Results for “autograd”

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

Builds reliable browser automation skills by iteratively running a browsing task, reading the trace, and improving the navigation strategy until it passes consistently.

Builds reliable browser automation skills through iterative experimentation, running an inner agent to browse sites and improving navigation instructions until tasks pass consistently.

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immutable prepare.py / 300-second / val_bpb contract, and route prompt/skill eval work away to LangSmith, Promptfoo, Braintrust, or skill-autoresearch.

Clade goal-driven autonomous improvement loop (Blueprint architecture — deterministic pre/post phases + LLM supervisor/worker nodes, converges when goal met or max-iter hit). NOT the Claude Code built-in /loop (which polls a prompt on an interval like `/loop 5m /foo`) — if the user wants interval polling, route to the built-in.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Scaffolds a program.md research program for autoresearch by auto-detecting codebase signals and interviewing for missing details.

Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.

After scaffolded practice, run an unassisted check — a problem with no AI help. Separates what the learner can do with support from what they can do independently. Critical for preventing phantom attainment.

Full autonomous execution from idea to working code

Use when a carrier asks about autonomous trucks — current state of Level 4 development, major programs (Aurora, Kodiak, Plus, Waymo Via, Embark history), regulatory status, operational implications, hub-to-hub model, driver impact, insurance, and what carriers should be doing now (or not doing) to prepare.

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

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.

Expert en AudioCraft avancé (MusicGen text-to-music, AudioGen text-to-sound, fine-tuning)

Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Run autonomous optimization loops that iteratively improve artifacts against evaluators using hypothesis tree refinement, without overfitting.

Runs an autonomous optimization loop that iteratively improves an artifact against an objective and evaluator using Hypothesis Tree Refinement, with subagent executors in isolated git worktrees.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Improves skills by analyzing execution data to identify patterns in successful versus failed runs, staging changes for human approval.

Give your agent a budget, a target, and a deadline — it does the rest. Orchestrates DSL + Opportunity Scanner + Emerging Movers into a full autonomous trading loop on Hyperliquid. Race condition prevention, conviction collapse cuts, cross-margin buffer math, speed filter. 3 risk profiles: conservative, moderate, aggressive. Use when setting up autonomous trading, creating a trading strategy, or running a scan-evaluate-trade-protect loop.

Evaluates Claude Agent Skills on 10 quality axes with letter grades (A+ through F) and specific improvement recommendations. Use when auditing a skill, comparing skills, prioritizing improvements, or performing quality control on a skill library. Activate on "grade skill", "evaluate skill", "skill quality", "skill audit", "skill review", "rate skill". NOT for creating skills (use skill-architect), grading code quality, or evaluating non-skill documents.

DeepClaw - Autonomous Agent Network

Provides guidance on using JAX for machine learning and mathematical analysis, covering core concepts, transformations, ML specifics, control flow, and parallelism.