Loading...
Loading...
Found 2,087 Skills
Debug container agent issues. Use when things aren't working, container fails, authentication problems, or to understand how the container system works. Covers logs, environment variables, mounts, and common issues.
Force critical evaluation of proposals, requirements, or decisions by analyzing from multiple adversarial perspectives. Triggers on: accepting a proposal without pushback, 'sounds good', 'let's go with', design decisions with unstated tradeoffs, unchallenged assumptions, premature consensus. Invoke with /challenge-that.
Structural feedback on a legal writing draft (memo, brief, paper, exam essay) — organization, analysis depth, clarity, citation form. NEVER rewrites the draft. Use when the user says "feedback on my memo", "read my draft", or "critique my brief".
Automated AI-powered code review that runs on git hooks with progressive disclosure design. Use when setting up automated code review for a project, installing git hooks for code review, creating or modifying review rules, or configuring review behavior. Triggers on requests like "set up AI code review", "install review hooks", "create review rules", or "configure code reviewer".
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.
Stream live swarm events using the Monitor tool for real-time observability
Deep briefing on one matter — current posture, what's changed, next deadline, open questions, and a risk re-assessment check, ready before a GC update or outside counsel call. Use when the user says "brief me on [matter]", "where are we on [matter]", or needs a read on a specific matter.
Train SONA neural patterns from successful task completions, view learned patterns, and optimize the intelligence pipeline
This skill should be used when users need help with content planning, calendar management, research organization, content ideation, or multi-platform planning. It activates when users ask about content planning, calendar management, research organization, content ideation, or multi-platform planning.
Access 1200+ AI Agent tools via Model Context Protocol (MCP)
Design and build multi-agent harness architectures for long-running AI application development. GAN-inspired Generator-Evaluator pattern, Sprint Contract negotiation, context management, quality criteria calibration. Based on Anthropic Engineering patterns. Use when: "build a harness", "multi-agent architecture", "agent orchestration", "generator-evaluator", "long-running app", "harness design", "agent pipeline", "quality evaluation loop", "sprint contract", "build app with agents", "Claude Agent SDK architecture", or when building complex full-stack apps that need planning → generation → evaluation cycles. Also use when discussing context degradation, self-evaluation bias, or assumption testing in AI workflows.
Generate UI in Nothing's design language — monochrome, typographic, industrial with Swiss hierarchy and OLED blacks