agentsclimarketplace

Context & AI engineering

25,831 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Agent introspection debugging

    mturac/everything-openai-codex/docs/ja-JP/skills/agent-introspection-debugging Skill

    88★ repo

    キャプチャ、診断、封じ込め回復、内省レポートを使用した AI エージェント障害のための構造化された自己デバッグワークフロー。

  • Agent payment x402

    mturac/everything-openai-codex/docs/ja-JP/skills/agent-payment-x402 Skill

    88★ repo

    タスクごとのバジェット、支出コントロール、ノンカストディアルウォレットを備えた x402 決済実行を AI エージェントに追加します。agentwallet-sdk を通じて Base をサポートし、OKX Payments / OKX エージェント決済プロトコルを通じて X Layer をサポートします。

  • Agent sort

    mturac/everything-openai-codex/docs/ja-JP/skills/agent-sort Skill

    88★ repo

    並行リポジトリ対応のレビューパスを使用して、スキル、コマンド、ルール、フック、エクストラを DAILY と LIBRARY のバケットに分類することで、特定のリポジトリ向けのエビデンスに基づいた ecc インストール計画を構築します。プロジェクトが完全なバンドルをロードする代わりに実際に必要なものに ecc をトリミングする必要がある場合に使用します。

  • Agentic engineering

    mturac/everything-openai-codex/docs/ja-JP/skills/agentic-engineering Skill

    88★ repo

    評価ファースト実行、分解、コスト対応モデルルーティングを使用してエージェニックエンジニアとして動作します。

  • Agentic os

    mturac/everything-openai-codex/docs/ja-JP/skills/agentic-os Skill

    88★ repo

    OpenAI Codex 上に永続的なマルチエージェントオペレーティングシステムを構築します。カーネルアーキテクチャ、スペシャリストエージェント、スラッシュコマンド、ファイルベースのメモリ、スケジュールされた自動化、外部データベースなしの状態管理をカバーします。

  • Autonomous agent harness

    mturac/everything-openai-codex/docs/ja-JP/skills/autonomous-agent-harness Skill

    88★ repo

    OpenAI Codexを永続的なメモリ、スケジュール済み操作、コンピュータ使用、タスクキューイングを備えた完全自動エージェントシステムに変換します。スタンドアロンエージェントフレームワーク(Hermes、AutoGPT)を、OpenAI Codexのネイティブcrons、dispatch、MCPツール、メモリを活用して置き換えます。ユーザーが継続的な自動操作、スケジュール済みタスク、または自己指令エージェントループを望む場合に使用します。

  • Benchmark

    mturac/everything-openai-codex/docs/ja-JP/skills/benchmark Skill

    88★ repo

    このスキルを使用して、パフォーマンスベースラインを測定し、PR前後の回帰を検出し、スタック代替案を比較します。

  • Continuous agent loop

    mturac/everything-openai-codex/docs/ja-JP/skills/continuous-agent-loop Skill

    88★ repo

    品質ゲート、評価、リカバリーコントロールを備えた継続的な自律エージェントループのパターン。

  • Cost aware llm pipeline

    mturac/everything-openai-codex/docs/ja-JP/skills/cost-aware-llm-pipeline Skill

    88★ repo

    LLM APIの使用量のコスト最適化パターン — タスクの複雑さによるモデルルーティング、予算追跡、リトライロジック、プロンプトキャッシング。

  • Data scraper agent

    mturac/everything-openai-codex/docs/ja-JP/skills/data-scraper-agent Skill

    88★ repo

    任意のパブリックソース(ジョブボード、価格、ニュース、GitHub、スポーツなど)用の完全自動化されたAI搭載データ収集エージェントを構築します。スケジュールでスクレイプし、無料LLM(Gemini Flash)でデータを豊かにし、Notion/Sheets/Supabaseに結果を保存し、ユーザーフィードバックから学習します。GitHub Actions上で100%無料で実行。ユーザーがパブリックデータを自動的に監視、収集、または追跡したい場合に使用します。

  • Enterprise agent ops

    mturac/everything-openai-codex/docs/ja-JP/skills/enterprise-agent-ops Skill

    88★ repo

    オブザーバビリティ、セキュリティ境界、およびライフサイクル管理を備えた長寿命エージェントワークロードを運用します。

  • Eval harness

    mturac/everything-openai-codex/docs/ja-JP/skills/eval-harness Skill

    88★ repo

    OpenAI Codexセッションの正式な評価フレームワークで、評価駆動開発(EDD)の原則を実装します

  • Healthcare eval harness

    mturac/everything-openai-codex/docs/ja-JP/skills/healthcare-eval-harness Skill

    88★ repo

    ヘルスケアAIモデル評価ハーネス、臨床メトリクス、およびレギュレーション遵守の検証。

  • Llm trading agent security

    mturac/everything-openai-codex/docs/ja-JP/skills/llm-trading-agent-security Skill

