evalloop
Пакет плагинов · kingmadellc
evalloop: пакет плагинов для ИИ-инструментов разработки, издатель kingmadellc. Витрин, которые мы читаем и где он опубликован: 1 (Claude Code: claude-plugins-community). Мы впервые увидели его 2026-10-11 и с тех пор изменений не фиксировали. Данные нашего прохода по витринам на 2026-10-12.
Autonomous prompt optimization using Karpathy's autoresearch pattern. Editable file + fixed eval metric + autonomous improvement loop.
- Витрины
- 1
- Где работает
- Ставится как пакет плагинов
- Самое большое опубликованное число
- Число не опубликовано
- Впервые замечен
- 2026-10-11
- Последнее изменение
- Не зафиксировано
- Отметка о проверке
- Не помечен
Где опубликован
| Витрина | Статус | Версия | Числа | Проверен | Впервые замечен |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Открыть исходники на GitHub) | Опубликован | 0c586f1 | Число не опубликовано | Не помечен | |
| Claude Code: claude-plugins-community (Открыть исходники на GitHub) | Опубликован | 0c586f1 | Число не опубликовано | Не помечен | |
| Claude Code: claude-plugins-community (Открыть исходники на GitHub) | Опубликован | 0c586f1 | Число не опубликовано | Не помечен |
Каждое число принадлежит своей витрине и никогда не складывается с числами других витрин. Если витрина число не публикует, мы его не показываем: нет числа не значит ноль.
Что умеет
Устанавливается в ИИ-инструмент как пакет плагинов; что он запускает, перечислено ниже.
Ни одна из витрин, которые мы читаем, не публикует его инструменты или настройки, которые он просит.
Что менялось
С тех пор как мы следим за плагином, ничего не менялось.
Издатель
kingmadellc · Репозиторий: github.com/kingmadellc/claude-plugins
Похожие плагины
Продукты, чьи собственные названия, описания, инструменты и скиллы ближе всего по смыслу к этому, на всех витринах, которые мы читаем. Близость упорядочена только внутри этого списка.
- autoresearchAutonomous experiment loops on any codebase — one file, one metric, one loop. An agent edits a constrained file, runs an eval, keeps improvements, reverts failures, and repeats…
- harness-evolverAutonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experiments, and merges winners automatically…
- autoresearch-ai-pluginAutonomous experiment loop for Claude Code. Run an endless optimize-measure-keep/discard cycle on any optimization target: LLM training loss, test speed, bundle size, build time…
- Plugin EvalEvaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
- evolve-loopA self-learning development pipeline that gets smarter with every cycle. It calibrates itself against your codebase, dynamically selects the highest-impact tasks, implements them…
- mutagentOfficial MutagenT skills bundle for AI coding agents — guides Claude Code through prompt upload, dataset curation, evaluation rubric creation, optimization, framework tracing, and…
- model-advisorClaude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
- contextstellarContext engineering plugin for Claude Code — real-time prompt scoring, RLM adaptive weights, and token optimization. Scores every tool use across 5 dimensions (token utilization…
- claude-prompt-optimizer io.github.rishiatlan/claude-prompt-optimizerScores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.
- dominion-flowResearch-backed orchestration for Claude Code. Structured workflow from idea to production with parallel execution, session memory, 70-point validation, autonomous mode, and…
Похожие плагины по витринам
Тот же вопрос к каждой витрине по отдельности: есть ли там аналог этого плагина?
Есть на витрине Claude Code: claude-plugins-community (5)
- autoresearchAutonomous experiment loops on any codebase — one file, one metric, one loop. An agent edits a constrained file, runs an eval, keeps improvements, reverts failures, and repeats…
- harness-evolverAutonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experiments, and merges winners automatically…
- autoresearch-ai-pluginAutonomous experiment loop for Claude Code. Run an endless optimize-measure-keep/discard cycle on any optimization target: LLM training loss, test speed, bundle size, build time…
- evolve-loopA self-learning development pipeline that gets smarter with every cycle. It calibrates itself against your codebase, dynamically selects the highest-impact tasks, implements them…
- mutagentOfficial MutagenT skills bundle for AI coding agents — guides Claude Code through prompt upload, dataset curation, evaluation rubric creation, optimization, framework tracing, and…
Есть на витрине Claude Code: claude-plugins-official (5)
- ralph-loopInteractive self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Claude works on the same task repeatedly, seeing its previous work, until…
- pydantic-aiWrite accurate Pydantic AI code from the start. Up-to-date patterns, decision trees, and common gotchas for agents, tools, structured output, streaming, and multi-agent apps.
