed values, actions for state mutations, and reactions for side effects — providing a natural, class-based or functional approach where the UI automatically updates when state changes without manual subscriptions.

Enforces strict outside-in red-green-refactor TDD with one-failure-per-turn discipline, predicting failures before every run, hardcoding minimum changes, and using triangulation and property-based testing. Triggers on explicit TDD requests and tasks phrased as 'implement', 'add', 'write a function', 'build a feature'.

Address Codex review comments on an open PR, re-run thermo-nuclear-code-quality-review, sync with the base branch, and push the updates. Use after a Codex (or human) review has landed on a PR you opened — the skill resolves each comment in code, marks the GitHub review thread resolved, then rebases/merges any new base-branch commits before pushing.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

Create a new AgentHub collaboration session with task, agent count, and evaluation criteria for multi-agent competitions.

Create pull requests with structured descriptions based on committed branch diffs, following Sentry's engineering practices.

Generates a comprehensive .editorconfig file based on project analysis and user preferences, ensuring consistent coding styles across editors.

Create scroll-driven animations with pinning, scrubbing, and trigger-based timelines using GSAP ScrollTrigger.

Generates minimal macOS Seatbelt sandbox configurations to isolate and restrict applications with allowlist-based profiles.

Deploy and manage projects on Vercel using token-based authentication, without interactive login.

Enforces evidence-based completion claims and rigorous code review practices, including receiving feedback, requesting reviews, and verification gates.

Read, search, post, and engage with X/Twitter from the command line using cookie-based authentication.

Builds single-page applications with component-based architecture, dependency injection, reactive forms, and routing.

Routes freeform user requests to the appropriate GSD command based on intent, confirming the routing before dispatching.

Produce a 30/60/90-day cash-flow forecast from AR and AP with base/low/high confidence bands and shortfall alerts.

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document

Signal-based outbound specialist who designs multi-channel prospecting sequences, defines ICPs, and builds pipeline through research-driven personalization — not volume.

GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.

Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.

Build the PRINCE2 Initiating a Project pack: project initiation documentation, business case, project plan, controls, management approaches, product descriptions, and baseline decisions.

Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document

Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document

Researches federal opportunities, competitors, incumbents, recompetes, teaming partners, agencies, markets, and pricing context to support evidence-based GovCon capture and growth decisions.

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs RAG/semantic search, or wants to start a local web UI for their docs.

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs RAG/semantic search, or wants to start a local web UI for their docs.

Creates, edits, and analyzes spreadsheet files with professional formatting, formula-based calculations, and error-free delivery.