发现 部署与运维 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。
Guide for creating effective agent skills. Use when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or tool integration...
Guide for adding support for new django packages to djdevx
A structured workflow for AI-assisted development using research, planning, and systematic implementation phases. Users refer to this skill as RPI, rpi or Research Plan Implement.
SCL (Structured Control Language) syntax assistance for Siemens TIA Portal V20+ PLC programming. Generates error-free SCL code using native functions from a 222-function database. Bilingual support (Italian/Eng...
Riferimento per funzioni di sistema SCL (TIA Portal V20+) con sintassi e anti-pattern. Usa quando devi generare o revisionare codice SCL per S7-1200/S7-1500, scegliere funzioni native o chiarire la sintassi di...
Interviews users to clarify their thinking instead of writing for them. Use when asked to help with writing, content ideas, exploring topics, or reviewing drafts. Reads existing notes to identify themes, asks p...
Create a new release version. Use when asked to create a release, prepare a release, bump version, or update the changelog.
Use when automating desktop interactions via OSCTRL CLI - mouse, keyboard, screen capture, window management. ALWAYS get context before mouse operations.
Codex-native skill creator. Self-contained 4-phase methodology for creating production-ready Claude Code skills. Adapted from SkillCreator v3.2 for Codex agents with embedded methodology and simulated synthesis...
Evaluate pipeline runs against ACCEPTANCE_MATRIX.md. Use after feature releases to verify acceptance criteria.
Advanced visibility analysis using head pose, face mesh, and temporal patterns. Use for face-visible vs body-only breakdowns.
Embedding backends (InsightFace/PyTorch+ONNXRuntime vs TensorRT). Use when optimizing embedding throughput or debugging drift/fallbacks.
Ultimate meta-skill for creating production-ready Claude Code skills. Uses deep iterative analysis with 11 thinking models, regression questioning until exhausted, evolution and timelessness as core lens, and m...
Face alignment, landmark extraction, and quality gating. Use when debugging alignment issues, reviewing rejected faces, or tuning quality thresholds.
Person detection, tracking, and Re-ID. Use when faces aren't visible but cast should still be tracked, or when debugging face-body association.
AI-powered pipeline diagnostics. Explains why faces weren't detected, tracked, embedded, or clustered using OpenAI GPT-4o analysis. Use when debugging pipeline issues, reviewing unclustered tracks, or understan...
Generate and improve unit tests using the Assured LLMSE approach from Meta's TestGen-LLM. Use this skill when users request help with writing unit tests, improving test coverage, adding test cases to existing t...
Scaffold Python projects with uv (package/Python version manager), hatchling (build tool), and pytest (testing). Generates onion architecture structure with domain, infrastructure, application, and presentation...
Comprehensive UI/UX design principles for web applications based on Sociomedia Human Interface Guidelines (SHIG). Use when Claude needs to design or review web application interfaces, evaluate UI/UX decisions a...
Integrate xAI's Grok models for multi-model collaboration. Triggers on "Ask Grok", "What does Grok think", "Have Grok analyze", or similar phrases. Provides access to grok_query, grok_analyze_code, grok_reason,...
Create, configure, and document custom Claude Code subagents, including choosing scope, defining YAML frontmatter, selecting tools, model, permission mode, hooks, and usage examples.
Inspect a repository and draft an AGENTS.md file using the standard template, capturing commands, structure, and workflow rules.
Release workflow for uti project. Use when user says "release", "create release", "bump version", "publish version", or wants to prepare a new version for distribution.
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。