huangwb8

72 mods across 3 repositories, 3.0k stars between them.

huangwb8/ChineseResearchLaTeX

Skill Claude CodeCodex

A research-literature interpretation skill for explaining one academic paper. It traces what problem the paper addresses, how its method works, what evidence supports it, and where its conclusions may not apply.

not rated 2.9k +62 changed 1mo ago A SkillSpector: pass 89 tokens original MIT

huangwb8/ChineseResearchLaTeX

Skill Codex

A research workflow for finding, judging, classifying, tracking, and archiving important research papers. It treats bioRxiv and similar sources as places where researchers share papers, and combines database searches with other discovery signals.

not rated 2.9k +62 changed 1mo ago A SkillSpector: pass 96 tokens original MIT

huangwb8/ChineseResearchLaTeX

Skill Claude CodeCodex needs its repo

A literature-search workflow that finds candidate research papers from a topic and a set of queries. It cleans up paper details, removes duplicates, records where results came from, and produces a checkable results bundle.

not rated 2.9k +62 changed 1mo ago A SkillSpector: pass 49 tokens original MIT

auto-draw-plot

28

huangwb8/skills

Skill Claude CodeCodex

A workflow for planning and creating images from a written description. It supports general images as well as roadmaps, flowcharts, schematics, and architecture diagrams.

not rated 50 changed 1mo ago B 108 tokens original MIT

auto-test-code

29

huangwb8/skills

Skill Claude CodeCodex

A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.

not rated 50 changed 1mo ago A SkillSpector: pass 56 tokens original MIT

auto-test-project

30

huangwb8/skills

Skill Claude CodeCodex

A structured process for testing and improving a complete software project. It runs repeated critical tests and broader quality checks across the project.

not rated 50 changed 1mo ago A SkillSpector: pass 83 tokens original MIT

auto-test-skill

31

huangwb8/skills

Skill Claude CodeCodex

A structured process for critically testing and improving a coding skill. It records test plans, findings, fixes, and quality checks in files that can be reviewed later.

not rated 50 changed 1mo ago A SkillSpector: pass 61 tokens original MIT

awesome-code

32

huangwb8/skills

Skill Claude CodeCodex

A coordinator for complex software work involving multiple AI agents. It discovers available agents and project rules, then chooses whether the work should use one agent or several in parallel or sequence.

not rated 50 changed 1mo ago A SkillSpector: pass 67 tokens original MIT

backend-specialist

33

huangwb8/skills

Skill Claude CodeCodex

A guide for designing and building backend services, the parts of an application that handle data, business rules, and requests. It covers APIs, databases, authentication, and service performance.

not rated 50 changed 1mo ago A SkillSpector: pass 62 tokens original MIT

brainstorming

34

huangwb8/skills

Skill Claude CodeCodex

A guided design discussion that uses questions to clarify what should be built before coding starts. It compares possible approaches and removes unnecessary requirements.

not rated 50 changed 1mo ago A SkillSpector: warn 65 tokens original MIT

code-reviewer

35

huangwb8/skills

Skill Claude CodeCodex

A code-review workflow that checks completed work against its requirements or plan before merging. It groups findings by severity and gives each issue a fix and a way to verify it.

not rated 50 changed 1mo ago A SkillSpector: pass 40 tokens original MIT

context-optimizer

36

huangwb8/skills

Skill Claude CodeCodex

A context-management assistant for long conversations with AI agents. It helps organize the information an agent needs when conversations become large or contain conflicting details.

not rated 50 changed 1mo ago A SkillSpector: pass 48 tokens original MIT

devops-specialist

37

huangwb8/skills

Skill Claude CodeCodex

A DevOps and operations guide for running software reliably. DevOps combines software development with the work of building, deploying, monitoring, and maintaining systems.

not rated 50 changed 1mo ago A SkillSpector: pass 55 tokens original MIT

huangwb8/skills

Skill Claude CodeCodex

A technical-writing assistant for creating and maintaining developer documentation, such as README files and API references. API documentation explains how software interfaces accept requests and return responses.

not rated 50 changed 1mo ago A SkillSpector: pass 47 tokens original MIT

frontend-specialist

39

huangwb8/skills

Skill Claude CodeCodex

A front-end development workflow for building or improving web pages, components, layouts, forms, dashboards, and responsive interfaces. It covers common tools and frameworks such as React, Vue, Next.js, Tailwind, and CSS.

not rated 50 changed 1mo ago A SkillSpector: pass 61 tokens original MIT

git-workflow

40

huangwb8/skills

Skill Claude CodeCodex

A Git workflow guide for organizing commits, branches, pull requests, releases, and automated version-control tasks. Git is the system developers use to track code changes and collaborate.

not rated 50 changed 1mo ago A SkillSpector: warn 47 tokens original MIT

mirror-optimizer

41

huangwb8/skills

Skill Claude CodeCodex

A skill that detects a project’s package managers and configures regional package mirrors, mainly for deployments from mainland China. Package mirrors are alternate servers for downloading dependencies such as libraries and container images.

not rated 50 changed 1mo ago A SkillSpector: warn 73 tokens original MIT

huangwb8/skills

Skill Claude CodeCodex

A coordinator for carrying out software implementation plans with multiple coding agents. It splits work into independent tasks, assigns fresh agents, and adds review and testing checkpoints.

not rated 50 changed 1mo ago A SkillSpector: pass 32 tokens original MIT

security-specialist

43

huangwb8/skills

Skill Claude CodeCodex

A security review skill for finding risks in applications, such as broken access controls, unsafe input handling, exposed secrets, and insecure settings. It also considers threat modelling and compliance needs.

not rated 50 changed 1mo ago A SkillSpector: pass 48 tokens original MIT

huangwb8/skills

Skill Claude CodeCodex

A four-phase method for investigating software bugs and test failures before changing code. It focuses on finding and confirming the underlying cause.

not rated 50 changed 1mo ago A SkillSpector: warn 43 tokens original MIT

tdd-workflow

45

huangwb8/skills

Skill Claude CodeCodex

A test-first development workflow, commonly called TDD, where a failing test is written before the code that should make it pass. The cycle then adds the smallest working change and cleans it up.

not rated 50 changed 1mo ago A SkillSpector: pass 45 tokens original MIT

writing-plans

46

huangwb8/skills

Skill Claude CodeCodex

A guide for writing clear, multi-step plans for software changes. It explains the situation in everyday language before describing the technical work and how to check the result.

not rated 50 changed 1mo ago A SkillSpector: pass 29 tokens original MIT

bensz-collect-bugs

47

huangwb8/skills

Skill Claude CodeCodex

A process for recording bugs caused by defects in Bensz skills. It stores a structured local report and can publish one only when the user explicitly asks.

not rated 50 changed 1mo ago A SkillSpector: pass 68 tokens original MIT

better-prompt

48

huangwb8/skills

Skill Claude CodeCodex

A prompt editor that turns rough instructions for AI systems into clearer, more complete prompts. It follows published OpenAI and Anthropic guidance.

not rated 50 changed 1mo ago A SkillSpector: pass 107 tokens original MIT

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: