「karpathy」の検索結果

Skill Optimization: Auto Research. 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.

日本語の概要は準備中です。原文の説明を表示しています。

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

日本語の概要は準備中です。原文の説明を表示しています。

Autonomous fixed-budget ML experiment loop — setup, iterative hypothesis testing, git-based keep/discard tracking, and indefinite autonomous execution. Implements the karpathy/autoresearch protocol.

日本語の概要は準備中です。原文の説明を表示しています。

File a librarian query result back into the library as a new page with provenance tracking. Karpathy's "good answers can be filed back into the wiki as new pages" insight made concrete. The library compounds from explorations, not just from external sources.

日本語の概要は準備中です。原文の説明を表示しています。

Scaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up autonomous code improvement, generating adversarial eval harnesses, running hypothesis-implement-eval-keep/discard loops, or checking autoresearch progress. Triggers on "autoresearch", "autonomous improvement", "eval loop", "hypothesis loop", "self-improvement loop".

日本語の概要は準備中です。原文の説明を表示しています。

Before any material decision — code chunk, plan, strategy, design, scope cut, push to GitHub — convene a war-room. The session driver takes the CEO seat: frame the tradeoff, summon specialist seats from whatever agent roster the user has built, dispatch a cross-family voice via `ato dispatch` so priors actually disagree, decide. A failure-mode filter (wrong assumptions / overcomplexity / orthogonal edits / imperative-over-declarative — Karpathy's four are one good default, swap in your own) runs on every dispatch. Place in the v2.16 stack: war-rooms DECIDE before code starts; `ato-mission` EXECUTES the work between decisions (multi-step, goal-driven, persisted across days); `ato-review` VERIFIES the resulting commits. Use a war-room for the design verdict, hand the verdict to a Mission, review the merged result. Fires before: sending a code draft to the user as final, opening a PR, pushing to a remote-tracking branch, committing >50 LOC of behavior change, or delivering a plan or strategic recommendation as the final answer.

日本語の概要は準備中です。原文の説明を表示しています。

Behavioral guardrails against the six most common LLM coding failure modes. Apply on every coding task: writing, editing, reviewing, or refactoring.

日本語の概要は準備中です。原文の説明を表示しています。

Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email sequences, ad copy, headlines, form pages, CTA text, or any conversion-focused content. Triggers on "optimize this page", "run autoresearch", "score these variants", "A/B test this copy".

日本語の概要は準備中です。原文の説明を表示しています。

Council — 5 independent AI perspectives + mutual critique + synthesis (adapted from karpathy/llm-council for Claude Code). For high-stakes decisions where the answer does NOT follow unambiguously from the data — go/no-go before real consequences, critiquing a methodology, choosing between competing approaches, pressure-testing a conclusion you're attached to, designing risk controls. NOT for log/data analysis (the council has no data access) and not for factual lookups. Triggers — "convene the council", "run it past the council", "go/no-go", "pressure-test this".

日本語の概要は準備中です。原文の説明を表示しています。

Generate and maintain a persistent codebase wiki — LLM-built interlinked markdown knowledge base (Karpathy LLM Wiki pattern)

日本語の概要は準備中です。原文の説明を表示しています。

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.

日本語の概要は準備中です。原文の説明を表示しています。

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

日本語の概要は準備中です。原文の説明を表示しています。

Karpathy's LLM Wiki: build/query interlinked markdown KB.

日本語の概要は準備中です。原文の説明を表示しています。

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 spe...

日本語の概要は準備中です。原文の説明を表示しています。

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiabl

日本語の概要は準備中です。原文の説明を表示しています。

Karpathy's LLM Wiki: build/query interlinked markdown KB.

日本語の概要は準備中です。原文の説明を表示しています。

Behavioral guardrails for implementation work. Reduces common LLM coding mistakes: overcomplication, silent assumption-picking, scope drift, and unverifiable success criteria. Load on Builder and software-engineer-mode.

日本語の概要は準備中です。原文の説明を表示しています。

Karpathy's LLM Wiki: build/query interlinked markdown KB.

日本語の概要は準備中です。原文の説明を表示しています。

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

日本語の概要は準備中です。原文の説明を表示しています。

Segundo cérebro persistente em Markdown — LLM Wiki no padrão Karpathy mantida como bundle Open Knowledge Format v0.2, com fontes imutáveis em raw/ e conceitos citados em wiki/. Use quando o usuário disser "segundo cérebro", "second brain", "adiciona isso ao meu brain", "salva na minha wiki", "ingere esse artigo/PDF/link", "o que minha wiki diz sobre", "o que meu brain sabe sobre", "consulta meu conhecimento", "lint da wiki", ou pedir para acumular conhecimento de fontes de forma durável. NÃO use para notas do Obsidian (pwdev-obsidian), planejamento de features (pwdev-feat) nem PRDs (pwdev-prd).

日本語の概要は準備中です。原文の説明を表示しています。

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

日本語の概要は準備中です。原文の説明を表示しています。

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.

日本語の概要は準備中です。原文の説明を表示しています。

Karpathy's LLM Wiki: build/query interlinked markdown KB.

日本語の概要は準備中です。原文の説明を表示しています。