huangxinxinyu/xinyu-s-skill-set
Skill Codex
Use when finishing non-trivial work, marking a goal complete, handing off code or documents, or when work may be drifting from the user's requested outcome and needs evidence-based acceptance before final response.
huangxinxinyu/xinyu-s-skill-set
Skill Codex
Use when preparing, splitting, staging, or creating git commits for completed work, especially when changes span multiple concerns, tests, files, or behavioral units and each commit should be independently reviewable and verifiable.
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
huangxinxinyu/xinyu-s-skill-set
Skill Codex
Use when researching current engineering solutions, comparing tools or architectures, tracking frontier engineering thinking, or needing high-signal X-first sources for modern software decisions.
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
Use when the user explicitly asks to start or resume the Multica delivery workflow for the target repository, or invokes $multica-delivery.
huangxinxinyu/xinyu-s-skill-set
Skill Claude Code
Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates taskplan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear.
huangxinxinyu/xinyu-s-skill-set
Skill Claude Code
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports…
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
huangxinxinyu/xinyu-s-skill-set
Skill Claude Code
Teach the user a new skill or concept, within this workspace.
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
Use when implementing any feature or bugfix, before writing implementation code.
huangxinxinyu/xinyu-s-skill-set
Skill Codex
Use when the user asks to connect to, inspect, operate, or read Docker/service logs from the Foodism test environment at 34.63.71.94.
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: