devops-infrastructure
Manage deployment, Docker, CI/CD, server hardening, and infrastructure security. EXCLUSIVE to devops-engineer agent.
Discover Tools skills, compare source repositories and read the instructions for each workflow.
Manage deployment, Docker, CI/CD, server hardening, and infrastructure security. EXCLUSIVE to devops-engineer agent.
Expert guidance for building stateful, multi-actor AI agents with LangGraph - graphs, nodes, edges, state management, and agent architectures.
Diagnose errors and failing tests in Laravel + React + Python applications. Use when encountering bugs, exceptions, stack traces, 500 errors, TypeErrors, failing tests, or unexpected behavior. EXCLUSIVE to debu...
Plan and implement safe database schema changes including migrations, indexes, and backfills. Use when creating tables, adding columns, optimizing queries, or managing Eloquent/SQLAlchemy relationships. EXCLUSI...
Expert guidance for building LLM applications with LangChain framework - chains, prompts, memory, retrievers, and integrations.
Brainstorm and advise on technical decisions using structured process and MCP helpers. EXCLUSIVE to brainstormer agent. Does NOT implement — only advises.
Expert guidance for DeepAgents framework - simplified agent creation with tool integration for LangChain/LangGraph workflows.
Audit code for security vulnerabilities using OWASP Top 10 guidelines. Use for security audits, pre-deployment checks, authentication reviews, or when checking for XSS, SQL injection, CSRF, or authorization iss...
Create clear, step-by-step implementation plans with acceptance criteria using MCP helpers. EXCLUSIVE to planner agent.
Review code changes for correctness, security, performance, and maintainability. Use for PR reviews, code audits, pre-merge checks, or quality validation of Laravel + React + Python code. EXCLUSIVE to reviewer...
Fetch and summarize authoritative external sources into actionable guidance using MCP helpers. EXCLUSIVE to researcher agent.
Code review for Next.js and TypeScript projects. Use when asked to "review this code", "check this PR", "review my changes", "look at this component", or any code review request. Applies team standards for Type...
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
Use when the user wants to analyze writing samples to extract voice patterns, create voice-replicating prompts, or refine content generation prompts to match a specific writing style
Add new MCP primitives (Tool, Resource, Prompt). Use when asked to add a new tool, resource, or prompt to the MCP server.
Automate the end-to-end process of handling a new API request, from model generation to Data Source integration.
Guide for creating a new feature or subfeature following the project's Clean Architecture + MVI pattern.
Parse JSON and create freezed object classes following project conventions.
F* proof-oriented programming language for verified software development. Use when: (1) writing or verifying F* code (.fst/.fsti files), (2) understanding verification errors from Z3/SMT, (3) learning dependent...
AWS CLI commands for dev/stage/prod environments. Use when running any aws CLI command, interacting with S3, Lambda, Glue, Athena, CloudWatch, or other AWS services. Ensures correct profile and region are use...
Learning-mode output style that mixes interactive coding with concise educational explanations. Use when the user asks for "learning mode", wants to co-write code, or requests a teaching/mentoring style: ask th...
CLI to search Claude Code conversation history by tool, pattern, or time, and export results.
Jujutsu (jj) version control commands. Use when working in a jj repository, running version control operations, viewing commit history, managing bookmarks (branches), creating or splitting commits, pushing to...
Use when working with Linear tickets/issues - establishes workflows for creating and updating tickets (issues)
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.