Development skills

Atomically ingest one already-verified evidence row into one named Gaia skill using the CLI, then appraise Trust Magnitude and propose—never silently apply—a calibration. Use after /ev-pipeline has verified an approved intake source, or whenever a curator says "ingest evidence", "add verified evidence", "gaia-ingest", or "turn this source into registry evidence".

The English summary is being prepared. Showing the original description.

Discovery-only global trending extension for Gaia. Snapshots configured external skill sources, prioritizes five-candidate pages for L4 review, and stops before trust, evidence, intake, or registry mutation.

The English summary is being prepared. Showing the original description.

Run any installed skill on several models at once — you, OpenAI Codex, OpenCode and whoever else the profile names — and show what each one made of it side by side. Every model gets the same prepared copy of the skill and works read-only. Use for "/multi:skill <name>", "run this skill on every model", "run <skill> through multi", or any skill whose answer you want from more than one model.

The English summary is being prepared. Showing the original description.

Put one question to several models at once — you, OpenAI Codex, and a cheap third via OpenCode — and show all the answers side by side. No judging, no consensus: three opinions, the user picks. Use for "ask everyone", "what do the other models think", "second opinion", "multi ask", or any open question where one model's answer is not enough.

The English summary is being prepared. Showing the original description.

Code review by several models at once — Claude sub-agents, OpenAI Codex, and a cheap third reviewer via OpenCode — reconciled into one report. Reviews whatever is named: a diff, a branch, specific files, one function, a legacy module, a whole repo. Use for any review request, a second or third opinion, a cross-check before a PR, or "code-review", "multi", "consensus review".

The English summary is being prepared. Showing the original description.

Execute a project from a folder of raw materials. Use when the user drops messages, screenshots, documents, drafts, and references into a project directory and wants Codex to identify the real goal, build a plan, do the work, drive the project to a submission-ready state, verify completion, and return a clear final summary of what was required, what was completed, and how it was done.

The English summary is being prepared. Showing the original description.

Runs a single Codex (ChatGPT/OpenAI) review check-fix cycle on a PR using gh CLI. Use this skill whenever the user wants to: check and fix Codex review comments, request a Codex code review on a PR, or iterate on PR feedback from the chatgpt-codex-connector bot. Trigger on phrases like 'codex review', '@codex review', 'fix codex comments', 'iterate on PR', 're-review with codex', or when the user mentions 'gh pr' with 'codex'. Combine with /loop for automated repeated cycles, e.g. '/loop 2m /codex-review'.

The English summary is being prepared. Showing the original description.

Prepare or open a GitHub or Gitea pull request with an explicit AI-authorship disclosure, change classification, reproducible reviewer verification steps, and optional Mermaid diagram. Use whenever the user asks to prepare, write, open, create, push, ship, or get changes ready for a PR or review. Unless the user explicitly asks for a draft-only result, create or reuse a dedicated branch, verify the change, commit scoped files, push the branch, and then create the PR with gh or tea.

The English summary is being prepared. Showing the original description.

Generate a conventional commit message by analyzing staged git changes. Use when the user wants to create, write, or generate a git commit message from their current staged diff. Trigger on phrases like "commit", "commit message", "commit msg", "寫 commit", "提交訊息", "generate commit", or when the user has just finished making code changes and wants to commit them. Also trigger when the user runs /commit-message.

The English summary is being prepared. Showing the original description.

Runs a single Copilot review check-fix cycle on a PR using gh CLI. Use this skill whenever the user wants to: check and fix Copilot review comments, request a Copilot code review on a PR, or iterate on PR feedback. Trigger on phrases like 'copilot review', 'fix PR comments', 'iterate on PR', 're-review', or when the user mentions 'gh pr' with 'copilot'. Combine with /loop for automated repeated cycles, e.g. '/loop 2m /copilot-review'.

The English summary is being prepared. Showing the original description.

