Agent 代码测试
编码代理(Claude Code、Aider、Codex等)在自定义任务上的直接比较,包含通过率、成本、时间和一致性指标 一个轻量级 CLI 工具,用于在可复现的任务上对编码代理进行头对头比较。
部署、CI、监控、回滚 · 417 个 Skill
编码代理(Claude Code、Aider、Codex等)在自定义任务上的直接比较,包含通过率、成本、时间和一致性指标 一个轻量级 CLI 工具,用于在可复现的任务上对编码代理进行头对头比较。
Guide for migrating PowerToys modules from WPF to WinUI 3 (Windows App SDK).
| You are an expert full-stack web developer specializing in modern JavaScript/TypeScript stacks with React, Node.js, and databases.
Build or extend LobeHub Agent Signal pipelines for background or quiet agent work driven by event sources, semantic signals, and action handlers.
Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms…
> Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens.
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Agent skill for app-store - invoke with $agent-app-store name: flow-nexus-app-store description: Application marketplace and template management specialist.
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm name: code-review-swarm description: Deploy specialized AI agents t…
Agent skill for data-ml-model - invoke with $agent-data-ml-model name: "ml-developer" description: "Specialized agent for machine learning model development, training, and deployment" version: "1.0.0" makes outbound network calls; runs on Python.
Agent skill for github-modes - invoke with $agent-github-modes name: github-modes description: Comprehensive GitHub integration modes for wo…
Agent skill for neural-network - invoke with $agent-neural-network name: flow-nexus-neural description: Neural network training and deployment specialist.
Agent skill for ops-cicd-github - invoke with $agent-ops-cicd-github name: "cicd-engineer" description: "Specialized agent for GitHub Actions CI/CD pipeline creation and optimization" version: "1.0.0" requires GitHub API key; runs on Node.js.
Agent skill for production-validator - invoke with $agent-production-validator name: production-validator color: "#4CAF50" description: Prod…
Agent skill for release-manager - invoke with $agent-release-manager name: release-manager description: Automated release coordination and d…
Agent skill for release-swarm - invoke with $agent-release-swarm name: release-swarm description: Orchestrate complex software releases usin…
Agent skill for sandbox - invoke with $agent-sandbox name: flow-nexus-sandbox description: E2B sandbox deployment and management specialist.
Agent skill for scout-explorer - invoke with $agent-scout-explorer name: scout-explorer description: Information reconnaissance specialist that explores unknown territories, gathers intelligence, and reports findings to the hive mind through continuous memory updates You are a Scout Explorer, the eyes and sensors of the hive mind.
Agent skill for swarm - invoke with $agent-swarm name: flow-nexus-swarm description: AI swarm orchestration and management specialist.
Agent skill for workflow-automation - invoke with $agent-workflow-automation name: workflow-automation description: GitHub Actions workflow…
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms.
AI job search command center -- evaluate offers, generate CVs, scan portals, track applications Determine the mode from $mode: | Input | Mode | |-------|------| | (empty / no args) | discovery -- Show command menu | | JD text or URL (no sub-command) | auto-pipeline |
Automates CI/CD pipeline setup.
Profile and optimize Python code using cProfile, memory profilers, and performance best practices.
Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration.
Build production React Native apps with Expo, navigation, native modules, offline sync, and cross-platform patterns.
| Patterns for adding safety, trust, and policy enforcement to AI agent systems.
| Use this skill when changing the shared agent setup for the repository.
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations.
A general-purpose academic paper writing tool — 12-agent pipeline covering all disciplines, with higher education domain as the default refe…
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize.
Universal deep research tool — a domain-agnostic 13-agent team for rigorous academic research on any topic.
Generate quiz questions with answers on any topic.
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
Track and manage recruiting pipeline stages.
Ansible automation expert for playbooks, roles, inventories, and infrastructure management You are a seasoned infrastructure automation engineer with deep expertise in Ansible.
CI/CD reference for Megatron-LM.
Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls.
> Three tasks.
Orchestrate a complete paper writing workflow for: $ARGUMENTS This skill chains five sub-skills into a single automated pipeline: /paper-pla…
Draft a complete patent application based on: $ARGUMENTS This skill orchestrates the full patent drafting lifecycle -- from prior art search through jurisdiction-formatted filing documents.
Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates.
Use when optimizing PostgreSQL queries, configuring replication, or implementing advanced database features.
Builds and debugs Shopify themes (.liquid files, theme.json, sections), develops custom Shopify apps (shopify.app.toml, OAuth, webhooks), and implements Storefront API integrations for headless storefronts.
Generates publication-quality figures for ML papers from research context.
You generate a high-quality daily financial news report based on reliable sources, including macro trends, market movements, and key events.
Use when multiple plausible dates exist and "latest" is not implied.
Generate a source-backed weekly financial trading outlook from daily-finance, finance-core-analysis, and finance-explosive-article outputs plus fresh authoritative market data.
Analyze, explore, clean, and visualize datasets with statistical rigor.
Agent management expert.
> for evaluating whether the skill fits the user's team and workflow, and whether it duplicates something already installed) This QA check runs automatically as part of /legal-builder-hub:skill-installer.
Autonomous novel writing CLI agent with web workbench (InkOS Studio) - use for creative fiction writing, standalone short-fiction packages, cover generation, novel generation, style imitation, chapter continuation/import, EPUB export, AIGC detection, and fan fiction.
Bump the Plano version across all required files.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference.
Meta Ads deep analysis covering Facebook, Instagram, and Threads advertising in the Andromeda + GEM + Lattice era.
Orchestrates Android development tasks including project creation, deployment, SDK management, and environment diagnostics using the `android` command-line tool.
Nuxt full-stack Vue framework with SSR, auto-imports, and file-based routing.
> Audit the live site, not the source tree alone.
> Run all three phases of agent integration in a single session.
Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and drafts response Analyze a GitHub issue, classify it, check for duplicates, and draft an appropriate response.
Agentic Workflow Pattern Standard multi-agent pipeline for implementation tasks.
Reference guide for Agentica multi-agent infrastructure APIs Complete API specification for Agentica multi-agent coordination infrastructure.
Generate viral 9:16 YouTube Shorts (or TikTok/Reels clips) from a long-form YouTube URL or local video.
Build and run LLM-powered data processing pipelines with DocETL.
OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox DETECT PLATFORM FIRST.
Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis Invokes the code-reviewer persona for t…
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages Multi-stage pipeline for deep content an…
Run a full build-and-ship pipeline from a spec — use for hands-off project generation DO NOT call Skill() again.
Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done This generated Codex skill preserves an enforced…
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Create UML diagrams using PlantUML syntax.
花叔Design(Huashu-Design)——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索、设计方向顾问与专家评审。
翰林院 OpenViking 记忆增强 — 将小说写作 pipeline 的设定、摘要、伏笔接入 OpenViking 语义记忆。
Automate the full hoverfly release process — version bump, GitHub release, wait for CI, trigger Homebrew update.
Full pipeline: Recon -> Learn -> Hunt -> Validate -> Report.
Create a new Harbor task for evaluating agents.
当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。
Meta-skill for creating new Claude Code skills with configurable execution modes.
SKILL.md simplification with functional integrity verification.
Skill Install Guardian v3.0 - Professional Security Audit 当执行安全审计时,必须: 1.
Release skills to ClawhHub through the full publication pipeline — auto-scaffolding, OPSEC scan, dual review (agent + user), force-push rele…
| 你是写作基础设施部署器。
>- Run isolated E2E tests in devcontainer.
>- Execute CLI commands and tests inside the devcontainer.
>- Implement a feature following TDD workflow.
Evaluate Agent Skill design quality against official specifications and best practices.
Use when a test fails and you need to diagnose the root cause.
Design new Claude skills from structured idea specifications.
Mine Claude Code session logs for skill idea candidates.
Validate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (JSON schema compatibility), file naming conventions, and handoff integrity.
Testing framework for evaluating Databricks skills.
Query video analytics data and metrics from Elastic search via the VA-MCP server (port 9901).
Generating rich inline SVG diagrams to visually explain systems, processes, architectures, and abstract concepts.
AI 视频生成全流程:通过 6 个阶段(剧本→角色/场景设计→分镜→参考图→视频生成→后期剪辑)将用户想法转化为完整视频。
Spring Boot 3.x development - REST APIs, JPA, Security, Testing, and Cloud-native patterns.
PowerPoint slide deck generation and management using python-pptx with YAML-driven content and styling - Brought to you by microsoft/hve-core Generates, updates, and manages PowerPoint slide decks using python-pptx with YAML-driven content and styling definitions.
Generate editable PPTX from documents using local ppt-master pipeline.
Turn SOPs, URLs, or stated intent into an installed skill package.
A comprehensive auditor for any agent skill — including Manus, OpenClaw/ClawHub, Claude, LobeHub, or custom SKILL.md-based skills.
Enforces a disciplined workflow for coding, debugging, refactoring, and automation: brainstorm -> plan -> implement with verification (prefer TDD) -> review -> finish.
> Automated pipeline: session analysis -> duplicate check -> skill creation.
Use when creating Nuxt modules: (1) Published npm modules (@nuxtjs/, nuxt-), (2) Local project modules (modules/ directory), (3) Runtime extensions (components, composables, plugins), (4) Server extensions (API routes, middleware), (5) Releasing/publishing modules to npm, (6) Setting up CI/CD workflows for modules.
This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines.
Expert knowledge for Azure HPC Cache development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
Manage Kurtosis cluster settings.
Search for and install Agent Skills that give you specialized capabilities.
Authors deterministic and LLM rubric graders for skillgrade evaluations.
Sets up and runs skillgrade evaluation pipelines for Agent Skills.
Autonomous skill lifecycle manager.
Meta-skill for creating and managing Claude Code skills Meta-skill for creating new Claude Code skills, including skills that wrap MCP pipelines.
Create and push semantic version tags for CI/CD deployment.
Optional sidecar skill for controlled feedback-driven skill evolution.
| nf-core is a community-driven collection of **143+ curated Nextflow pipelines** for bioinformatics.
| Open-ST is an open-source spatial transcriptomics method that captures transcriptome-wide expression at sub-cellular resolution using sequencing-based spatial barcoding on Illumina flow cells.
| Best practices and workflows for single-cell and spatial omics data analysis, based on the Single-cell Best Practices book.
| Skills and workflows for upstream data processing steps that precede standard single-cell analysis (QC, normalization, clustering, etc.).
Browse and install community skills from the BioClaw Skills Hub.
Analyze skill effectiveness across sessions.
Deploy workflow for Vercel and Supabase Edge Functions npx vercel --yes npx vercel --prod --yes supabase functions deploy [name] --project-ref [ref] supabase functions deploy --project-ref [ref]
date: {當前時間,格式: 2022-01-01T00:00:00+08:00} author: davidlei categories: ["{category}"]
Reports on the newest news on a specific topic.
Run full Contextium session startup sequence with all agents Run the full startup agent pipeline to initialize this session.
股票投资调研执行引擎,执行8阶段投资尽调流程。
Runs SQL queries against the WordPress development database.
Evaluate Agent Skill design quality against official specifications and best practices.
Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR.
| Turn every hard-earned lesson into a reusable improvement.
> from rclpy.node import Node from rclpy.qos import QoSProfile, ReliabilityPolicy, HistoryPolicy from std_msgs.msg import String class PerceptionNode(Node): def init(self):; runs on Node.js.
Help users discover available skills and help Claudia pick the right one when a request is ambiguous.
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Scan a repository to bootstrap new skills or audit and update existing ones Bootstrap skills for a new repo, or audit and update skills in an existing one.
> You are helping a penetration tester with <technique description>.
>- Run isolated E2E tests in devcontainer.
>- Execute CLI commands and tests inside the devcontainer.
>- Implement a feature following TDD workflow.
| Run scenarios without the skill (RED — watch agent fail), write skill addressing those failures (GREEN), then close loopholes (REFACTOR).
> The conductor, not a player.
Automate HappyCapy skill creation by finding and adapting existing skills from anthropics/skills repository.
Autonomous 9-agent swarm that continuously contributes to open source projects on GitHub.
Use when implementing complex multi-step tasks, fixing critical bugs, or when quality and completeness matter more than speed - ensures comprehensive implementation without shortcuts through systematic analysis, implementation, and verification phases This skill ensures comprehensive, complete implementation of complex tasks without shortcuts.
Backend skills for Supabase — CRM, billing, support, and more Composable backend schemas for Supabase.
Terraform and OpenTofu infrastructure as code — module design, state management, multi-environment setups, remote backends, secrets manageme…
Breaks complex systems into atomic components, maps their relationships, and reconstructs them in optimized configurations to identify bottlenecks, critical failure points, and redesign opportunities.
Manage contacts, companies, deals, and pipeline with crm.cli — a headless CLI-first CRM backed by SQLite with a virtual filesystem interface…
Generate complete academic survey papers using multi-LLM parallel outline generation, RAG-based subsection writing, citation validation, and local coherence enhancement.
| Use when MCP returns no images, or when page-region cropping is needed:.
BoltzGen is an all-atom diffusion model that generates antibody, nanobody, and de novo miniprotein backbones conditioned on a target structure and a set of binding (hotspot) residues.
Instead, it answers four questions before any GPU compute is committed: This skill encodes the canonical decision tree, the modality → tool…
Thorough target research before design prevents wasted compute and failed campaigns.
一套完整的學術研究 Skill 套件,涵蓋從論文閱讀到撰寫、審稿的完整研究流程。
| 你是一位擅长信息可视化的设计师,能把文字描述转化为设计精美、布局清晰的图表 HTML 文件。
Comprehensive Terraform Infrastructure as Code skill covering resources, modules, state management, workspaces, providers, and advanced patt…
Give your OpenClaw agent a homelab.
Use when users ask how to write, explain, customize, migrate, secure, or troubleshoot GitHub Actions workflows, workflow syntax, triggers, m…
IT Manager Pro (Elite Leadership Advisor) workflow skill.
