houshuang

13 mods across 3 repositories, 16 stars between them.

alif CLAUDE.md

01

houshuang/alif

Instructions file

Claude Code instructions for houshuang/alif, covering alif — arabic reading & listening trainer, project overview, quick start, backend and frontend.

10 4d ago C 12,933 tokens

autoresearch

02

houshuang/awesome-claude-code

Skill Claude CodeCodex

Run automated experiment loops to optimize algorithms, parameters, or prompts. Two modes: 'grid' for systematic parameter sweeps with Optuna TPE + WilcoxonPruner, 'creative' for Karpathy-style LLM-proposed changes. Use when: optimizing algorithm parameters, tuning thresholds, prompt optimization, ablation studies, or…

3 4mo ago A 120 tokens

calibration-eval

03

houshuang/awesome-claude-code

Skill Claude CodeCodex

Generate interactive HTML evaluation pages for collecting human ground-truth judgments on structured data from any project. Use when a project needs calibration data, quality audits, inter-rater evaluation, algorithm tuning, or ground truth labeling. Triggers on: /calibration-eval, 'evaluate these', 'need ground…

3 4mo ago A 89 tokens

claude-api

04

houshuang/awesome-claude-code

Skill Claude CodeCodex

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming questions.

3 4mo ago C 78 tokens

frontend-design

05

houshuang/awesome-claude-code

Skill Claude CodeCodex

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…

3 4mo ago A 77 tokens

knowledge-probe

07

houshuang/awesome-claude-code

Skill Claude CodeCodex

Adaptively map what a user knows about a topic via an interactive HTML assessment page, then generate a personalized HTML explainer. Uses limbic.amygdala's knowledgemap module for entropy-maximizing probes and Bayesian belief propagation. Can load existing knowledge graphs or generate new ones from topic descriptions.…

3 4mo ago A 93 tokens

playwright-e2e

08

houshuang/awesome-claude-code

Skill Claude CodeCodex

Write Playwright e2e tests with semantic selectors and accessibility-first assertions. Use when creating or modifying e2e tests (.spec.ts files using Playwright).

3 4mo ago A 38 tokens

pr-walkthrough

09

houshuang/awesome-claude-code

Skill Claude CodeCodex

Generate a detailed, pedagogical HTML walkthrough of a PR or feature branch. Use when the user wants to understand, document, or share how a PR works — covering architecture, data flow, design decisions, tradeoffs, and extension patterns. Triggers on requests like "walk me through this PR", "explain this branch"…

3 4mo ago A 84 tokens

readme-writer

10

houshuang/awesome-claude-code

Skill Claude CodeCodex

Write README documentation focused on deep understanding and mental models. Use when asked to document a package, write a README, or create documentation for a library.

3 4mo ago A 35 tokens

useeffect-review

11

houshuang/awesome-claude-code

Skill Claude CodeCodex

Reviews React code for correct useEffect usage. Use when reviewing React components, checking for useEffect anti-patterns, or deciding whether useEffect is appropriate for a given use case.

3 4mo ago A 40 tokens

visual-explainer

12

houshuang/awesome-claude-code

Skill Claude CodeCodex

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to…

3 4mo ago A 90 tokens

limbic CLAUDE.md

13

houshuang/limbic

Instructions file

Instructions for houshuang/limbic, covering limbic — ai agent guide, rules of thumb, always whiten domain-focused corpora, always genericize number-heavy text and clustering thresholds depend on whitening.

3 5d ago A 1,933 tokens original MIT