10,232 skills found · Page 276 of 342
borghei / senior-cloud-architectUse when the user asks to "design cloud architecture", "set up Terraform infrastructure", "optimize cloud costs", "plan disaster recovery", "configure multi-region failover", "audit IAM policies", "migrate to cloud", "set up VPC networking", "compare AWS vs GCP vs Azure", or "right-size cloud instan…
borghei / senior-data-engineerData engineering for batch and streaming pipelines with Airflow, dbt, Spark, and Kafka
borghei / senior-frontendFrontend development for React, Next.js, TypeScript, and Tailwind CSS
borghei / senior-fullstackFullstack development toolkit with project scaffolding for Next.js/FastAPI/MERN/Django stacks and code quality analysis
borghei / senior-qaTesting for React/Next.js with Jest, React Testing Library, and Playwright
borghei / senior-secopsSecOps for application security, vulnerability management, compliance, and secure development
borghei / senior-securitySTRIDE threat modeling, DREAD risk scoring, secret detection, and secure architecture design
borghei / tech-debt-trackerScan codebases for technical debt with AST parsing, prioritize by impact, and generate trend dashboards
borghei / tech-stack-evaluatorEvaluate and compare technology stacks with TCO analysis, security assessment, and ecosystem health scoring
unbrowse-ai / unbrowseSearch and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, authenticated site access, and live canvas planning with Unbrowse.
decebals / concurrency-reviewReview Java concurrency code for thread safety, race conditions, deadlocks, and modern patterns (Virtual Threads, CompletableFuture, @Async)
decebals / security-auditJava security checklist covering OWASP Top 10, input validation, injection prevention, and secure coding. Works with Spring, Quarkus, Jakarta EE, and plain Java
decebals / architecture-reviewAnalyze Java project architecture at macro level - package structure, module boundaries, dependency direction, and layering
decebals / performance-smell-detectionDetect potential code-level performance smells in Java - streams, collections, boxing, regex, object creation. Provides awareness, not absolutes - always measure before optimizing. For JPA/database performance, use jpa-patterns instead.
decebals / clean-codeClean Code principles (DRY, KISS, YAGNI), naming, function design and readability
decebals / design-patternsCommon design patterns with Java examples (Factory, Builder, Strategy, Observer, Decorator, etc.)
decebals / java-migrationGuide for upgrading Java projects between major versions (8→11→17→21→25)
decebals / jpa-patternsJPA/Hibernate patterns and common pitfalls (N+1, lazy loading, transactions, queries)
decebals / api-contract-reviewReview REST API contracts for HTTP semantics, versioning, backward compatibility, and response consistency
decebals / java-code-reviewSystematic code review for Java with null safety, exception handling, concurrency, and performance checks
decebals / maven-dependency-auditAudit Maven dependencies for outdated versions, security vulnerabilities, and conflicts
dongshuyan / assess-interview-candidate根据候选人简历与岗位要求生成可审计的后台评估、简明的候选人介绍、按岗位重要性排列的简历疑点、12–18 道可直接照读的面试题，以及支持重点标记和本机保存的离线 HTML。用于招聘方准备结构化面试、核验岗位能力和记录回答。不要用于求职者模拟面试、私人背景调查、心理或人格诊断、从敏感属性推断表现，或自动录用、淘汰、排序候选人。
dongshuyan / task-clarifierDeep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct.
dongshuyan / session-handoff-promptCreate a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session
dongshuyan / task-forestMaintains a repo-local task forest or task DAG for the current workspace
dongshuyan / run-history-skill-builderTurn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan
dongshuyan / run-history-skill-upgraderUse real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill
dongshuyan / academic-humanizerDraft, audit, or minimally revise English- or Chinese-language academic prose to reduce formulaic, vacuous, mechanically repetitive, or process-leaking language while preserving claims, evidence strength, logical relations, manuscript-wide terminology identity, document-level pattern variation, and…
Snowflake-Labs / cocoscoutRelevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
staruhub / wechat-article-writer专业微信公众号文章助手，支持四个独立且可组合模式：article 写正文；image-prompts 从文章生成版本化、provider-neutral 的图片提示词 manifest 与稳定占位符，但不调用生图；layout 把文章和 manifest 确定性转换为微信安全的内联 HTML；full-pipeline 串联正文、提示词/占位符和排版。用户提到公众号、微信文章、推文、配图提示词、图片 manifest、公众号排版、内联 HTML 或完整图文流水线时触发。支持企业官号、个人技术博客、活动回顾和产品评测。不用于：带引用的研究报告（用 deep-research）、PPT/组图（用…
