Results for “pr”

Generates a step-by-step construction plan from a one-line objective, where each step is self-contained and executable by a fresh agent in a new session.

Designs and reviews feedback loops for AI agents to ensure goals are machine-decidable, loops are damped, and human judgment is preserved.

Manage design systems in Stitch using MCP tools, including retrieval of assets, creating or updating design systems, and applying them to screens.

Look up the precise term for a web animation or motion effect from a vague description, such as 'the bouncy thing when a popover opens' → 'Pop in'.

Investigates bugs, regressions, and crashes by dispatching four parallel read-only sub-agents, then ranks hypotheses and recommends the fastest proof or fix path.

Test web applications for clickjacking vulnerabilities by assessing frame embedding controls and crafting proof-of-concept overlay attacks during authorized security assessments.

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

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining, covering SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Train AI models to be harmless through self-critique and AI feedback using a set of constitutional principles, without requiring human labels for harmful outputs.

Enables compact, machine-native agent-to-agent messaging using a shared vocabulary of 340+ 2-character atoms across 7 domains, achieving 3x compression over natural language.

Fine-tune Gemma models locally using QLoRA, Unsloth, or TRL for SFT, DPO, and reward modeling, with dataset preparation and conversion to GGUF or LiteRT-LM.

Provides a standardized interface for ingesting raw data across domains such as genomics, network analysis, document review, and spatial mapping, converting it into semantic vectors for agent use.

Run ML workloads on Modal's serverless GPU cloud: deploy models as auto-scaling APIs, run batch jobs, and schedule tasks with pay-per-second GPU pricing.

Extracts a language-agnostic ghost package (spec, tests, install and verify docs) from an existing repository, preserving behavior via tests.yaml and evidence bundles.

Implements AI safety guardrails including input validation, output filtering, robustness testing, human oversight, and monitoring to prevent harmful outputs and ensure system reliability.

Scores generated image captions against reference captions and source images using the Polos metric, which is trained to align with human judgments and probes hallucination robustness and open-vocabulary evaluation.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers, list available MCP servers/tools, or call MCP tools from command line.

Build production AI agents with Agno (formerly Phidata) — define Agent with model/tools/instructions/memory/knowledge, compose Agent Teams with coordinator routing, add Storage for persistence, and integrate RAG via built-in KnowledgeBase with PDF/URL/text sources.

Expert patterns for Plaid API integration including Link token flows, transactions sync, identity verification, Auth for ACH, balance checks, webhook handling, and fintech compliance best practices. Use when: plaid, bank account linking, bank connection, ach, account aggregation.

Agent profile for review API platform contracts, versioning, auth, rate limits, SDK clients, and developer experience. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Agent profile for plan PPC account structure, creative testing, budget hypotheses, measurement, and landing-page alignment. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Agent profile for design test strategy across unit, integration, contract, E2E, visual, performance, and regression layers. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Agent profile for write developer docs, user docs, API docs, tutorials, changelogs, and concise implementation notes. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Build a five-level rubric with coherent logic for a learning target within a developmental band. Use for Manning methodology programmes where Competent = success. For general curriculum rubrics, use criterion-referenced-rubric-generator instead.

Identify a linear dynamic model from input-output or time-series data using MATLAB System Identification Toolbox. Use when estimating transfer function, state-space, ARX, ARMAX, BJ, OE polynomial or process models from measurement data.

Build and sharpen a project's domain model — a CONTEXT.md glossary and ubiquitous language. Use when pinning down terminology, or the agent "uses the wrong words". Repo decision-memory system (INDEX.md, rejected alternatives) → docs-adr.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Build comprehensive AI-native brand asset systems that maintain consistency across all AI-generated content. Train AI tools on brand guidelines, create reusable prompt libraries, and manage visual/voice assets at scale. Use when ", " mentioned.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, set issue fields (dates, priority, custom fields), set issue types, manage issue workflows, link issues, add dependencies, or track blocked-by/blocking relationships. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", "set the priority", "set the start date", "link issues", "add dependency", "blocked by", "blocking", or any GitHub issue management task.

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

Design or revise a company's commercial policy governing discounts, approver thresholds, exception flows, and deal frameworks using data-backed matrices and linting tools.

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page.

Build ML demos on Hugging Face Spaces with ZeroGPU hardware, covering @spaces.GPU decorator usage, duration and quota tuning, process isolation, CUDA availability model, concurrency safety, and build constraints.