Agent Building Agent Skills

Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase.

Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.

Automate multi-turn adversarial conversations against LLM agents using Microsoft PyRIT, including Crescendo and Tree-of-Attacks-with-Pruning (TAP) attack chains with scorer feedback loops.

Scan Model Context Protocol servers and tool metadata for poisoning, SSRF, and unauthenticated exposure.

Build, debug, and extend MCP servers and clients that connect AI systems with external tools and data sources.

Add a batteries-included agent component to React/Next.js apps with runtime, streaming, human-in-the-loop approvals, and client-side tools.

Build AI applications with the inference.sh Python SDK: run apps, build agents, and integrate with 250+ models using sync/async, streaming, file uploads, and a tool builder API.

Run 250+ AI apps from the command line: generate images and videos, call LLMs, search the web, create 3D models, and automate Twitter posts.

Access 100+ LLMs including Claude, Gemini, Kimi, and GLM via the inference.sh CLI with automatic fallback and cost optimization.

Control a headless browser to navigate pages, click elements, fill forms, take screenshots, record video, and execute JavaScript using Playwright and inference.sh.

Build automated AI workflows combining multiple models and services for batch processing, scheduled tasks, event-driven pipelines, and agent loops using the inference.sh CLI.

Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring for complex product management tasks.

Provides structured guidance for building production-grade AI agent systems through context engineering, covering fundamentals, architectural patterns, operational excellence, and evaluation.

Design and build hosted agent infrastructure with sandboxed execution, warm pools, session persistence, and multiplayer collaboration.

Designs persistent memory architectures for AI agents, covering cross-session knowledge retention, entity tracking, temporal validity, graph/vector retrieval, and memory consolidation.

Shares memory between agents at the representation level by compacting the orchestrator's KV cache for efficient worker handoff, reducing token costs without summarization or retrieval.

Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.

Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.

Build, deploy, and manage continuous AI agents using a visual workflow editor or development toolkit.

Optimize AI agents through automated evolution cycles using LLM-driven mutation of prompts, skills, and memory against measurable benchmarks.

Build LLM-powered applications with agents, chains, and RAG using a framework that supports multiple providers and 500+ integrations.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture for rapid experimentation and synthesis, producing papers and presentations.

Build complex AI systems with declarative programming, optimize prompts automatically, and create modular RAG systems and agents using Stanford NLP's DSPy framework.

Evaluate NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments with headless GPU evaluation and inference profiling.

Control LLM output with regex and grammars to guarantee valid JSON, XML, or code generation, enforce structured formats, and build multi-step workflows using Microsoft Research's Guidance framework.

Add programmable safety guardrails to LLM applications at runtime, including jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, and toxicity detection.

Run interpretability experiments on neural network internals using nnsight, with optional NDIF remote execution for massive models.

Train and analyze Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features for mechanistic interpretability research.

Compiles research inputs—PDFs, code, logs, notes—into structured Agent-Native Research Artifacts with cognitive and physical layers.

Inspect and manipulate transformer internals via HookPoints and activation caching for mechanistic interpretability research.

Performs a semantic epistemic review of Agent-Native Research Artifacts, scoring six dimensions and producing a constructive report with a recommendation.

Install and configure Acontext, a memory layer for AI agents that provides persistent sessions, file storage, and skill management.

Analyzes 18-month investment scenarios from a news headline by invoking two specialized agents and generating a comprehensive report with sector impacts, stock recommendations, and a critical review.

Review AI agent skills using a dual-axis method: deterministic code-based checks and LLM deep review, with weighted scoring and improvement recommendations.

Build, run, and visualize multi-step AI generation workflows by chaining image, video, and audio nodes into automated pipelines.

Decides when to delegate to compressed-output subagents (investigator, builder, reviewer) instead of using vanilla agents, saving main-context tokens across long sessions.