Pipeline for downloading academic paper full-text at scale.
You are a malware analysis expert and you are able to understand malware for any kind of platform including, Windows, MacOS, Linux or android.
Strategic business coach (Leila Hormozi-style) providing direct, no-BS guidance on scaling, resource allocation, systems thinking, and strategic decision-making for entrepreneurs.
Comprehensive DAG failure diagnosis and root cause analysis.
PDF processing: extraction, text mining, form filling, manipulation, OCR integration This skill provides tools for PDF processing, including text extraction, mining, form filling, manipulation, and OCR integration, to handle document workflows efficiently.
Assist with physics from intuitive explanations to formal derivations at any level.
> EVERY piece of content MUST go through the voice-master skill before publishing.
ERNE — Validate and submit app builds using parallel expo-config-resolver and code-reviewer agents You are executing the /erne-deploy comman…
ERNE — Manual skill generation — runs continuous-learning-v2 scripts to extract patterns from session You are executing the /erne-learn comm…
ERNE — Autonomous ticket execution — polls a provider, picks up ready tickets, and runs the full ERNE pipeline (validate, plan, code, test,…
Ollama API Documentation Comprehensive assistance with Ollama development - the local AI model runtime for running and interacting with large language models programmatically.
Improves an existing skill based on real project pain (prior eval corpora under .ai-engineering/evals/, Engram cross-session observations, L…
ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ.
Use when editing files under `plugin/asicrs/`, `sdk/rust/`, or `server/sdk/v1/pb/` (which the asicrs build also consumes).
Use this skill when committing VCSDD pipeline artifacts to git.
Self-referential loop until task completion with architect verification [RALPH + ULTRAWORK - ITERATION {{ITERATION}}/{{MAX}}] Your previous attempt did not output the completion promise.
使用 RuoYi-Vue 框架(SpringBoot + Spring Security + MyBatis + JWT + Vue)时应该使用此技能。
Vben Admin 5.0 前端框架开发技能。
How agents use ttal comment for review workflows - plan reviews, PR reviews, triage reports, and verdicts.
Expert guidance for developing cross-platform desktop applications with Avalonia UI framework.
Enforce coding standards, style guides, and architectural patterns across projects.
| This skill enables Claude Code to work effectively with Lovable.dev projects while respecting Lovable's deployment requirements.
Universal validation and knowledge capture.
Enable ControlKeel governance for Cloudflare Agents with policy gates, budget enforcement, PII detection, and secure execution.
Performs comprehensive deep analysis of entire codebase and deployment pipeline to identify issues in production environment.
Analyze manufacturing defect detection and quality control systems — computer vision inspection pipelines, SPC control charts, Six Sigma pro…
Comprehensive PocketBase development and deployment skill providing setup guides, schema templates, security patterns, API examples, data management scripts, and real-time integration patterns for building backend services with PocketBase.
Intake gate for adding new system or infrastructure components to Anton.
Expose a workload for access.
Triage ntfy.sh-routed alerts in Anton — identify which alert fired, why it fired (or why it didn't deliver), and propose a fix.
> 适用于 兼职/ 下所有需要交付 Word 报告、论文式分析说明、正式统计表或客户可见结果文档的任务。
Diagnose broken CI pipelines across GitHub Actions, GitLab CI, and similar build systems by inspecting configs, logs, caches, artifacts, and step failures.
Master creative specialized skill 38 with comprehensive coverage of concepts, implementation, optimization, and production best practices.
Docker 多服务部署最佳实践 - 遵循生产级 Dockerfile 和 Docker Compose 架构原则。
Improve Dockerfiles for image size, caching, security, reproducibility, and multi-stage build hygiene.
飞牛 fnOS FPK 应用包开发指南。
Amplify safe or boring designs to make them more visually interesting and stimulating.
Review Kubernetes manifests, deployment defaults, probes, resources, security context, and rollout safety.
Use this skill whenever a user asks for OSINT dorks, Google dorks, GHDB queries, Shodan filters, GitHub code search dorks, search operators, or exposed asset discovery.
Start any type of modern application — web apps, APIs, full-stack projects, Docker-based stacks, microservices, and more.
Start any type of modern application — web apps, APIs, full-stack projects, Docker-based stacks, microservices, and more.
act is an open-source CLI tool that runs GitHub Actions workflows locally using Docker, enabling fast feedback on workflow changes without pushing to GitHub.
Orchestrate the full add-a-program workflow on the crazy4points project (works for airlines, hotels, alliances, and credit cards — generic b…
Add a chunking hook for a new or existing language in the ingest pipeline.
Audits Claude Code agent configuration against latest best practices.
Audit and score an agent-definition markdown such as `AGENTS.md`, `CLAUDE.md`, `SKILL.md`, `SOUL.md`, `.cursorrules`, or a system prompt using a cold-reader rubric for clarity, consistency, context independence, and operating-model fit.
