review-optimization
Reviews memory optimization patches using a 5-persona peer review system. Requires unanimous approval backed by benchmarks. Bugs discovered during review are valuable - invoke /validate-correctness to validate...
发现 devops cicd 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Reviews memory optimization patches using a 5-persona peer review system. Requires unanimous approval backed by benchmarks. Bugs discovered during review are valuable - invoke /validate-correctness to validate...
Environment validation checklist. Run this FIRST when starting a new Claude session to verify the environment is ready for optimization work. Checks build tools, test runners, benchstat, git, and database acces...
Spawn and coordinate parallel Claude Code sub-agents using git worktrees. Use this skill when you need to parallelize work across multiple independent tasks, delegate subtasks to sub-agents, or orchestrate comp...
Validate pull request source/target rules and draft standardised PR titles and Markdown descriptions that match repository GitHub Actions enforcement.
Maintain testing and formatting discipline aligned with the repository CI pipeline without automatically running tools.
GitHub Actions 워크플로우 로그를 조회하고 분석합니다. "CI 로그 확인해줘", "워크플로우 실패 원인 분석해줘", "GitHub Actions 상태 알려줘", "빌드 로그 보여줘", "테스트 실패 로그 확인" 등을 요청할 때 활성화됩니다.
요구사항 명세를 기반으로 프로젝트 구조와 CI 파이프라인을 설정합니다. "프로젝트 초기화해줘", "프로젝트 부트스트랩", "CI 설정해줘", "프로젝트 구조 만들어줘" 등을 요청할 때 활성화됩니다.
Comprehensive guide for Test-Driven Development (TDD) methodology. Use this skill when the user asks to implement features using TDD, write tests first, follow red-green-refactor cycle, or develop code with tes...
Self-improvement workflow after fixing any bug. Analyzes root causes and updates project guidance (CLAUDE.md, skills, commands) to prevent similar bugs. MUST be invoked after completing any bug fix before marki...
Run build and lint verification before deployment. Use when user mentions "check build", "verify", "pre-deploy", "ready to deploy", or asks to validate the project.
This skill should be used when the user asks about "code review best practices", "how to review code", "review methodology", "code review framework", "impact prioritization", "root cause analysis", or needs gui...
Manage and guide Hikaze-Model-Manager-2 Codex project work via the .codex governance system. Use when the user says "root skill" or asks to start development based on the root skill, or when asked to set up or...
Analyze changes, determine semantic version bump, build executables, and cut a GitHub release with Claude-written minimalist notes.
Comprehensive pre-production repository audit for preparing repos for public release. Use when the user wants to perform a "final sweep", "production check", "pre-release audit", or prepare a repository to be m...
Generate GitHub issues from an approved engineering specification. Use to break down a spec into implementable, atomic tasks with dependencies, sizing, and labels.
Coordinates adaptive QA testing across behavioral, contract, and regression dimensions. Routes to specialized sub-agents based on context and depth.
Generate GitHub issues from an approved engineering specification. Use to break down a spec into implementable, atomic tasks with dependencies, sizing, and labels.
Apply critic feedback to improve an engineering spec. Use when revising a spec based on review comments to address issues and improve quality scores.
Reviews code quality analyst findings. Validates issues are real, severity is appropriate, and suggested refactorings are practical.
Generate GitHub issues from an approved engineering specification. Use to break down a spec into implementable, atomic tasks with dependencies, sizing, and labels.
Parallel execution orchestrator. Picks up existing beads, computes parallel tracks, spawns worker agents, coordinates via Agent Mail, runs calibration at phase boundaries.
Coordinate changes across project-beta repositories when updating runner configurations. Ensures workflow labels match runner scale set names. Use when changing runnerScaleSetName or deploying new runner pools.
Troubleshoot ARC (Actions Runner Controller) runners on Rackspace Spot Kubernetes. Diagnose stuck jobs, scaling issues, and cluster access. Activates on "runner", "ARC", "stuck job", "queued", "GitHub Actions",...
Best practices for running GitHub Actions ARC runners on Rackspace Spot Kubernetes. Covers spot instance management, preemption handling, cost optimization, and resilience strategies. Activates on "rackspace sp...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。