Results for “pe”

Generates an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, running a one-off migration or cutover, or the user says "build a wizard" or wants a scripted step-by-step setup. Don't invoke this for steps the agent can perform itself.

Designs collaborative AI agent teams with CrewAI, covering agent personas, task definitions, crew orchestration, and process types.

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

`analysis-agent`/`task-agent`/`review-agent`: use when code needs correctness, security, performance, maintainability, or hallucinated-API review; skip when no review is needed.

`analysis-agent`/`task-agent`/`review-agent`: use when personal-data purpose, retention, deletion, sharing, telemetry, or provider handling changes; skip legal-only work.

`task-agent`: use when local, server, global, derived, optimistic, persisted, form, auth, or cache state ownership changes; skip when state boundaries are unaffected.

Use for Site Building work when Codex should design content types, editorial workflows, previews, localization, permissions, and migration-safe CMS models.

OWL v5.2 — Pure contrarian. One scanner, one thesis: the crowd is wrong. Monitors crowding across top 30 assets (funding extremity, OI concentration, SM tilt). When crowding persists 4+ hours AND exhaustion signals fire (volume declining, price stalling, RSI divergence), enters AGAINST the crowd to ride the liquidation unwind. 1-2 trades per day max. Re-crowding exit: if the crowd comes back, thesis is dead, exit immediately. DSL High Water Mode (mandatory). The patient predator. v5.2: funding floor lowered from 20% to 12% so the five-factor scoring model actually runs. Added observability logging (top 3 crowding scores per scan cycle).

Autonomous spec-driven development agent. Syncs DEV_SPEC.md into chapter-based reference files, identifies the next pending task from the schedule, implements code following spec architecture and patterns, runs tests with up to 3 auto-fix rounds, and persists progress with atomic commits. Use when user says "auto code", "自动开发", "自动写代码", "auto dev", "一键开发", "autopilot", or wants fully automated spec-to-code workflow.

Autonomous spec-driven development agent. Syncs DEV_SPEC.md into chapter-based reference files, identifies the next pending task from the schedule, implements code following spec architecture and patterns, runs tests with up to 3 auto-fix rounds, and persists progress with atomic commits. Use when user says "auto code", "自动开发", "自动写代码", "auto dev", "一键开发", "autopilot", or wants fully automated spec-to-code workflow.

Autonomous spec-driven development agent. Syncs DEV_SPEC.md into chapter-based reference files, identifies the next pending task from the schedule, implements code following spec architecture and patterns, runs tests with up to 3 auto-fix rounds, and persists progress with atomic commits. Use when user says "auto code", "自动开发", "自动写代码", "auto dev", "一键开发", "autopilot", or wants fully automated spec-to-code workflow.

Create new skills, modify existing ones, and measure their performance through iterative evaluation and benchmarking.

Adds a persistent memory layer that stores and retrieves user preferences and context across conversations using semantic search.

Creates and manages AI agent teams for complex engineering tasks, with model routing, cost optimization, and performance evaluation.

Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)

Provider-neutral processkit MCP gateway. Use when a harness should see one processkit MCP surface while processkit keeps per-skill servers canonical and available.

Read and create PDF documents — extract text (and per-page text) from a PDF to JSON/markdown, and render markdown/plain text into a new PDF.

Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance using the ax CLI.

Turns a person's photo into a custom 3D action figure with collectible toy packaging.

High-performance numerical computing with JAX, covering functional transformations, Flax NNX, and best practices for ML research.

Fetches and analyzes LangSmith execution traces to debug LangChain and LangGraph agents, investigating errors, tool calls, and performance.

Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a question.

Analyse existing written feedback for quality, specificity, actionability, and impact on student learning. Use when reviewing teacher or peer feedback to improve feedback practices.

Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts. Masters prompt patterns and techniques.

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.

Optimize MATLAB design files for GPU Coder to generate faster CUDA code. Iteratively profiles, rewrites, and benchmarks until performance targets are met or diagnostics are resolved. Use when asked to: optimize for GPU Coder, improve GPU codegen performance, profile generated GPU/CUDA code, profile GPU MEX, fix gpuPerformanceAnalyzer diagnostics, speed up GPU MEX, reduce GPU memory transfers, improve kernel parallelism, rewrite MATLAB for CUDA, or run gpuPerformanceAnalyzer.

Provides patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend.

Deploy and scale Python AI/ML workloads on Modal's serverless cloud, including GPU compute, web endpoints, scheduled jobs, and persistent storage.

Provides detailed, structured image descriptions covering objects, people, colors, text, and scene context, with an overview and interpretation.

Performs astronomical data analysis with astropy: coordinate transformations, unit conversions, FITS file handling, cosmological calculations, time systems, tables, and WCS.

Runs independent AI CLI reviewers over phase plans and merges their feedback into a REVIEWS.md file.

Emulates Andrew Ng's teaching style to explain AI and machine learning concepts with structured, practical guidance.

Quantize LLMs to 8/4/3/2/1-bit precision without calibration data, using multiple backends and HuggingFace/vLLM integration.

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.