Total 33,100 skills
Showing 12 of 33100 skills
Review Prisma code for common violations, security issues, and performance anti-patterns found in AI coding agent stress testing. Use when reviewing Prisma Client usage, database operations, or performing code reviews on projects using Prisma ORM.
通用的 MDX 文档发布工具。验证语法 → 语义化提交 → Git 推送。支持任何 MDX 项目（Fumadocs、Next.js、Docusaurus 等）。可配置 build 命令，自动检测多语言文件。与 fumadocs-article-importer 配合完成文章导入→发布工作流。
Expert at building resilient applications through proper error handling. Covers Result types, error boundaries, try-catch patterns, typed errors, and graceful degradation. Use when "error handling, try catch, error boundary, Result type, exception, error-handling, typescript, react, resilience" mentioned.
Interactive daily productivity review with guided priority setting. Supports morning planning, midday check-ins, and end-of-day wrap-ups. Use for daily ritual or cron automation.
Build, validate, and deploy LLM-as-Judge evaluators for automated quality assessment of LLM pipeline outputs. Use this skill whenever the user wants to: create an automated evaluator for subjective or nuanced failure modes, write a judge prompt for Pass/Fail assessment, split labeled data for judge development, measure judge alignment (TPR/TNR), estimate true success rates with bias correction, or set up CI evaluation pipelines. Also trigger when the user mentions "judge prompt", "automated eval", "LLM evaluator", "grading prompt", "alignment metrics", "true positive rate", or wants to move from manual trace review to automated evaluation. This skill covers the full lifecycle: prompt design → data splitting → iterative refinement → success rate estimation.
Skill template with Bun Shell pattern. Copy this folder to create new skills.
Data validation and pipeline testing utilities for ML training projects. Validates datasets, model checkpoints, training pipelines, and dependencies. Use when validating training data, checking model outputs, testing ML pipelines, verifying dependencies, debugging training failures, or ensuring data quality before training.
Senior engineering analyst for code review, plan review, and automation review. Four-lens review covering architecture, code quality, reliability, and performance, each scored 1-10. Delivers APPROVE, REVISE, or REJECT verdicts. Use when you need a code review, plan review, quality check, or want to verify work before shipping. Part of the architect-system loop. Reads from system/blueprints/ and source code. Outputs to system/reviews/.
A brief description of what this skill does
Security incident remediation playbooks for removing threats, restoring systems, and recovering from incidents. Use for post-containment cleanup, system recovery, and returning to normal operations.
Koin dependency injection framework for Kotlin. Use for Kotlin DI, Android development, Ktor backend, Compose Multiplatform, dependency injection patterns, and module definitions.
Scan crypto wallets and tokens for Sharia (Islamic finance) compliance. Checks tokens against halal/haram criteria including riba (interest), gharar (uncertainty), maysir (gambling), and prohibited protocol types. Outputs per-token verdicts and overall wallet health score.