Explorar skills

Generates a ready-to-use project-context.md file for Claude Cowork through an interactive interview. Triggers EN: 'create project context', 'new project context', 'context-builder', 'generate context file', 'quick context'. Triggers RU: 'создай контекст проекта', 'новый проект контекст', 'сформируй контекстный файл', 'быстрый контекст'.

软件正确性调查 skill。用于用户说“XX 不太对”“这个功能有 bug”“结果和预期不一致”“帮我查原因”，也用于用户要求 review 某个模块、文件、diff 或 PR 的正确性。遇到已知异常或模块 correctness review 时必须优先使用本 skill。 本 skill 使用贝叶斯根因调查：先列候选原因 H，再按日志、代码路径、测试、diff、spec 等证据 E 更新置信度，最后判断根因属于原始 spec 不一致、实现过程偏移、spec 缺口、环境/数据问题或证据不足。 x-cr 独立于 x-verify / x-qa-gate 自动门禁，产出 `reports/cr/cr-report-*.md`，x-fix 可按该 CR 报告继续修复。

Cloudflare-first platform selection. Decision trees for Workers, D1, R2, KV, DO, Queues, Vectorize, Containers, Sandboxes, Flagship, Agent Memory, Workflows v2. Default stack, override conditions, auth, data patterns, reliability.

Assess the health of your current Claude session context and get a clear action recommendation — no technical metrics needed. Use when your session feels long, Claude seems to be forgetting earlier details, or you are unsure whether to continue or start fresh. Triggers: 'check my context', 'context health check', 'is my context running out', 'should I start a new session', 'проверь мой контекст',

Ponto de entrada principal para o fluxo de trabalho Forge. Ele verifica o status do projeto, recomenda a próxima skill e deve ser usado quando não souber o que fazer em seguida. É ativado por "forge", "próximo passo" ou "continuar" (sem contexto claro).

Execute BDD test scenarios from .feature files using browser automation.

Emotion 스타일링 규칙. @emotion/styled, css prop 사용, 스타일 파일 분리 기준.

Convert chat export JSON files into multiple Markdown files (one conversation per file). Use when users ask to split AI chat logs, preserve only user-assistant Q/A, format question as heading, keep response Markdown, and normalize filenames/headings after export.

14-category product-building OS. CF Workers+Hono, Angular, D1, Drizzle, Clerk, Stripe. 94 reference docs, 18 agents.

Self-learning system that records and applies insights from pipeline executions

Generates R implementations for Six Sigma / statistical-process-control tasks — control charts (X-bar R, I-MR, P, NP, C, U), process capability (Cp/Cpk/Pp/Ppk), DPMO and sigma level, Pareto and run charts, histograms, box plots, scatter/regression, correlation, hypothesis tests (1- and 2-sample t, proportion, Wilcoxon, chi-square), one-way and regression ANOVA, binomial/Poisson/normal distribution

Analyze a set of related tickets to identify the underlying root cause.