编码代理(Claude Code、Aider、Codex等)在自定义任务上的直接比较,包含通过率、成本、时间和一致性指标 Use when this capability is needed.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference.
Principal AI Architect.
>- Use when this capability is needed.
Comprehensive AI agent building skill merging Perplexity Computer's skill creation, webserver, and automation capabilities with Claude Code's agent orchestration, MCP server building, RAG system construction, subagent coordination, parallel agent dispatching, prompt optimization, and execution planning.
End-to-end workflow for redesigning a SaaS or AI product landing page and building an interactive AI agent UX flow.
> Use when this capability is needed.
Configure Akka.NET with .NET Aspire for local development and production deployments.
Akka.Management for cluster bootstrapping, service discovery (Kubernetes, Azure, Config), health checks, and dynamic cluster formation without static seed nodes.
Write unit and integration tests for Akka.NET actors using modern Akka.Hosting.TestKit patterns.
Use this skill when a local container won't start, a service is unreachable from the host, a local docker-compose stack is misbehaving, or a…
Evaluates ML applications in investment with feature engineering, model selection, and implementation considerations for alpha generation.
Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->
>- Use when this capability is needed.
Write integration tests using .NET Aspire's testing facilities with xUnit.
>- Transcribe audio/video to speaker-labeled text.
DevOps expertise for deployment, CI/CD, infrastructure, and automation To build and maintain the infrastructure, automation, and tooling that enables the development team to ship high-quality software efficiently and reliably.
Bootstrap a new host application on top of the published atrium base image, or retrofit an existing FastAPI / SQLAlchemy / React app onto atrium.
Scaffold a new FastAPI microservice from zero with ab0t-auth already integrated.
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using…
Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature.
> Use when this capability is needed.
Expert knowledge for Azure Database Migration service development including troubleshooting, decision making, limits & quotas, security, integrations & coding patterns, and deployment.
Expert knowledge for Azure Database for MySQL development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
Expert knowledge for Azure Database for PostgreSQL development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
Operate Azure SQL Database, Cosmos DB, and managed database services.
Expert knowledge for Azure SQL Database development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
Expert knowledge for Azure SQL Managed Instance development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
Expert knowledge for SQL Server on Azure Virtual Machines development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
>- Get the structured substrate the Bigdata.com MCP server doesn't hand over.
Use when creating a new project repository to initialize it with standard CLAUDE.md, .cursorrules, CLAUDE.local.md, SESSION_LOG.md, and gitignore entries Initialize a new project with the standard file structure for Claude Code and Cursor development.
Fast headless browser for QA testing and site dogfooding.
Post-deploy canary monitoring.
> Use when this capability is needed.
Python or Docker Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Python.
Set up CI/CD pipelines - use when working on related tasks Use when this capability is needed.
Automates CI/CD pipeline setup.
Scaffold/audit GitHub Actions CI/CD — Go/Rust/TS.
CI/CD patterns for mobile - GitHub Actions workflows for Android/iOS, Fastlane integration, code signing, artifact publishing, and automated release.
Design and implement production-grade CI/CD pipelines with GitHub Actions, layered testing strategies, secure deployment patterns, and environment management.
CI/CD review for workflows, artifact safety, caching, deployment gates, secrets, permissions, and reproducibility.
GitHub Actions security hardening, CI/CD pipeline integrity, release security, and SSDF alignment Use when this capability is needed.
仓库上下文(如:repo_name/branch/commit_hash/环境变量名) Use when this capability is needed.
Manage apps on a Cloudron server using the cloudron CLI.
Cockpit CMS is a lightweight headless content platform for teams that want flexible models, REST and GraphQL APIs, and self-hosted deployment without a heavy stack.
> Use when this capability is needed.
Use whenever the user is authoring or modifying Kubernetes configuration stored in ConfigHub, or is about to reach for Helm, Kustomize, Jsonnet, cdk8s, or a values file.
Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->
Normalize FFT_nano to Docker-first runtime defaults.
Keeps examples/integrations/* demos aligned to the north-star (langgraph-python).
Analyze code coverage and CRAP (Change Risk Anti-Patterns) scores to identify high-risk code.
Chief Security Officer mode.
SQL database migrations with zero-downtime strategies for PostgreSQL, MySQL, and SQL Server.
Debug nano-core agent runtime issues (Docker default, host opt-in).
Deploy Grokky — start Docker, ensure grok_spawner, build images, publish package Use when this capability is needed.
| Use when this capability is needed.
Initialize and configure local development tooling for TypeScript, Rust, and Python projects including monorepos.
Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Node.js.
Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes.
Develops iOS/macOS apps with XcodeGen, SwiftUI, and SPM, including Apple Developer signing, notarization, and CI/CD pipelines.
Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
Annotates codebases with dimensional analysis comments documenting units, dimensions, and decimal scaling.
Django + FastAPI development.
Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.
Run and triage Django/DRF security smoke checks for settings hardening, throttling, safe HTML, ORM race/idempotency patterns, and model integrity; especially useful before shipping or when evaluating djangoSecurityHunter-style findings.
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
Use the upstream install or setup path that matches your environment: Use when this capability is needed.
Runs systematic health diagnostics on Docker containers using docker inspect, docker stats, and the Docker Engine API.
Inspects Docker container health using the Docker Engine API v1.45 /containers/{id}/json and /containers/{id}/stats endpoints.
Start and verify the local Docker CDC lab (dvdrental), run the PostgreSQL load generators, reset Databricks tables, trigger Databricks notebook jobs through databricks.sdk, and check whether Bronze/Silver notebooks completed successfully.
Manage Docker containers, images, volumes, and networks.
</applicability> 文档在docs目录下,根据文档类型进行分类存放,如docs/tasks等。
Dokku is a self-hosted Platform-as-a-Service built on Docker that provides Heroku-like git-push deployment on your own infrastructure.
Managing local .NET tools with dotnet-tools.json for consistent tooling across development environments and CI/CD pipelines.
| Use when this capability is needed.
Complete DreamHost website management via SFTP/SSH for React JS deployments, multi-site routing, file operations, and content management.
Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.
Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.
Diagnose and resolve FFT_nano runtime issues across container execution, provider credentials, Telegram/WhatsApp routing, scheduler behavior, and per-group logs/state.
Drive the FFT_demo_dash holodeck system — scene triggers, agent commentary, canvas presets, and live weather mirroring — to produce impactfu…
Verify host prereqs (node, npm, container runtime) before running nano-core.
Operate FFT_nano Telegram workflows including main chat claiming, command safety boundaries, admin panel usage, media intake behavior, and Telegram-first deployment patterns.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities.
当用户需要在中国环境部署 Flutter 项目、配置国内镜像加速或解决依赖下载问题时使用。
Run a complete engineering project through Forge's 8-phase autonomous pipeline.
>- Audit the interface the user can actually see.
Use when working with a skill for managing and maintaining a project-wide `.gemini/GEMINI.md` repository manifest.
Write professional git commits using conventional format for clear communication and automated workflows.
在用户提及 GitHub 仓库、Issue、Pull Request、Actions、代码管理相关内容与操作时使用此技能。
Create and manage GitLab Merge Requests on gitlab.example.com repositories, driving them to a truly mergeable state.
Gitleaks is an open-source SAST tool for detecting hardcoded secrets like passwords, API keys, and tokens in Git repositories, files, and directories.
| Use when this capability is needed.
Write and review Go code with idiomatic project structure, errors, concurrency, testing, and performance guidance.
Write Go integration tests with testcontainers-go Use when this capability is needed.
> Use when this capability is needed.
Operate the homelab platform — start/stop services, backups, updates, disaster-recovery, and Docker management.
Configure AIDE (Advanced Intrusion Detection Environment) for file integrity monitoring including baseline creation, Use when this capability is needed.
Kubernetes NetworkPolicies provide pod-level network segmentation by defining ingress and egress rules that control Use when this capability is needed.
Use when the user is deciding how to slice Kubernetes YAML into ConfigHub Units — phrases like "one Unit or many?", "how should I split thes…
iOS/Swift development: SwiftUI, UIKit, Core Data, Xcode builds, simulator management, code signing, and App Store submission.
Autonomous iOS bug fixer.
Operate JellyCore services in Docker Compose with a safe runbook: start, stop, restart, health-check, inspect logs, and collect diagnostics.
K9s is a terminal-based UI for managing Kubernetes clusters, providing real-time observation of resources, log tailing, pod shell access, and cluster navigation.
Build, test, analyze, or start Docker for a Kotlin project Use when this capability is needed.
Kubernetes - use when working on related tasks Use when this capability is needed.
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring.
Assess the security posture of Kubernetes etcd clusters by evaluating encryption at rest, TLS configuration, access controls, backup encryption, and network isolation.
Diagnoses restart storms with the Kubernetes Events API, Pod status conditions, and the Metrics API to explain why workloads are stuck in CrashLoopBackOff.
Specialist in Kubernetes cost allocation, namespace and label-based chargeback, and cluster-level optimization.
Auditing Kubernetes cluster RBAC configurations to identify overly permissive roles, wildcard permissions, dangerous ClusterRoleBindings, service account abuse, and privilege escalation paths using kubectl, rbac-tool, KubiScan, and Kubeaudit.
Audit Kubernetes cluster security posture against CIS benchmarks using kube-bench with automated checks for control plane, worker nodes, and RBAC.
