Skill UI

Instructor lets you shape LLM responses into validated Pydantic models, automatically retrying failed extractions, parsing complex JSON with type safety, and streaming partial outputs across Anthropic, OpenAI, and other providers.

Master the art of building robust, production-grade LLM chains using LangChain Expression Language (LCEL). This guide covers advanced composition patterns, including sequential, parallel, and conditional branching chains. It also details prompt templating, structured output parsing (JSON/Zod), and context injection, enabling the creation of complex, multi-step AI pipelines.

Workflow for parsing SillyTavern-compatible character cards and world info from PNG/WebP/JSON files using a dedicated Node.js parser, with clear steps for copying presets, installing deps, running the extractor, and verifying results.

This skill provides methods for reliably extracting typed, validated, and structured data from Large Language Models (LLMs), moving beyond simple text parsing. It covers best practices across major APIs (OpenAI's response_format, Anthropic's tool_use, Google's responseSchema) and local models. Key workflows include defining schemas (Pydantic/Zod), implementing constrained decoding, and building robust retry loops for production-grade data pipelines.

Hunts MITRE ATT&CK T1055 process-injection techniques via Sysmon Event IDs 8/10 and EDR telemetry, parsing JSON logs to flag CreateRemoteThread calls, risky access masks, and reporting severity with mitigation guidance.

Track running experiments by inspecting remote screen sessions, gathering logs, parsing JSON outputs, and optionally pulling WandB metrics before summarizing baselines, deltas, and costs for Vast.ai or Modal runs.

`jq` is the standard and powerful CLI tool for querying, filtering, and reshaping JSON data. This skill provides expert-level practical patterns for working with deeply nested structures, handling complex transformations (like flattening, renaming, and grouping), and integrating JSON logic into shell pipelines. Essential for parsing API outputs (AWS, GitHub), log files, and building robust Bash scripts.

This guide provides a comprehensive framework for investigating production issues on the Nexu platform using the Datadog Logs API. It details how to query crash events, analyze OpenClaw stderr output, check gateway startup status, and review API request logs (including 5xx errors). It includes best practices for authentication, filtering by pod/time, and parsing raw JSON logs using Python for actionable insights.