    88★ repo

    日本語翻訳:このファイルは llm-trading-agent-security 用の日本語翻訳が必要です

  • Mcp server patterns

    mturac/everything-openai-codex/docs/ja-JP/skills/mcp-server-patterns Skill

    88★ repo

    日本語翻訳:このファイルは mcp-server-patterns 用の日本語翻訳が必要です

  • Prompt optimizer

    mturac/everything-openai-codex/docs/ja-JP/skills/prompt-optimizer Skill

    88★ repo

    日本語翻訳:このファイルは prompt-optimizer 用の日本語翻訳が必要です

  • Regex vs llm structured text

    mturac/everything-openai-codex/docs/ja-JP/skills/regex-vs-llm-structured-text Skill

    88★ repo

    構造化テキストの解析に正規表現と大規模言語モデルのどちらを使うかを選択するための意思決定フレームワーク——まず正規表達式から始め、信頼度の低いエッジケースにのみ大規模言語モデルを追加する。

  • Eval harness

    mturac/everything-openai-codex/docs/ko-KR/skills/eval-harness Skill

    88★ repo

    평가 주도 개발(EDD) 원칙을 구현하는 OpenAI Codex 세션용 공식 평가 프레임워크

  • Eval harness

    mturac/everything-openai-codex/docs/tr/skills/eval-harness Skill

    88★ repo

    Eval-driven development (EDD) ilkelerini uygulayan OpenAI Codex oturumları için formal değerlendirme çerçevesi

  • Agent eval

    mturac/everything-openai-codex/docs/zh-CN/skills/agent-eval Skill

    88★ repo

    编码代理(OpenAI Codex、Aider、Codex等)在自定义任务上的直接比较,包含通过率、成本、时间和一致性指标

  • Agent harness construction

    mturac/everything-openai-codex/docs/zh-CN/skills/agent-harness-construction Skill

    88★ repo

    设计和优化AI代理的动作空间、工具定义和观察格式,以提高完成率。

  • Agent introspection debugging

    mturac/everything-openai-codex/docs/zh-CN/skills/agent-introspection-debugging Skill

    88★ repo

    针对AI代理故障的结构化自调试工作流程,包括捕获、诊断、受限恢复和内省报告。

  • Agent payment x402

    mturac/everything-openai-codex/docs/zh-CN/skills/agent-payment-x402 Skill

    88★ repo

    将 x402 支付执行添加到 AI 代理中——通过 MCP 工具实现每任务预算、支出控制和非托管钱包。当代理需要为 API、服务或其他代理付费时使用。

  • Agent sort

    mturac/everything-openai-codex/docs/zh-CN/skills/agent-sort Skill

    88★ repo

    通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查,为特定仓库构建基于证据的 ecc 安装计划,将其分为 DAILY 和 LIBRARY 两类。当 ecc 应精简为项目实际所需而非加载完整包时使用。

  • Agentic engineering

    mturac/everything-openai-codex/docs/zh-CN/skills/agentic-engineering Skill

    88★ repo

    作为代理工程师,采用评估优先执行、分解和成本感知模型路由进行操作。

  • Autonomous agent harness

    mturac/everything-openai-codex/docs/zh-CN/skills/autonomous-agent-harness Skill

    88★ repo

    将 OpenAI Codex 转变为具有持久记忆、定时操作、计算机使用和任务队列的完全自主代理系统。通过利用 OpenAI Codex 的原生定时任务、调度、MCP 工具和记忆,取代独立的代理框架(Hermes、AutoGPT)。当用户需要持续自主操作、定时任务或自我导向的代理循环时使用。

