← All creators

liujiarui0918

User

Batteries-included Claude Code setup: 33 skills / 22 agents / 25 commands / 11 hooks / 8 MCPs + one-click installer for Windows & macOS

54 indexed · 0 Featured · 0 stars · avg score 62
Prolific

Categories

Indexed Skills (54)

AI & Automation Listed

condition-based-waiting

Use when waiting for something async. NEVER use Start-Sleep blindly — wait on conditions.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

defense-in-depth

Use when a critical invariant matters. Single-layer protection is a tech-debt smell.

0 Updated yesterday
liujiarui0918
Data & Documents Listed

document-handling

Use when reading/writing docx/pdf/pptx/xlsx files. Prefer programmatic libs over shelling out.

0 Updated yesterday
liujiarui0918
Data & Documents Listed

extracting-from-images

Use when user pastes a screenshot / image. Extract text, layout, intent — don't just describe pixels.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

incremental-context-building

Use when entering a large unfamiliar codebase. Build understanding in layers, not all-at-once.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

lean-context

Use to keep context lean. Read only what you need. Compress aggressively.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

mcp-builder

Use when building a new MCP server. Covers stdio vs HTTP, tool schema, error handling.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

prompt-engineering

Use when helping user write an LLM prompt. Cover structure, examples, output format, anti-patterns.

0 Updated yesterday
liujiarui0918
Code & Development Listed

receiving-code-review

Use when receiving review feedback. Reason about each item — don't performatively agree.

0 Updated yesterday
liujiarui0918
Code & Development Listed

requesting-code-review

Use BEFORE handing off / committing. Self-review checklist to run between tasks.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

root-cause-tracing

Use when fixing a bug. Trace along the call chain to the source — don't stop at the symptom.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

skill-creator

Use when authoring a new skill. Standardized template + quality checklist.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

subagent-driven-development

Use for complex multi-task work. One fresh subagent per task + two-stage review.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

using-claude-api

Use when writing or debugging code that calls Anthropic SDK. Covers Opus 4.7, prompt caching, tool use, vision, batch, thinking.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

using-context7

Use when working with any library/framework/SDK to fetch current docs. Beats training-data memory which is stale.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

using-cron

Use when user wants "remind me in N min", "check every hour", "run X daily", or any scheduled work. Pick session-only vs durable correctly.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

using-git-worktrees

Use when starting a feature. Isolate work in a worktree to keep main clean.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

using-memory

Use when working with the auto-memory system. What goes in / stays out / how to update.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

using-playwright

Use when verifying UI changes, scraping web data, or automating browser flows.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

using-sequential-thinking

Use for complex multi-step reasoning where you need to think out loud, revise, branch.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

using-task-list

Use when deciding whether to TaskCreate. Tasks track multi-step work — don't open one for trivial single-step jobs.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

verification-before-completion

Use BEFORE claiming any task complete. "Looks right" is not verification.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

writing-skills

Use when creating a new skill. Meta-skill with template + anti-patterns.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

condition-based-waiting

Use when waiting for something async. NEVER use Start-Sleep blindly — wait on conditions.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

defense-in-depth

Use when a critical invariant matters. Single-layer protection is a tech-debt smell.

0 Updated 1 weeks ago
liujiarui0918
Data & Documents Listed

document-handling

Use when reading/writing docx/pdf/pptx/xlsx files. Prefer programmatic libs over shelling out.

0 Updated 1 weeks ago
liujiarui0918
Data & Documents Listed

extracting-from-images

Use when user pastes a screenshot / image. Extract text, layout, intent — don't just describe pixels.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

incremental-context-building

Use when entering a large unfamiliar codebase. Build understanding in layers, not all-at-once.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

lean-context

Use to keep context lean. Read only what you need. Compress aggressively.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

mcp-builder

Use when building a new MCP server. Covers stdio vs HTTP, tool schema, error handling.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

prompt-engineering

Use when helping user write an LLM prompt. Cover structure, examples, output format, anti-patterns.

0 Updated 1 weeks ago
liujiarui0918
Code & Development Listed

receiving-code-review

Use when receiving review feedback. Reason about each item — don't performatively agree.

0 Updated 1 weeks ago
liujiarui0918
Code & Development Listed

requesting-code-review

Use BEFORE handing off / committing. Self-review checklist to run between tasks.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

root-cause-tracing

Use when fixing a bug. Trace along the call chain to the source — don't stop at the symptom.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

skill-creator

Use when authoring a new skill. Standardized template + quality checklist.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

subagent-driven-development

Use for complex multi-task work. One fresh subagent per task + two-stage review.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

using-claude-api

Use when writing or debugging code that calls Anthropic SDK. Covers Opus 4.7, prompt caching, tool use, vision, batch, thinking.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

using-context7

Use when working with any library/framework/SDK to fetch current docs. Beats training-data memory which is stale.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

using-cron

Use when user wants "remind me in N min", "check every hour", "run X daily", or any scheduled work. Pick session-only vs durable correctly.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

using-git-worktrees

Use when starting a feature. Isolate work in a worktree to keep main clean.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

using-memory

Use when working with the auto-memory system. What goes in / stays out / how to update.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

using-playwright

Use when verifying UI changes, scraping web data, or automating browser flows.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

using-sequential-thinking

Use for complex multi-step reasoning where you need to think out loud, revise, branch.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

using-task-list

Use when deciding whether to TaskCreate. Tasks track multi-step work — don't open one for trivial single-step jobs.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

verification-before-completion

Use BEFORE claiming any task complete. "Looks right" is not verification.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

writing-skills

Use when creating a new skill. Meta-skill with template + anti-patterns.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

brainstorming

Use BEFORE any creative or non-trivial design work. Socratic clarification first, then 2-3 approaches, then a spec.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

dispatching-parallel-agents

Use when ≥2 independent tasks exist. Dispatch all in a single message with multiple Agent calls.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

executing-plans

Use to execute a written plan. Run tasks in batches with human checkpoints.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

writing-plans

Use after brainstorming produces a spec. Break the spec into 2-5 minute independently-verifiable tasks.

0 Updated yesterday
liujiarui0918
AI & Automation Listed

brainstorming

Use BEFORE any creative or non-trivial design work. Socratic clarification first, then 2-3 approaches, then a spec.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

dispatching-parallel-agents

Use when ≥2 independent tasks exist. Dispatch all in a single message with multiple Agent calls.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

executing-plans

Use to execute a written plan. Run tasks in batches with human checkpoints.

0 Updated 1 weeks ago
liujiarui0918
AI & Automation Listed

writing-plans

Use after brainstorming produces a spec. Break the spec into 2-5 minute independently-verifiable tasks.

0 Updated 1 weeks ago
liujiarui0918

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.