- DeepEvalSkills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
- huggingface-skillsBuild, train, evaluate, and use open source AI models, datasets, and spaces.
- langfuseSkills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Есть на витрине Claude: knowledge-work-plugins (5)
- langfuseSkills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
- datarobot-agent-skillsDataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
- AI-FirstifyAI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
- Desktop CommanderMCP server for terminal commands, file operations, and process management
- pixeltableBuild multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
Есть на витрине Codex: openai-curated (openai/plugins) (5)
- Plugin EvalEvaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
- NVIDIASkills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
- OpenAI DevelopersBuild with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
- SuperpowersAn agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
- CodeRabbitAI-powered code review in Codex, powered by CodeRabbit.
Есть на витрине Community GitHub marketplaces (5)
- DeepEvalSkills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
- Endor Labs Agent KitEndor Labs workflow agents and setup for Claude Code.
- datarobot-agent-skillsDataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
- magentsShared session bus so Cursor can hand off with Claude, Codex, Grok, and friends.
- atomic-agentsComprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
Есть на витрине Copilot CLI: github/awesome-copilot (5)
- copilot-goal-skillGoal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector…
- ai-team-orchestrationRun a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
- radiusModel, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.
- noob-modePlain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
- jupyter-notebooksCreate, edit, run, save, and checkpoint Jupyter notebooks in an interactive Copilot canvas.
Есть на витрине Copilot CLI: github/copilot-plugins (5)
- microsoft-365-agents-toolkitToolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
- azure-devops-copilot-pluginBring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
- model-appsBuild and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
- advanced-securityAdvanced Security plugin for GitHub Copilot.
- code-apps-previewBuild and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Есть на витрине Cursor: cursor/plugins (5)
- Ralph LoopIterative self-referential AI loops using the Ralph Wiggum technique.
- AdvisorConsult a stronger model before major decisions, when stuck, and before declaring done.
- pstackif you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
- Cursor SDKBuild apps, scripts, and automations with the TypeScript SDK.
- CLI for AgentsPatterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
Есть на витрине Docker MCP Catalog (5)
- OpikRead and score Opik traces, experiments, datasets and prompts from your AI assistant.
- ZenBridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
- EffectTools and resources for writing Effect code in Typescript.
- E2BGiving Claude ability to run code with E2B via MCP (Model Context Protocol).
- Desktop CommanderMCP server for terminal commands, file operations, and process management
Есть на витрине Official MCP Registry (5)
- claude-prompt-optimizer io.github.rishiatlan/claude-prompt-optimizerScores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.
- PromptBranchLocal-first MCP server for versioning, searching, evaluating, and improving AI prompts.
- prompyai io.github.samouh-waleed/prompyaiScores your prompts against your real codebase — context-aware prompt intelligence
- PromptheusAI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
- betterprompt-mcp io.github.AungMyoKyaw/betterprompt-mcpMCP server for AI-enhanced prompt engineering and request conversion.
Найдено по смыслу, а не по общему коду или репозиторию: похожие плагины остаются разными продуктами, и это не обзор и не рекомендация.
Это ваш плагин?
Докажите, что поддерживаете плагин: файлом в его репозитории, файлом на вашем домене или DNS-записью. Вы будете получать уведомления, когда витрина добавит плагин, снимет его, изменит отметку verified или список того, что он просит, и сможете поставить его удалённый endpoint на мониторинг как веб-сервис.
Данные витрины Claude Code: claude-plugins-community. Числа взяты из наших регулярных обходов витрин, последняя проверка . Контакты издателей плагинов мы не публикуем.