Results for “pr”

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Master Rust 1.75+ development with async runtime (Tokio/smol).

Prompt for generating an AGENTS.md file for a repository

Large Language Model development, training, fine-tuning, and deployment best practices.

MLflow, model versioning, experiment tracking, model registry, and production ML systems

Drive mex (`mex-agent`), persistent project memory and code graphs for AI coding agents. One command scaffolds a living wiki, builds a deterministic code graph, and installs a project anchor file (CLAUDE.md, root AGENTS.md, .cursorrules, .windsurfrules, copilot-instructions.md, or .opencode/opencode.json) that your agent auto-loads as a standing rule document. Use when the user wants to `mex setup` a new project, build a symbol-grounded wiki, keep knowledge connected to implementation, route relevant context to agents, or run drift detection (`mex check`, `mex sync`). Triggers on: "mex setup", "project memory", "code graphs", "codebase documentation", "drift detection", "agent memory", "structured scaffolds", "architectural context", "living wiki", "project anchor file".

Transaction-verified trading signals on Base. Register agent as signal provider, publish trades with TX hash proof, consume signals from top performers via REST API. All track records verified against blockchain data. No fake performance claims. Triggers on: "publish signal", "post trade signal", "register provider", "subscribe to signals", "copy trade", "bankr signals", "signal feed", "trading leaderboard", "read signals", "get top traders".

CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, parallel performance.

Tactical fast path: turn a small problem, bug report, edit request, or narrow refactor into three deliverables — a brief change-spec (docs/specs/), a detailed implementation-ready plan (docs/plans/), and a TODO.md with agent-pickable tasks and milestones. Load when the user describes a tactical problem and wants quick planning artifacts, says "plan this change", "create a TODO", "write a plan for this", "problem to plan", "break this into tasks for agents", "I want to change X — plan it", or when process-decomposer routes here after determining the user needs lightweight planning deliverables. Also triggers on "create tasks from this problem", "make this actionable", or "turn this into a plan agents can execute". For feature-sized work that needs an executable spec + constitution + cross-check gate, route to `spec-driven-development` (or `feature-spec`) instead.

Ingest, index, search, and edit video and audio from files, URLs, live streams, or desktop sessions with timestamps, subtitles, overlays, and real-time alerts.

Transform the voice in an audio recording into a different target voice while preserving emotion, timing, and delivery using the ElevenLabs Voice Changer API.

Extract Amazon product reviews by ASIN using the BrowserAct API, returning structured data including ratings, text, reviewer info, and verified purchase status.

Explains foundational concepts of context engineering: what context is, attention mechanics, the U-shaped attention curve, and why context quality matters more than quantity.

Audits a website against the Forter Agentic Readiness Guide by running 25 weighted rubrics, scoring each guideline, and producing a prioritized fix report.

Provides best practices for using MariaDB's built-in vector support for AI workloads, including SQL syntax for vector columns, indexes, distance functions, and RAG patterns.

Syncs key-value preferences and state across multiple agents using a shared TiDB Zero database, with optional auto-provisioning of a free ephemeral database.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

ONNX Runtime in Rust via the `ort` crate (2.x): loading sessions, configuring CPU/CoreML/CUDA execution providers, tensor I/O with ndarray, async-safe spawn_blocking wrapping, global thread-pool init, and debugging provider/opset issues

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

End-to-end finite element analysis in MATLAB PDE Toolbox — geometry creation, model setup, solve, and post-processing in one skill. Use when building geometry from primitives or file import, setting up femodel with BCs/loads/materials, solving thermal/structural/EM problems, and extracting or visualizing results. Covers fegeometry, multicuboid, multicylinder, multisphere, decsg, boolean ops, mesh generation, femodel, all AnalysisTypes (thermalSteady, thermalTransient, structuralStatic, structuralTransient, structuralModal, structuralFrequency, electrostatic, magnetostatic, dcConduction, harmonic EM), materialProperties, faceBC, faceLoad, cellLoad, vertexLoad, solve, interpolation, von Mises stress, principal stress, reaction forces, heat flux, pdeplot3D visualization. Triggers on: PDE Toolbox, finite element, FEA, thermal analysis, structural analysis, electromagnetic analysis, femodel, mesh, boundary conditions, stress, displacement, heat transfer, post-processing.

Featurizes molecules for machine learning with molfeat (100+ featurizers) — ECFP/MACCS/MAP4 fingerprints, RDKit and Mordred physicochemical descriptors, and pretrained embeddings (ChemBERTa, ChemGPT, GIN) exposed as scikit-learn transformers that convert SMILES into feature vectors. Use when turning molecules into ML-ready feature matrices for QSAR/QSPR or virtual screening, or benchmarking fingerprint against descriptor and embedding representations; for training models and MoleculeNet benchmarks on those features prefer alterlab-deepchem, and for low-level fingerprint or descriptor primitives prefer alterlab-rdkit. Part of the AlterLab Academic Skills suite.

Build and improve AI or probabilistic software through evaluation-driven development. Use for LLM applications, agents, prompts, RAG, tool use, classifiers, model migrations, quality regressions, golden datasets, LLM-as-judge rubrics, benchmarks, or requests to add evals and measurable release gates. Pair with TDD for deterministic code; do not use as the primary guide for ordinary unit testing without model behavior.

Configures dynamic threshold alerting policies for Google Cloud Vertex AI Agent Platform agents, monitoring latency, error rates, and quality metrics using Terraform and PromQL.

Provides idiomatic PyTorch patterns and best practices for building robust, efficient, and reproducible deep learning applications, covering model architecture, training loops, data pipelines, and checkpointing.

Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Covers the complete object model, coordinate system, measurement units, export workflows, and best practices.

Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking, creates orchestration DAGs, builds feature store schemas, deploys model registries, and automates retraining and validation workflows.

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

Integrates multi-dimensional health data to detect anomalies, predict risks (hypertension, diabetes, cardiovascular), and generate personalized recommendations and interactive HTML reports.

Reconciles project documentation, agent memory, and rule files against the actual codebase after a development session, ensuring accuracy and consistency across all knowledge layers.