Instructions file CodexOpenCode
A repository instruction file for maintaining Skill-hub, a collection of reusable skills for coding agents. It explains where skills belong, how they are named, and which indexes and publishing rules apply.
Skill Claude CodeCodex
Use when managing Alibaba Cloud Simple Application Server (SWAS OpenAPI 2020-06-01) resources end-to-end, including querying instances, starting/stopping/rebooting, executing commands (cloud assistant), managing disks/snapshots/images, firewall rules/templates, key pairs, tags, monitoring, and lightweight database…
Skill Claude CodeCodex
A configuration guide for interactive cards in Feishu, a workplace messaging platform, when a bot uses a persistent WebSocket connection. It explains card templates, event routing, dropdown handling, button callbacks, and response formats.
Skill Claude CodeCodex
Use when operating Alibaba Cloud through a custom OpenAPI MCP server, especially for SWAS deployment workflows: OAuth setup, selector updates, missing-tool diagnosis, deployment permission closure, and pre-deploy verification.
Skill Claude CodeCodex
An automation guide for Feishu, also called Lark, a workplace app for chat, documents, databases, tasks, and calendars.
Skill Claude CodeCodex
A Chinese-language workflow for building, auditing, and testing reference data from 163 email, a NetEase email service. It includes special handling for connecting to 163 through IMAP, a standard email access protocol.
Skill Claude CodeCodex
Use for unattended QQ controlled frontend lockcheck runs, failure classification, bounded autofix decisions, and packaging-gate evidence in this repository. Trigger when the task is to automate full frontend batch tests, run controlled lockcheck loops, classify QQ truth-audit failures, or decide whether an autofix may…
Skill Claude CodeCodex
A testing procedure for running batches and checking results against verified email reference data. It is written in Chinese and includes separate handling for QQ and 163 email accounts, including regression checks after changes.
Skill Claude CodeCodex
Build, rebuild, audit, and compare QQ mailbox invoice ground truth datasets for this repository using the existing truth-building scripts and evidence artifacts. Use when the task is to generate a QQ mailbox ground truth set, validate QQ batch output against truth, review QQ mailbox invoice evidence, or investigate…
Skill Claude CodeCodex
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
Skill Claude CodeCodex
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. Use it proactively when an existing skill could be a ready-made building block, while keeping installation scoped to the…
Skill Claude CodeCodex
Qualify Windows desktop installers in GitHub Actions and promote verified Windows/macOS assets from one frozen SHA. Use for cloud packaging, installer failures, or GitHub Release publication; not local packaging or macOS qualification.
Skill Claude CodeCodex
A consultation workflow that uses GPT 5.6 Sol Pro as an outside reviewer when the user explicitly requests it.
Skill Claude CodeCodex
Review a compact fixture contract.
Skill Claude CodeCodex
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships. Use when output must clear two independent adversarial reviewers before it ships.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Skill Claude CodeCodex
Manage Agent Skills across Codex, Claude Code, local/global/project roots, Skill Hubs, GitHub, skills.sh, and managed plugin caches. Use when searching, installing, updating, upgrading, syncing, merging, auditing, deduplicating, cleaning, packaging, publishing, validating, resolving upstream sources, choosing runtime…
Skill Claude CodeCodex
Project-private fixture that must not be flattened into the local shared root.
Skill Claude CodeCodex
Shared fixture from the repository.
Skill Claude CodeCodex
A safety-focused Windows maintenance workflow for auditing and cleaning storage or investigating memory problems.
Skill Claude CodeCodex
Patterns for implementing Apple's Liquid Glass — a dynamic material that blurs content behind it, reflects color and light from surrounding content, and reacts to touch and pointer interactions. Covers SwiftUI, UIKit, and WidgetKit integration.