Perform security risk analysis on Kubernetes resource manifests using Kubesec to identify misconfigurations, privilege escalation risks, and deviations from security best practices.
Pod Security Standards (PSS) define three levels of security policies -- Privileged, Baseline, and Restricted -- enforced by the Pod Security Admission (PSA) controller built into Kubernetes 1.25+.
Kubernetes cluster management skill.
> Use when this capability is needed.
Kubernetes NetworkPolicies provide pod-level network segmentation by defining ingress and egress rules that control traffic flow between pods, namespaces, and external endpoints.
Implement Kubernetes network segmentation using Calico NetworkPolicy and GlobalNetworkPolicy for zero-trust pod-to-pod communication.
Use this skill whenever a user wants to onboard, deploy, install, or operate kubernetes-ontology; set up its Helm chart, release CLI, daemon, or topology viewer; run Kubernetes topology queries; diagnose Pod or Workload failures with AI-agent workflows; or connect human visual troubleshooting to the CLI and HTTP API.
Use when building a Kubernetes Operator — custom controllers that reconcile CRD state.
Pods, deployments, services, ingress, RBAC, autoscaling, and production cluster best practices Use when this capability is needed.
Kubernetes penetration testing systematically evaluates cluster security by simulating attacker techniques against the API server, kubelet, etcd, pods, RBAC, network policies, and secrets.
Diagnoses CrashLoopBackOff pods using kubectl describe, container exit code analysis, and the Kubernetes Events API.
Kubernetes and Helm standards for manifests, charts, values files, RBAC, workloads, networking, policy, validation, or deployment review.
Expert Kubernetes Specialist with deep expertise in container orchestration, cluster management, and cloud-native applications.
Use when the user asks to "upgrade Kubernetes", "upgrade k8s", "update Kubernetes version", "bump Kubernetes version", mentions a target version like "upgrade to 1.35.1", or when Renovate updates kubernetesVersion in talconfig.yaml.
Tunes container resource requests/limits AND node-level autoscaling (Karpenter, Cluster Autoscaler) for the right balance of cost, scheduling latency, and pod stability.
Land and deploy workflow.
Use when productionising or deploying a LangChain / LangGraph / DeepAgents agent.
Use when editing a non-agentic LCEL pipeline — composing Runnables, retrievers, embeddings, chat models, parsers, or building a RAG chain.
Use when creating a new LangChain / LangGraph / DeepAgents project from scratch.
Use when starting work on any LangChain / LangGraph / DeepAgents project.
LazyDocker is a terminal UI for Docker and Docker Compose that provides container management, log viewing, resource monitoring, and image inspection through a keyboard-driven interface.
>- List project-scoped local histories without reconstructing ad hoc rg, stat, discovery, schema introspection, filtering, de-duplication, t…
Start the local Docker Compose stack (backend + frontend) for development.
>- Use when this capability is needed.
Expert ML engineer specializing in MLOps, ML platform design, distributed training, model optimization, and production ML systems.
Use when answering CLRS-style machine-learning algorithm questions about k-means clustering, Lloyd's procedure, multiplicative weights, weighted majority, online experts, gradient descent, projected gradient descent, convex optimization, linear regression, or regularization.
Design and implement a complete ML pipeline for: $ARGUMENTS Use when this capability is needed.
>- Diagnose the actual source of disk pressure, reclaim only approved space, and prove that the cleanup did not damage user data or co-resident services.
Run live tests of the Ariadne MCP server using Claude Code in headless mode.
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "develop MCP tools", "implement MCP resources", or discusses building something with the Model Context Protocol.
> Use when this capability is needed.
Configure, deploy, and troubleshoot Model Context Protocol (MCP) servers for AI agent workflows.
Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT).
Mine the chat-arch corpus for correction patterns — moments where the user pushed back on the AI — and propose concrete upgrades to CLAUDE.m…
Machine learning pipelines - use when working on related tasks Use when this capability is needed.
This skill should be used when the user asks about "LSP", "language server", "gopls", "pyright", "rust-analyzer", "typescript-language-server", "multi-language project", "code completion", "diagnostics", or "editor language support".
使用 newsbox CLI 与 Python SDK 采集 AI 内容信源、读取 raw.db、二次加工成日报/摘要/筛选结果。
Build Next.js 16+ applications with App Router, server components, caching strategies, and production deployment patterns Use when this capability is needed.
NocoDB turns any SQL database into a smart spreadsheet with a full REST API.
Node.js + Express backend patterns.
Use when helping someone use okdev to initialize, start, inspect, connect to, sync with, troubleshoot, or tear down Kubernetes dev sessions, including manifest-backed and PyTorchJob workloads.
Ollama runs large language models locally with a simple CLI and REST API.
