Search skill packs and skills together

Input validation often becomes inconsistent across forms, APIs, and business rules. This skill guides Claude, Codex, and Claude Code toward secure validation patterns.

Real-time Lark workflows need reliable event streams, filtering, and clean shutdown behavior. This skill guides AI agents through bounded event consumption with lark-cli.

Teams need consistent skill files that agents can discover and use correctly. This skill guides authors through structure, descriptions, examples, scripts, and review checks.

AI skills can fail when instructions are vague or untested. This skill guides test-driven skill writing with pressure scenarios and verification loops.

Creating a useful Agent Skill requires clear scope, discoverable descriptions, and valid structure. This skill guides authors through SKILL.md, examples, testing, and troubleshooting.

Multi-agent workflows often waste time, tokens, and compute through poor coordination. This skill guides profiling, workload distribution, cost controls, and measured optimization.

Pull request descriptions often miss context or reviewer needs. This skill guides Claude, Codex, and Claude Code through branch checks, diff review, draft PR creation, and Sentry-style descriptions.

Linear research can miss perspectives and take too long on broad questions. This skill directs users to a ten-agent workflow for parallel collection and synthesis.

LLM applications can become difficult to structure as agents, memory, retrieval, and tools grow. This skill guides LangChain design choices and production checks.

Weak prompts create inconsistent AI results and wasted review time. This skill gives clear patterns, templates, and testing methods for reliable prompts.

React and Next.js apps often suffer from slow data fetching, large bundles, and avoidable re-renders. This skill gives agents concrete rules and examples for performance-focused code generation and review.

Code review feedback can be unclear, incomplete, or wrong for the current codebase. This skill helps Claude, Codex, and Claude Code verify, prioritize, and respond with technical rigor.