Explorar skills
13.048 skills encontradas
Alerta por categoria
Receba novas skills de Desenvolvimento toda segunda
skill-to-web-prompt
Esta skill converte skills do Claude Code em prompts diretamente utilizáveis por IAs web (DeepSeek, Doubao, ChatGPT web, etc.). Ela é ativada quando o usuário solicita a conversão de uma skill em prompt para IA web.
checking-implementability
Verifique se seu plano de implementação será bem-sucedido com o Claude Code. Ele avalia se as fases se encaixam nas janelas de contexto e seguem padrões iterativos para desenvolvimento baseado em sessão.
rule-creator
Create, maintain, audit, remove, improve, and optimize Claude Code project rules (.md files in .claude/rules/). Trigger for: "create a rule", "add a coding standard as a Claude rule", "audit my rules", "delete/remove a rule", "this rule isn't working", "improve a rule", "optimize this rule", or references to .claude/rules/ and project coding standards. Do NOT trigger for creating skills (use skill
sandbox
Scaffolds a Docker "sandbox" harness into a repo so Claude Code can run in `--dangerously-skip-permissions` (YOLO) mode inside an Ubuntu container, with the project bind-mounted at /workspace and the host's ~/.claude bind-mounted for auth and session continuity. Use when the developer wants an isolated filesystem for agent writes but still wants host-visible builds, logs, and session history.
brainrotify
Rewrite developer-facing prose into playful Gen-Z "brainrot" language without changing executable code. Use when an AI coding agent or assistant needs to transform comments, docstrings, Markdown, README files, or other documentation text surfaces in one file or a directory while preserving syntax, logic, formatting, and code fences. Support optional backup creation and three intensity levels: `L`,
generator-coding
Template-based code generation pattern using data models, templates, and helper functions to generate repetitive interface code.
review-skill
Reviews a SKILL.md file or skill directory for quality, correctness, and alignment with Claude Code skill conventions. Use when you've written a new skill and want to check it before committing, or when evaluating an existing skill for improvements.
miki-rebase-reflect
Miki's rebase-and-reflect skill. Rebases the current branch onto the latest default branch, then reflects on the nature of what landed in the default branch and what it might mean for this branch. If the rebase gets complex (non-trivial conflicts, unexpected git state), flags and hands off to the user or model. Invoke when the user says "/miki-rebase-reflect", "rebase against main", "pull main and
post_mortem
Generate a detailed post-mortem analysis after a debugging session or incident, capturing what failed, what worked, and lessons learned
claude-suggestion
Search Claude Code GitHub issues for duplicates, then auto-fill a new issue form with the suggestion. User reviews and submits manually.
experiment-set-design
Use when designing experiments to test whether a Claude Code skill is effective, or when planning how to validate a new or improved skill
worktree-start
Claude Code 専用。素の `claude` で起動した直後に、タスク説明または issue URL / 番号から命名した git worktree へ `EnterWorktree` で切り替えて作業を開始する。issue 起点・タスク起点どちらでも並列セッション立ち上げに使う。issue URL / 番号入力で Status: Ready の場合は worktree 切り替え後に `issue-implement` へ自動連鎖する。