Communitygithub.com

Evaluar agentes CLI en post-entrenamiento autónomo de LLM con P…

Ejecuta Claude Code, Codex CLI, Gemini CLI u OpenCode a través de tareas de post-entrenamiento acotadas en H100 y compara cómo cada agente mejora un LLM base.

¿Qué es Evaluar agentes CLI en post-entrenamiento autónomo de LLM con P…?

PostTrainBench es un benchmark diseñado para evaluar la capacidad de agentes CLI autónomos —como Claude Code, Codex CLI, Gemini CLI y OpenCode— para realizar tareas de post-entrenamiento de modelos de lenguaje grandes (LLMs) en un entorno controlado con GPUs H100. La herramienta mide cuantitativamente cómo cada agente mejora un LLM base durante el post-entrenamiento, ofreciendo una comparación justa y reproducible. Está diseñada para ejecutarse en clústeres HTCondor con soporte de contenedores Apptainer y fuse-overlayfs, lo que permite un aislamiento y reproducibilidad adecuados. Este skill es útil para desarrolladores, investigadores y equipos de MLOps que deseen comparar herramientas de agente de IA en tareas reales de post-entrenamiento, optimizando así sus flujos de trabajo de mejora de modelos.

Compatible con✓Claude Code✓Codex CLI~Cursor✓Gemini CLI✓OpenCode
npx skills add https://github.com/agentskillexchange/skills/tree/main/skills/benchmark-cli-agents-on-autonomous-llm-post-training-with-posttrainbench
Ver original→Ver todas las habilidades

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentación

Evaluar agentes CLI en post-entrenamiento autónomo de LLM con PostTrainBench

Ejecuta Claude Code, Codex CLI, Gemini CLI u OpenCode a través de tareas de post-entrenamiento acotadas en H100 y compara cómo cada agente mejora un LLM base.

Prerrequisitos

Python, apptainer, fuse-overlayfs, caché de Hugging Face, acceso a GPU H100, compatibilidad actual con el planificador HTCondor, y credenciales para los andamios de agente CLI seleccionados

Instalación

Instala o configura siguiendo las instrucciones basadas en el código fuente:

Clona https://github.com/aisa-group/PostTrainBench, instala los requisitos incluyendo apptainer y fuse-overlayfs, construye el contenedor estándar con bash containers/build_container.sh standard, descarga la caché de Hugging Face con bash containers/download_hf_cache/download_hf_cache.sh, copia example.env a .env, configura las claves API y rutas, y luego envía los trabajos con bash src/commit_utils/commit.sh.

Documentación

Fuente

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

Academic Paper Citation Network Mapper

Builds citation networks from Semantic Scholar API and CrossRef DOI metadata. Visualizes paper influence graphs using NetworkX, identifies seminal works, and tracks research lineage across fields.

ACF Custom Fields REST Exposer

Exposes Advanced Custom Fields data through the WordPress REST API using register_rest_field and acf_format_value. Handles repeater fields, flexible content layouts, and gallery fields with proper serialization.

ACF Extended for Advanced Custom Fields Workflows

An ASE skill built around ACF Extended, the WordPress enhancement suite for Advanced Custom Fields that adds field types, admin improvements, front-end forms, options pages, and developer tooling. It is a practical fit for agents working inside complex WordPress content models and custom field workflows.

ACF to Gutenberg Block Migrator

Converts Advanced Custom Fields field groups into native Gutenberg blocks using the ACF Block API v2 and @wordpress/scripts build pipeline. Maps ACF repeaters, groups, and flexible content to InnerBlocks and block attributes with server-side rendering via acf_register_block_type().

Activepieces Open Source Workflow Automation

Activepieces is an open-source, self-hostable workflow automation platform with 200+ integrations. It provides a visual builder for creating automated workflows and exposes all its connectors as MCP servers for AI agent use.

ActivityWatch Cross-Platform Automated Time Tracker and Producti

ActivityWatch is a privacy-first, open-source automated time tracker that records application usage, browser activity, and AFK status across Windows, macOS, and Linux. With 16k+ GitHub stars, it provides detailed productivity analytics without sending data to external servers.

act Local GitHub Actions Runner

act is an open-source CLI tool that runs GitHub Actions workflows locally using Docker, enabling fast feedback on workflow changes without pushing to GitHub. It is a standard tool for local Actions development and testing.

Add a browser review checkpoint before risky agent actions with

Use AgentClick when an agent should pause before risky commands, plans, drafts, or code changes so a human can inspect, edit, approve, or reject them in a purpose-built browser UI.

Add Claude design-system and accessibility workflows with UX/UI

Use UX/UI Agent Skills when Claude should generate tokens, component specs, accessibility audits, and framework-specific UI code from a repeatable design workflow.

Add executable smoke tests for shell scripts and CLIs before ref

Use Bats-core when an agent needs to turn fragile shell scripts or command-line workflows into something it can verify repeatedly after edits. The agent writes focused Bash tests for success paths, failure paths, and output contracts, then runs them locally or in CI before a refactor, release, or incident fix goes out.

Add graph-backed memory and context retrieval to agent workflows

Use Cognee to ingest project knowledge into graph and vector memory so agents can retrieve durable context across sessions and workflows.

Add IDE-style semantic code navigation and symbol-safe refactors

Give a coding agent symbol-aware lookup, cross-file rename, and structural edit tools before it starts making brittle text-only changes.

Add managed long-term memory to LangGraph agents with LangMem

Give LangGraph agents memory management and search tools so they can store, retrieve, and update durable facts across sessions.

Add multimodal lifelong memory to MCP and Python agents with Sim

Use SimpleMem to store, compress, index, and retrieve text or multimodal memories for agents through MCP or Python integrations.

Add persistent project memory and hook-driven synthesis with Cla

Keep Claude Code sessions grounded in prior decisions, project context, and daily handoff notes instead of starting from zero every time.

Add Postgres-native vector retrieval to agent and RAG workflows

Store embeddings beside application data in Postgres, create vector indexes, and query nearest neighbors for semantic search, RAG, recommendations, or agent memory retrieval.

Address GitHub PR review comments from the current branch with g

Find the open PR for the current branch, gather unresolved review comments, and drive a focused comment-resolution workflow with gh-authenticated context.

Add runtime guardrails to TypeScript agents with VoltAgent

Use VoltAgent to intercept, validate, and enforce input/output policies in TypeScript agent workflows.

Add temporal context memory to agent workflows with Zep

Use Zep as an external context layer for agents that need to store events, assemble temporal graph context, and retrieve relevant memory before model calls.

Adobe Firefly API Batch Image Generator

Calls Adobe Firefly

Skills relacionados

steipete/video-frames

Extract frames or short clips from videos using ffmpeg.

community

steipete/summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

community

openclaw/openclaw

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

community

obra/superpowers

Obra superpowers agent skills.

community

affaan-m/ECC

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...

community

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

community