Run and audit OperatorOne Stage1 marketing SEO shadow experiments across input sync, context index, keyword graph, experiment synthesis, and Ready/Hold/Drop queueing.
Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
Use immediately for any pasted OpenClaw GitHub issue or PR URL/number, and for OpenClaw issue/PR review, triage, duplicate search, opener identity/who wrote it, author account age/activity, comments, labels, close, land, or maintainer evidence checks.
Manage the local Docker Compose development environment for Rails applications.
Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
Convert markdown files to professional PDF documents with proper Chinese font support, theme system, and visual self-check.
Turn a PDF into a single, self-contained, readable HTML file — images, tables, charts and reading order preserved — and optionally translate…
Kubernetes penetration testing systematically evaluates cluster security by simulating attacker techniques against Use when this capability is needed.
>- Two related pipelines, same destination look, different starting point: phone photos of paper documents, or a digital document that needs a synthetic signature before it looks signed.
Cache Playwright browser binaries in CI/CD pipelines (GitHub Actions, Azure DevOps) to avoid 1-2 minute download overhead on every build.
Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
Initialize a brand-new project from scratch with a default full-stack scaffold (Rust core + React Router 7 portal + Docker + Kubernetes).
Guides initial CockroachDB cluster provisioning and production deployment.
> Use when this capability is needed.
Deploy a Python project to the target environment.
Prepare Python projects with professional structure, documentation, and tooling.
Build reactive/event-driven C# with R3 (Cysharp's modern reimplementation of Reactive Extensions).
Locate root causes of failing regression tests by analyzing code changes, error messages, and test dependencies.
Keep repository documentation, AGENTS.md, and contributor/test guidance aligned with code, design, and product changes.
| +-- .pdf --> python parse.py --input resume.pdf --output resume.md | +-- .docx/.doc --> python parse.py --input resume.docx --output resum…
> Use when this capability is needed.
Execute and orchestrate external CLI-based agents to delegate subtasks, obtain specialized outputs, or compose multi-agent workflows.
> Ruzzy is a coverage-guided fuzzer for Ruby built on libFuzzer.
>- You are a SARIF parsing expert.
Guides through Trail of Bits' 5-step secure development workflow.
| Use when this capability is needed.
Test, analyze, or start Docker for the server project Use when this capability is needed.
Start Docker Compose services for local development and testing.
Run initial nano-core setup.
Configure deployment settings for /land-and-deploy.
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
>- Use when | Required evidence | Do not add by default |.
Use this skill when the agent is designing schemas, reviewing migrations, tuning queries, modeling NoSQL access patterns, configuring replic…
Use when working with an official MCP server that connects Supabase projects to AI assistants like Claude, Cursor, and Windsurf.
Complete Telegram bot creation for AI agents and pipelines.
Terraform IaC - use when working on related tasks Use when this capability is needed.
Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->
Terraform CLI 安装与初始化技能。
State management, modules, workspaces, remote backends, and multi-environment strategies Use when this capability is needed.
Basic usage or getting-started notes: Use when this capability is needed.
> Use when this capability is needed.
Terraform IaC management skill.
**UTILITY SKILL** — Reusable Azure Terraform patterns: hub-spoke, private endpoints, diagnostics, AVM-TF modules.
Terraform and OpenTofu standards for .tf, .tfvars, .tofu, modules, providers, state, plans, policy checks, and IaC review.
Use this skill when authoring or running a Terraform plan/apply, refactoring modules, performing state surgery, importing existing cloud res…
**WORKFLOW SKILL** — Discover existing Azure resources and bulk import them into Terraform management.
> Failure patterns from real deployments.
**WORKFLOW SKILL** — Write and run Terraform tests (.tftest.hcl).
Write integration tests using TestContainers for .NET with xUnit.
Token integration and implementation analyzer based on Trail of Bits' token integration checklist.
>- The deploy workflow now owns rotation end-to-end; this skill is a thin wrapper that decides which workflow input to pass, not a sequence of bash commands.
>- 适用于 TokenKey fork of sub2api。
>- 适用于通过 deploy-edge-lightsail-stage0.yml 部署的 Lightsail Edge(与 EC2 EIP 路径不通用)。
Use this skill when the user asks to "verify my deployment", "check if everything is working", "test my deployment", "check if my services are up", "run health checks", or when invoked by deploy-project as the final step after CI/CD setup.
|- Use when this capability is needed.
>- Systematically evaluate incoming vulnerability reports against 7 principled criteria before committing resources to deeper analysis.
You are a professional web designer and developer who creates complete, production-ready websites from concept to deployment.
Set up Wren Engine MCP server via Docker and register it with an AI agent.
Use when creating new skills, editing existing skills, or verifying skills work before deployment You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
Use this skill any time a spreadsheet file is the primary input or output.