confidence-scoring
Assess quality of PRPs and work-orders using systematic confidence scoring. Use when evaluating readiness for execution or subagent delegation.
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。
Assess quality of PRPs and work-orders using systematic confidence scoring. Use when evaluating readiness for execution or subagent delegation.
Playwright end-to-end testing for web applications. Cross-browser testing (Chromium, Firefox, WebKit), visual regression, API testing, mobile emulation. Use when writing E2E tests, testing across browsers, or s...
Python code quality with ruff linter. Fast linting, rule selection, auto-fixing, and configuration. Use when checking Python code quality, enforcing standards, or finding bugs.
Fast JavaScript package management with Bun - install, add, remove, update dependencies with optimized CLI flags for agentic workflows.
Detect PRD/ADR/PRP opportunities in conversations and prompt for document creation. Activates when users discuss features, architecture decisions, or implementation planning.
Python code quality with ruff (linting & formatting) and mypy (type checking). Covers pyproject.toml configuration, pre-commit hooks, and type hints. Use when user mentions ruff, mypy, linting, formatting, type...
Convert and manipulate images with ImageMagick. Covers format conversion, resizing, batch processing, quality adjustment, and image transformations. Use when user mentions image conversion, resizing images, Ima...
Advanced Clippy configuration for comprehensive Rust linting with custom rules, categories, and IDE integration. Use when configuring linting rules, enforcing code standards, setting up CI linting, or customizi...
Build and publish Python packages with uv and modern build tools. Covers uv build, uv publish, pyproject.toml, versioning, entry points, and PyPI publishing. Use when user mentions building packages, publishing...
Structured guidelines for drafting GitHub issues and technical tickets. Uses What/Why/How format with concise descriptions, markdown formatting, and positive framing without estimates or bold claims. Use when u...
List Terraform Cloud runs for a workspace with filtering by status, operation type, and date. Use when reviewing run history, finding failed runs, or auditing infrastructure changes. Requires TFE_TOKEN environm...
Create, test, and package Helm charts for Kubernetes. Covers helm create, Chart.yaml, values.yaml, template development, chart dependencies, packaging, and repository publishing. Use when user mentions Helm cha...
Inspect GitHub Actions workflow runs, check status, analyze logs, debug failures, and identify root causes. Use when investigating CI/CD failures, checking workflow status, or debugging GitHub Actions issues.
Generate diagrams from text using Mermaid CLI (mmdc) - flowcharts, sequence diagrams, ERDs, class diagrams, state machines, and more.
Claude Code hooks configuration and development. Covers hook lifecycle events, configuration patterns, input/output schemas, and common automation use cases. Use when user mentions hooks, automation, PreToolUse...
Advanced pytest patterns including fixtures, markers, parametrization, and parallel execution. Use when implementing test infrastructure, organizing test suites, writing fixtures, or running tests with coverage...
LangChain JS/TS framework for building LLM-powered applications - models, chains, tools, and RAG patterns.
Domain analysis, conflict detection, and relationship validation for Architecture Decision Records. Use when creating or validating ADRs to ensure consistency.
Core Python development concepts, idioms, best practices, and language features. Covers Python 3.10+ features, type hints, async/await, and Pythonic patterns. For running scripts, see uv-run. For project setup,...
Layer 2 network topology mapping and neighbor discovery using LLDP/CDP protocols and ARP scanning. Covers lldpd/lldpcli for switch topology, arp-scan-rs for fast host discovery, and arping for single-host probe...
Monitor GitHub Actions workflow runs using blocking watch commands instead of polling with timeouts.
Connectivity troubleshooting with modern Rust-based tools - trippy (traceroute/mtr), gping (graphical ping), and ss (socket statistics). Preferred over legacy netstat/traceroute.
Detect test smells, overmocking, flaky tests, and coverage issues. Analyze test effectiveness, maintainability, and reliability. Use when reviewing tests or improving test quality.
Manage Helm values across environments with override precedence, multi-environment configurations, and secret management. Covers values files, --set, --set-string, values schema validation. Use when user mentio...
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。