  • Benchmark

    mturac/everything-openai-codex/docs/zh-CN/skills/benchmark Skill

    88★ repo

    使用此技能测量性能基线,检测PR前后的回归,并比较堆栈替代方案。

  • Continuous agent loop

    mturac/everything-openai-codex/docs/zh-CN/skills/continuous-agent-loop Skill

    88★ repo

    具有质量门、评估和恢复控制的连续自主代理循环模式。

  • Cost aware llm pipeline

    mturac/everything-openai-codex/docs/zh-CN/skills/cost-aware-llm-pipeline Skill

    88★ repo

    LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。

  • Data scraper agent

    mturac/everything-openai-codex/docs/zh-CN/skills/data-scraper-agent Skill

    88★ repo

    构建一个全自动化的AI驱动数据收集代理,适用于任何公共来源——招聘网站、价格信息、新闻、GitHub、体育赛事等任何内容。按计划进行抓取,使用免费LLM(Gemini Flash)丰富数据,将结果存储在Notion/Sheets/Supabase中,并从用户反馈中学习。完全免费在GitHub Actions上运行。适用于用户希望自动监控、收集或跟踪任何公共数据的场景。

  • Enterprise agent ops

    mturac/everything-openai-codex/docs/zh-CN/skills/enterprise-agent-ops Skill

    88★ repo

    通过可观测性、安全边界和生命周期管理来操作长期运行的代理工作负载。

  • Eval harness

    mturac/everything-openai-codex/docs/zh-CN/skills/eval-harness Skill

    88★ repo

    克劳德代码会话的正式评估框架,实施评估驱动开发(EDD)原则

  • Healthcare eval harness

    mturac/everything-openai-codex/docs/zh-CN/skills/healthcare-eval-harness Skill

    88★ repo

    用于医疗应用部署的患者安全评估工具。针对CDSS准确性、PHI暴露、临床工作流完整性和集成合规性的自动化测试套件。在安全故障时阻止部署。

  • Llm trading agent security

    mturac/everything-openai-codex/docs/zh-CN/skills/llm-trading-agent-security Skill

    88★ repo

    具有钱包或交易权限的自主交易代理的安全模式。涵盖提示注入、支出限制、发送前模拟、断路器、MEV保护和密钥处理。

  • Mcp server patterns

    mturac/everything-openai-codex/docs/zh-CN/skills/mcp-server-patterns Skill

    88★ repo

    使用Node/TypeScript SDK构建MCP服务器——工具、资源、提示、Zod验证、stdio与可流式HTTP对比。使用Context7或官方MCP文档获取最新API信息。

  • Prompt optimizer

    mturac/everything-openai-codex/docs/zh-CN/skills/prompt-optimizer Skill

    88★ repo

    分析原始提示,识别意图和差距,匹配ecc组件(技能/命令/代理/钩子),并输出一个可直接粘贴的优化提示。仅提供咨询角色——绝不自行执行任务。触发时机:当用户说“优化提示”、“改进我的提示”、“如何编写提示”、“帮我优化这个指令”或明确要求提高提示质量时。中文等效表达同样触发:“优化prompt”、“改进prompt”、“怎么写prompt”、“帮我优化这个指令”。不触发时机:当用户希望直接执行任务,或说“直接做”时。不触发时机:当用户说“优化代码”、“优化性能”、“optimize performance”、“optimize this code”时——这些是重构/性能优化任务,而非提示优化。

  • Regex vs llm structured text

    mturac/everything-openai-codex/docs/zh-CN/skills/regex-vs-llm-structured-text Skill

    88★ repo

    选择在解析结构化文本时使用正则表达式还是大型语言模型的决策框架——从正则表达式开始,仅在低置信度的边缘情况下添加大型语言模型。

  • Eval harness

    mturac/everything-openai-codex/docs/zh-TW/skills/eval-harness Skill

    88★ repo

    Formal evaluation framework for OpenAI Codex sessions implementing eval-driven development (EDD) principles

  • Agent architecture audit

    mturac/everything-openai-codex/skills/agent-architecture-audit Skill

    88★ repo

    Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.

    The same file is in 3 other repositories

  • Agent eval

    mturac/everything-openai-codex/skills/agent-eval Skill

    88★ repo

    Head-to-head comparison of coding agents (OpenAI Codex, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

  • Agent harness construction

    mturac/everything-openai-codex/skills/agent-harness-construction Skill

    88★ repo

    Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

  • Agent payment x402

    mturac/everything-openai-codex/skills/agent-payment-x402 Skill

    88★ repo

    Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol.

  • Agentic engineering

    mturac/everything-openai-codex/skills/agentic-engineering Skill

    88★ repo

    Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

  • Agentic os

    mturac/everything-openai-codex/skills/agentic-os Skill

    88★ repo

    Build persistent multi-agent operating systems on OpenAI Codex. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.

