Parcourez et installez des milliers de compétences pour AI Agents dans le répertoire Killer-Skills. Compatible avec Claude Code, Windsurf, Cursor et plus.
La compétence Hugging Face Datasets pour Claude Code permet l'exploration et l'extraction de données de manière efficace. Utilisez l'API de Dataset Viewer pour récupérer des métadonnées de sous-ensemble/split, paginer des lignes, rechercher du texte et appliquer des filtres.
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.
Resume localise : Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and guardrails. It covers claude, claude-code, codex workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Organize all outputs from slash commands and subagents in assets/ directory by topics, date format, and slugs.
Standards for String Catalogs, L10n, and Asset Management.
Standards for String Catalogs, L10n, and Asset Management.
Add a new Dagster asset to the pipeline. Use when creating a Bronze, Silver, or Gold layer asset.
Resume localise : # Databricks Asset Bundle (DABs) Writer Overview Create DABs for multi-environment deployment (dev/staging/prod). This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Expert in quantifying damages from construction and proximity impacts including noise, dust, vibration, traffic disruption, visual impairment, and business losses. Use when assessing temporary construction impacts, permanent proximity damages, business loss claims, or quantifying injurious affection beyond general principles. Key terms include injurious affection, construction impacts, noise modeling, vibration damage, traffic disruption, visual impairment, business losses
漏洞评估的专业技能和方法论
Resume localise : Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. It covers generative-ai, llm-evaluation, llm-evaluation-framework workflows. This AI agent skill supports Claude Code, Cursor, and
Generate and verify E2E tests for a feature. Explores live app, creates test plan, generates tests, runs and fixes until passing.