探索开发、内容、数据与办公效率等 AI 技能。先比较用途和仓库热度，再查看技能说明与来源。
Access Claude Blog for latest Claude Code improvements, usage patterns, and best practices. Use when researching Claude Code features, CLAUDE.md optimization, or staying current with Claude capabilities. Checks...
MCP server configuration for GitHub Actions including tool permissions, environment variables, and multi-server setups. Use when configuring MCP servers in GitHub Actions workflows.
Detect unused dependencies in Rust projects for cleaner Cargo.toml files and faster builds. Use when auditing dependencies, optimizing build times, cleaning up Cargo.toml, or detecting bloat. Trigger terms: unu...
Advanced dependency scenarios in uv projects: Git dependencies, path dependencies, editable installs, dependency groups, extras, constraints, and custom indexes. Use when user mentions git+https dependencies, l...
Convenience wrapper for listing Terraform Cloud runs in Forum Virium Helsinki workspaces (github, sentry, gcp, onelogin, twingate). Requires TFE_TOKEN. Use when user mentions TFC runs, Terraform Cloud workspace...
Modern Node.js development with Bun, Vite, Vue 3, Pinia, and TypeScript. Covers JavaScript/TypeScript projects, high-performance tooling, and modern frameworks. Use when user mentions Node.js, Bun, Vite, Vue, P...
HTTP load testing and stress testing with oha - real-time TUI, latency correction for coordinated omission, and HTTP/2-3 support. Includes comparison with wrk, vegeta, and hey.
Automatic selection of appropriate test tiers based on change scope. Guides unit tests for small changes, full suite for larger changes. Use when running tests, discussing testing strategy, or after code modifi...
Next-generation test runner for Rust with parallel execution, advanced filtering, and CI integration. Use when running tests, configuring test execution, setting up CI pipelines, or optimizing test performance....
Analyze Claude Code changelog for changes that impact plugin development. Use when checking for new features, breaking changes, or opportunities to improve plugins based on Claude Code updates.
Just command runner expertise, Justfile syntax, recipe development, and cross-platform task automation. Covers recipe patterns, parameters, modules, settings, and workflow integration. Use when user mentions ju...
Consistent style guide for writing blog posts about projects and technical work. Supports quick updates, detailed write-ups, retrospectives, and tutorials. Designed for low-friction entry and easy scanning.
Systematic project orientation for unfamiliar codebases. Automatically activates when Claude detects uncertainty about project state, structure, or tooling. Analyzes git state (branch, changes, commits), projec...
File-based context sharing for multi-agent workflows. Provides directory organization, agent output templates, progress tracking, and inter-agent context. Use when setting up multi-agent workflows, reading/writ...
Code coverage for Rust using LLVM instrumentation with support for multiple output formats and CI integration. Use when measuring test coverage, generating coverage reports, enforcing coverage thresholds, or in...
Real-time network traffic monitoring with bandwhich and Sniffnet. Per-process bandwidth tracking, connection analysis, and visual traffic inspection.
YAML querying, filtering, and transformation with yq command-line tool. Use when working with YAML files, parsing YAML configuration, modifying Kubernetes manifests, GitHub Actions workflows, or transforming YA...
Configures release-please for monorepos and single-package repos. Handles manifest files, component tagging, changelog sections, and extra-files setup. Use when setting up automated releases, fixing release wor...
Manages release-please PR merging workflow for monorepos. Handles batch merging, conflict resolution through PR closure/recreation, and iterative processing until all PRs are merged. Use when merging release PR...
Branch management, pull request workflows, and GitHub integration. Main-branch development pattern (push main to remote feature branches), modern Git commands (switch, restore), branch naming conventions, linea...
LangGraph framework for building stateful, multi-step AI agents with graph-based workflows, persistence, and human-in-the-loop support.
Retrieve plan and apply logs from Terraform Cloud runs. Use when examining TFC run output, debugging failed plans/applies, or reviewing infrastructure changes. Requires TFE_TOKEN environment variable.
Debug and troubleshoot Helm deployment failures, template errors, and configuration issues. Covers helm template, helm lint, dry-run, debugging YAML parse errors, value type errors, and resource conflicts. Use...
Manage Helm releases: install, upgrade, uninstall, list, and inspect releases. Covers helm install, helm upgrade, helm list, helm status, release history. Use when user mentions deploying Helm charts, upgrading...
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。