Explorar skills

Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

Claude Skills Hub oferece mais de 150 skills gratuitas para aprimorar a codificação de IA. É um marketplace de fluxos de trabalho criados por especialistas para otimizar sua experiência com Claude Code.

Analyze game balance by extracting stats from code and running mathematical simulations. Calculates DPS tier lists, TTK matrices, EHP comparisons, and character power rankings. Stress-tests economy earn/spend rates, progression XP curves, and unlock pacing. Runs Monte Carlo simulations on drop rates, loot tables, and crafting RNG. Use when tuning weapon damage, checking if characters are overpower

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

Diagnóstico abrangente de falhas em DAGs e análise de causa raiz. Esta skill é para depurações complexas que exigem investigação aprofundada, fornecendo análise estruturada e prevenção.

Generate project documentation — README files, API docs, and changelogs. Triggers: README, documentation, generate docs, document this project, write README, API docs, changelog.

Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb. Load this skill when the task involves exploration, iteration, or inspecting intermediate results — data science, ML experimentation, API exploration, or building up complex code step-by-step. Uses terminal to run CLI commands against a live Jupyter kernel. No new tools required.

Scalability audit — identifies performance bottlenecks, unbounded queries, N+1 patterns, missing indexes, synchronous blocking operations on hot paths, and memory pressure points. Outputs a prioritized fix list.

Create, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.

Evidence-first debugging for bugs that are hard to reproduce, intermittent, performance-related, or where previous static-analysis fixes have failed. Declares an explicit goal via /goal (the bug no longer reproduces), then loops through Hypothesis → Instrument → Reproduce → Analyze → Fix until that goal is met. Uses ATDD via /flagrare:atdd-plan to write the fix when the codebase has tests. Trigger

Add purposeful motion to interfaces using modern CSS — scroll-driven animations, view transitions, @starting-style, and GPU-accelerated transforms. Zero JS animation libraries needed. Supports web and Flutter. Use when: 'add animation', 'animate', 'add motion', 'transitions', 'scroll animation', 'page transitions', 'loading animation', 'micro-interactions'.

Read-only health check for an existing Peec AI project. In one pass produces (1) a setup-quality audit (red flags from the structural setup — wrong competitors, funnel gaps, taxonomy issues), (2) a brand-performance snapshot (visibility per stage / engine, hero prompts winning vs losing, source diversity, competitor delta), and (3) a priority-ranked list of 5–8 concrete improvements drawn from Pee