seed-forge

seed-forge/harness-ai-kit

Skill Claude CodeCodex

本技能随 harness-ai-kit-plugin bundle 注册。完整版见团队仓库 skills/harness-ai-kit-ops/（可 install skill harness-ai-kit-ops --scope global 获取）。.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A set of guidelines for speeding up Docker images and programming-language package downloads in mainland China or other unstable cross-border networks. It covers sources and proxies for Docker, Debian, Alpine, Node, Python, Maven, Gradle, and Go.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

Domain-neutral capture base for operation manuals. Use when the user wants an AI agent to autonomously operate an accessible system (Web now, Client later), take step-by-step screenshots with interactive user confirmation, and produce a screenshot ledger and operation trace that a manual-writing skill (e.g.…

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A method for designing applications that use AI agents or large language models. It separates the application into stages such as understanding input, extracting information, choosing a strategy, executing, checking results, and producing an answer.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

Review completed dev sessions to decide whether work should be distilled into devlab- assets (skills, CLI tools, MCP servers, loops, subagents, or knowledge cards). Based on base-session-ai-kit-miner, specialized for dev workflows (不局限于前后端，覆盖全栈研发场景). Triggers on "devlab-ai-kit-miner", "devlab skill miner", "研发复盘"…

seed-forge/harness-ai-kit

Skill Claude CodeCodex

Provider-neutral CI/CD onboarding workflow for repository analysis, pipeline design, configuration boundaries, and release verification.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A guide for agreeing on how a separate frontend and backend communicate through APIs. An API contract defines field types, optional values, data formatting, error codes, and which configuration belongs on each side.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A workflow for finding and fixing SQL dialect differences in the data-access layer of an application. SQL is the language used to query databases, and Oracle, PostgreSQL, and MySQL each have variations; the workflow supports MyBatis, JPA, MyBatis-Plus, and SQLAlchemy.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A guide to safely changing existing database tables and moving their data. It covers backups, repeatable checks, migration, verification, and restoring the backup if something fails.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A testing approach for AI agents and data-focused applications that uses example cases and automatic checks. An evaluation set is a collection of inputs with expected outputs; it shows whether a change improved or damaged results.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A guide to testing complete business flows across a frontend, backend services, databases, and other connected systems. It uses tools such as Playwright, Jest, SuperTest, Testcontainers, and mock servers to test multi-service setups.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A backend API testing guide for Java, Python, and Node.js services. It covers REST and GraphQL APIs, which let software exchange requests and data, plus OpenAPI documents that describe those interfaces.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A workflow for finding and safely reducing technical debt—the maintenance problems that make code harder to change, such as oversized classes, duplication, and tangled dependencies. It keeps business behaviour unchanged and verifies the result with tests.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A shared reference library for designing and troubleshooting software tests. It collects guidance on test strategy, test data, automation patterns, performance testing, flaky tests, accessibility, browser testing, and REST or GraphQL APIs.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A testing setup guide that examines a project and directs it to the appropriate testing approach. It covers browser end-to-end tests, backend API tests, full-stack integration tests, performance tests, and tests for AI applications.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A rule set for understanding the structure and context of front-end web projects before changing their code. It supports gradual investigation and records evidence and confidence for what was learned.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A method for deeply checking an existing web system, including its screens, buttons, and HTTP APIs. It records each feature in a registry, runs repeatable cases, investigates false successes such as an HTTP 200 response with missing data, and preserves the results for regression testing.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

An integration guide for Apache ECharts, a JavaScript library for drawing interactive charts and diagrams, in Astro and other front-end projects. It explains selective loading, delayed loading, custom chart types, and passing data through Astro Islands, which are server-rendered components that add client-side behaviour.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A front-end engineering guide for setting up, building, packaging, deploying, and maintaining web projects. It routes TypeScript or JavaScript projects by framework, with practical profiles for Vue and React and guidance for micro-frontends, which are web applications assembled from separately managed parts.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

Use when building a browser/web extension from scratch, especially one that extracts, downloads, or enhances data from an existing web app. Covers feasibility, reverse-engineering the target site's data channels, tech-stack selection (WXT + framework + Manifest V3), content/background/popup architecture, and a…

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A guide for connecting a browser-based application to Apache SkyWalking RUM, a monitoring system for real users in their browsers. It covers JavaScript errors, page performance, API calls, single-page app navigation, and links between browser and backend traces.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A browser end-to-end testing skill for Vue and React applications. End-to-end testing checks a feature through the browser, from a user's actions to the resulting behavior, using Playwright.

seed-forge/harness-ai-kit

Skill Claude CodeCodex

Web 视觉化操作（Web Visual Operations）：对 Web 应用做 Observe/Navigate/Interact/Inspect/Validate/Capture 的 day-2 操作手册。Router 层统一编排 Playwright（确定性）、Stagehand（AI 增强）、DevTools（Console/Network/Runtime）、Vision/CUA（视觉兜底）四类执行器，覆盖 Debug / UI Review / Visual Regression / E2E / Browser Automation 五类 Workflow。Stagehand 定位为 Router 的 AI…

seed-forge/harness-ai-kit

Skill Claude CodeCodex

A usage guide for @xyflow/react, a React library for interactive node-and-connection diagrams. It explains custom nodes and edges, zooming, panning, dragging, connecting, and integrating the canvas into Astro applications.