Write effective MCP server instructions for tool compaction support. Use when creating or updating the `instructions` parameter in MaaSProtectedFastMCP server initialization. Helps LLMs understand when to search for tools, workflow patterns, and cross-feature relationships.

The English summary is being prepared. Showing the original description.

安全重构代码技能。当用户明确提到"重构"、"代码异味"或需要在TDD循环的Refactor阶段改进代码内部结构时使用。 **仅在以下场景触发**： - 用户明确说"重构这段代码" - 提到"代码异味"并要求改进 - TDD循环中的Refactor阶段 - 代码审查中需要改进内部结构但不改变功能 **注意**：如果用户只是说"优化"、"改进"或"提升性能"，不应该触发此技能，除非明确提到"重构"。

The English summary is being prepared. Showing the original description.

前端 UED 开发工作流——数据先行、分步实施、迭代精化。当你需要设计或修改前端页面、组件、交互流程时使用此 skill，包括新页面开发、现有页面重构、可视化图表、Bug 调试、交互优化。即使用户只是说'改一下首页'或'这个图显示不对'，也应参考此工作流。覆盖 Vue / React / Svelte 等主流前端框架。

The English summary is being prepared. Showing the original description.

架构师工作技能 - 架构设计、文档管理、语义化版本控制、设计审查。当用户提到架构、设计文档、版本管理、技术选型、系统设计、数据模型、API设计、文档审查、设计规范、架构决策、或需要创建/更新设计文档时，必须使用此技能。确保所有设计文档遵循语义化版本规范和命名约定。

The English summary is being prepared. Showing the original description.

代码提交与 MR 创建技能 - 自动生成语义化 commit message、创建符合规范的 GitLab Merge Request、验证飞书工作项关联。当用户提到 Git 提交、commit、push、推送代码、创建 MR、创建 PR、合并请求、或需要提交代码、推送代码、创建 MR/PR 时，必须使用此技能。支持交互式（对话）和非交互式（参数）两种模式。

The English summary is being prepared. Showing the original description.

安全重构代码技能。当用户明确提到"重构"、"代码异味"或需要在TDD循环的Refactor阶段改进代码内部结构时使用。

The English summary is being prepared. Showing the original description.

This skill provides expert-level guidance for Test-Driven Development (TDD) in VS Code extension development following t-wada methodology. Use when writing tests before implementation, creating comprehensive test suites, implementing Red-Green-Refactor cycles, or improving test coverage for extension components like WebViews, terminal managers, and activation logic.

The English summary is being prepared. Showing the original description.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. This skill should be used after implementing features or bug fixes to clean up code, when refactoring for readability, or when reducing unnecessary complexity. It launches the code-simplifier subagent provided by the code-simplifier@claude-plugins-official plugin.

The English summary is being prepared. Showing the original description.

Pull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch). Use when Codex needs to sync a feature branch with origin, perform a merge-based update (not rebase), and guide conflict resolution best practices.

The English summary is being prepared. Showing the original description.

This skill enables GitHub repository documentation exploration using DeepWiki API directly via curl. Use when researching repository structure, understanding library APIs, or asking questions about open-source projects. MCP server not required.

The English summary is being prepared. Showing the original description.

This skill enables web scraping and content extraction using Firecrawl API directly via curl. Use when scraping web pages, crawling websites, or extracting structured data. MCP server not required.

The English summary is being prepared. Showing the original description.

This skill provides guidance for using DeepWiki MCP to explore GitHub repository documentation. Use when researching repository structure, understanding library APIs, asking questions about open-source projects, or exploring documentation for any GitHub repository.

The English summary is being prepared. Showing the original description.

Investigate stuck runs and execution failures by tracing Symphony and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly.

The English summary is being prepared. Showing the original description.

This skill provides expert-level guidance for VS Code extension development. Use when implementing new extension features, debugging extension code, designing WebView UIs, implementing Language Server Protocol features, or optimizing extension performance. Covers activation events, contribution points, VS Code API patterns, security best practices, testing strategies, and publishing workflows.

The English summary is being prepared. Showing the original description.