  • Autonomous agent harness

    mturac/everything-openai-codex/skills/autonomous-agent-harness Skill

    88★ repo

    Transform OpenAI Codex into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging OpenAI Codex's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop.

  • Benchmark

    mturac/everything-openai-codex/skills/benchmark Skill

    88★ repo

    Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.

  • Continuous agent loop

    mturac/everything-openai-codex/skills/continuous-agent-loop Skill

    88★ repo

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

  • Cost aware llm pipeline

    mturac/everything-openai-codex/skills/cost-aware-llm-pipeline Skill

    88★ repo

    Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

  • Data scraper agent

    mturac/everything-openai-codex/skills/data-scraper-agent Skill

    88★ repo

    Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.

    The same file is in 8 other repositories

  • Enterprise agent ops

    mturac/everything-openai-codex/skills/enterprise-agent-ops Skill

    88★ repo

    Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.

  • Healthcare eval harness

    mturac/everything-openai-codex/skills/healthcare-eval-harness Skill

    88★ repo

    Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures.

    The same file is in 2 other repositories

  • Knowledge ops

    mturac/everything-openai-codex/skills/knowledge-ops Skill

    88★ repo

    Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.

  • Llm trading agent security

    mturac/everything-openai-codex/skills/llm-trading-agent-security Skill

    88★ repo

    Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.

  • Prompt optimizer

    mturac/everything-openai-codex/skills/prompt-optimizer Skill

    88★ repo

    Analyze raw prompts, identify intent and gaps, match ecc components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.

  • Ralphinho rfc pipeline

    mturac/everything-openai-codex/skills/ralphinho-rfc-pipeline Skill

    88★ repo

    RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.

  • Recsys pipeline architect

    mturac/everything-openai-codex/skills/recsys-pipeline-architect Skill

    88★ repo

    Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.

    The same file is in 3 other repositories

  • Regex vs llm structured text

    mturac/everything-openai-codex/skills/regex-vs-llm-structured-text Skill

    88★ repo

    Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.

  • Alterlab skill finder

    AlterLab-IEU/AlterLab-Academic-Skills/skills/core/alterlab-skill-finder Skill

    87★ repo

    The AlterLab front door and multi-agent launcher — routes a task to the right AlterLab skill(s) when the user invokes the suite without naming one, and for a multi-stage goal (or on the keyword 'alterflow', aliases 'alterresearch' / 'ultralab') it CLARIFIES the goal with a few questions, SELECTS the skills the task needs, and runs a dynamic multi-agent workflow composing them (via alterlab-workflow-orchestration, alterlab-research-pipeline, or alterlab-ssci-orchestrator). Triggers on 'use AlterLab skills', 'which AlterLab skill for X', 'is there an AlterLab skill for…', a multi-stage research goal, 'alterflow …', or any generic AlterLab request where the user does not know skill names. It always asks clarifying questions before executing a multi-step run. Use when someone references AlterLab generically, describes a multi-stage goal, or fires the alterflow keyword; when the user already names a specific skill, defer to that skill directly. Part of the AlterLab Academic Skills suite.

  • Alterlab workflow orchestration

    AlterLab-IEU/AlterLab-Academic-Skills/skills/core/alterlab-workflow-orchestration Skill

    87★ repo

    Composes existing AlterLab skills into multi-agent agentic workflows using current Claude Code subagent and Claude Agent SDK orchestration patterns: parallel subagent fan-out, sequential pipelines, judge panels, adversarial verification, and loop-until-clean review cycles. Maps each pattern onto real skills (alterlab-research-pipeline, alterlab-deep-research, alterlab-citation-verifier, alterlab-paper-reviewer, alterlab-peer-review) with copyable delegation prompts, agent-definition frontmatter, and SDK query() snippets. Use when the request mentions multi-agent, subagents, agent team, parallel agents, orchestration, pipeline of skills, judge panel, adversarial verification, devil's advocate, loop until clean, chaining skills, dispatching agents, or composing skills into a workflow. Part of the AlterLab Academic Skills suite.

  • Alterlab bgpt search

    AlterLab-IEU/AlterLab-Academic-Skills/skills/research-tools/alterlab-bgpt-search Skill

    87★ repo

    Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server, returning 25+ fields per paper (methods, results, sample sizes, quality scores, conclusions). Use when running a literature review or evidence synthesis, or when needing experimental details (sample sizes, effect sizes, methods, quality scores) that abstracts alone do not provide. Part of the AlterLab Academic Skills suite.