Desenvolvimento
13.569 skills encontradas
Alerta por categoria
Receba novas skills de Desenvolvimento toda segunda
Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.
pr
Create, inspect, or merge GitHub pull requests. Use when the user asks to open a PR, check PR status, or merge a PR. Composes PR descriptions from existing review file metadata. Manual invocation only via /pr.
configure
Configure the claude-lark-plugin by managing ~/.claude/channels/lark/.env. Use when the user asks to configure, setup, or change Lark/Feishu settings or credentials.
case-outcome-predictor
Audit legal case prediction systems for bias, fairness, accuracy, and ethical guardrails. Use when: 'check my prediction model for bias', 'audit case outcome fairness', 'evaluate legal ML model', 'review sentencing prediction ethics', 'analyze bail risk algorithm', 'fairness metrics for justice system AI'.
lark-attendance
飞书考勤打卡:查询自己的考勤打卡记录
lark-okr
飞书 OKR:管理目标与关键结果。查看和编辑 OKR 周期、目标(Objective)、关键结果(Key Result)、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。
adr
Create and manage Architecture Decision Records using the Michael Nygard format. Supports new ADR creation, retrospective analysis to document existing decisions, superseding, deprecating, and index generation. Use when you need to document architecture decisions, record technical choices, explain why a technology was chosen, or create decision logs.
claude-code-101
Interactive tutorial teaching Claude Code fundamentals -- file ops, git, testing, context management, and advanced patterns. Use when: 'teach me claude code', 'how do I use claude code', 'claude code tutorial', 'learn claude code', 'getting started with claude code', 'claude code basics', 'how does claude code work'.
polish
Full quality pass -- chains parallel UX + scalability audit, then QA verification, then consistency gate. Fixes everything it finds. Works with any stack.
regression-bisecting
Use when a bug was recently introduced but you don't know which commit caused it.
ask-claude
Use when a Codex or generic local agent needs a focused second opinion from Claude CLI without MCP routing.
context-retrieval-loop
Deterministic 3-cycle loop for gathering codebase context before acting. Broad search → exact source and tests → target-specific docs and setup. Stop after enough context or report what is still missing.
hard-won-skill-extractor
Extract a learned skill from the current conversation manually