スキルを探す

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.

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。

Jev (TypeSafe System One) inner loop for ego-browser — one ~0.4 s typed decision per DOM step instead of an LLM turn. Use for multi-step clicking through a semantic page: fill known values into a form, set filters, open a row/card/menu by name, reach a page via nav or site search. Escalates login, payment, free text, canvas and content reading back to you.

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。

Build AI agents with LangChain framework. Use when building agents, tools, memory, MCP integrations, RAG pipelines, multi-agent systems, or any LLM-powered applications using LangChain or LangGraph in Python or TypeScript.

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。

Adaption AI SDK for synthetic data augmentation and dataset adaptation. Use when building data pipelines with the Adaption Python SDK, uploading datasets (local files, Hugging Face, Kaggle), running augmentation/adaptation jobs, configuring brand controls (hallucination mitigation, safety categories, length), recipe specifications (reasoning traces, deduplication, preference pairs, prompt rephrase), evaluating dataset quality, downloading results, or any workflow involving `pip install adaption`, `from adaption import Adaption`, Adaptive Data, or the adaptionlabs.ai API. Also trigger when the user mentions synthetic data generation for fine-tuning, dataset augmentation pipelines, DPO preference pair generation, or grounding-based hallucination reduction on training data.

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。

Find, build, evaluate, and improve systems using decision models. Use for bounded classification, routing, ranking, Choice/Score/Noul, decision-model composition, evaluation harnesses, prompt/program hill climbing, and Software 3.0 workflows across software, business, organizations, and life. Separate models, code, and human judgment. TypeSafe Jev is the default hosted exemplar. Not for straightforward arithmetic, prose rewriting, or provider setup alone.

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。

Builds and improves task-specific decision artifacts from application requirements and labeled records. Use for data assembly, primitive and base-model selection, fitting, export/reload, inference policy, or bounded data/model/program improvement. Includes rules and no-training outcomes; does not require a rung ladder or training a general Jev.

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。

Creates marketing analytics reports, KPI dashboards, ROI calculations, and performance summaries for SME marketing teams. Handles weekly/monthly reporting, campaign analysis, content performance reviews, and data-driven recommendations. Use when user asks about marketing metrics, reporting, KPIs, dashboards, ROI analysis, performance review, or data-driven marketing decisions.

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。

Use quando uma necessidade de negócio ou técnica precisar de discovery estruturado em pt-BR e de um prompt de implementação autocontido.

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。

Publish a proposal, offer, or pitch as a tracked link and report back whether it's getting read (view analytics after sending). Use when the user says "send the proposal", "did they open it", "track whether they read it", "share the offer". Not for recurring client reports (use client-reporter) or general research shares (use report-publisher).

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。

LLM生成文に特有の表現パターンを検出・修正する。任意のテキストファイルに対して使える。「LLMっぽい」「人間らしく」「humanize」で起動。

Refine a supplied question into a precise, expert-level query when the user asks to rewrite or optimize their question or prompt. Do not use to answer the underlying question.

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。

Use when creating, revising, or critiquing a chart, dashboard, or KPI display that makes a quantitative comparison someone will act on. Covers honest comparison and rendered checks; leave palette, marks, and library mechanics to the medium's own skill. Skip decorative graphics and diagrams with no data.

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。

Operate or troubleshoot Interlateral CLI mesh transport: tmux socket discovery, direct-send helpers, comms.md ledger, identity stamping, idle checks, ACK proof, and safe prompt injection. This is comms mechanics only, not a collaboration workflow.

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。

Role-based collaboration pattern (Drafter, Reviewer, Breaker). Assigns roles to available agents via prompt parameters. Use when starting multi-agent dev work.

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。

Padrões de banco de dados ClickHouse, otimização de consultas, analytics e melhores práticas de engenharia de dados para cargas de trabalho analíticas de alto desempenho.

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。

Migre prompts e código de Claude Sonnet 4.0, Sonnet 4.5 ou Opus 4.1 para Opus 4.5. Use quando o usuário quiser atualizar sua base de código, prompts ou chamadas de API para usar Opus 4.5. Lida com atualizações de string de modelo e ajustes de prompt para diferenças comportamentais conhecidas de Opus 4.5. NÃO migra Haiku 4.5.

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。

Configure e execute buscas web locais usando a API SERP do Bright Data com o pipeline unfancy-search (expansão de query, recuperação de SERP, reranking com RRF).

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。

Projete um schema específico para PostgreSQL. Abrange práticas recomendadas, tipos de dados, indexação, constraints, padrões de desempenho e recursos avançados

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。

Workflow de otimização de banco de dados PostgreSQL para sintonia de consultas, estratégias de indexação, análise de desempenho e gerenciamento de banco de dados em produção.

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。

Domine SQL moderno com bancos de dados cloud-native, otimização OLTP/OLAP e técnicas avançadas de query. Especialista em tuning de performance, modelagem de dados e sistemas analíticos híbridos.

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。

Extraia dados estruturados de respostas de LLM com validação Pydantic, tente novamente automaticamente extrações que falharem, analise JSON complexo com segurança de tipo e transmita resultados parciais com Instructor - biblioteca de saída estruturada testada em batalha

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。

Coleção curada de prompts de alta qualidade para diversos casos de uso. Inclui prompts baseados em função, templates específicos de tarefas e técnicas de refinamento de prompts. Use quando o usuário precisar de templates de prompts, prompts para dramatização, ou exemplos de prompts prontos para uso em codificação, escrita, análise ou tarefas criativas.

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。

Quando o usuário quiser configurar, melhorar ou auditar rastreamento e medição de análises. Também use quando o usuário mencionar "configurar rastreamento", "GA4", "Google Analytics", "rastreamento de conversão", "rastreamento de eventos", "parâmetros UTM", "tag manager", "GTM", "implementação de análises" ou "plano de rastreamento". Para medição de testes A/B, consulte ab-test-setup.

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。

Controle saída de LLM com regex e gramáticas, garanta geração válida de JSON/XML/código, aplique formatos estruturados e construa fluxos de trabalho multi-etapas com Guidance - framework de geração restrita da Microsoft Research

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。