Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
respond
Add builder's exegesis to a critique post. Use /respond to add inline reflections to each Roman numeral section of a critique, exploring what it means for the ecosystem and the builder.
majiayu000/claude-skill-registry 163
-
web-developer-work-skill
Persistent context management system for web developers that never loses work between Claude Desktop sessions. Features automatic context backup, work session continuity, project state management, and comprehensive error recovery.
majiayu000/claude-skill-registry 163
-
self-improve-prompt-design
Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for agent experts, designing validation logic, or implementing the LEARN step of Act-Learn-Reuse.
majiayu000/claude-skill-registry 163
-
Objective-C ARC Patterns
Use when automatic Reference Counting in Objective-C including strong/weak references, retain cycles, ownership qualifiers, bridging with Core Foundation, and patterns for memory-safe code without manual retain/release.
majiayu000/claude-skill-registry 163
-
pre-commit-check
コミット前品質チェックスキル（Lint、テスト、ビルドの高速検証）
majiayu000/claude-skill-registry 163
-
telemetry-anomaly
Detect anomalies from live telemetry streams and propose remediation; use when asked to analyze SSE/WebSocket metrics for abnormal behavior.
majiayu000/claude-skill-registry 163
-
Classification Modeling
Build binary and multiclass classification models using logistic regression, decision trees, and ensemble methods for categorical prediction and classification
majiayu000/claude-skill-registry 163
-
copilot-pr-reviewer
Reviews pull requests created by GitHub Copilot agents before merging. Triggers on "review this PR", "check PR
majiayu000/claude-skill-registry 163
-
git-safe-workflow
Safely inspect, stage, commit, and (only if asked) push changes made by an AI agent. Use for commit/push requests, end-of-task checkpoints, merge conflict resolution, worktree safety checks, or deciding whether to use git commit --amend.
majiayu000/claude-skill-registry 163
-
bayesian-workflow
Use when performing Bayesian statistical analysis, building probabilistic models, or when the task involves prior specification, posterior inference, or predictive checks.
majiayu000/claude-skill-registry 163
-
local-config
This skill should be used for configuring devloop project settings via .devloop/local.md, git workflow preferences, commit settings, review options
majiayu000/claude-skill-registry 163
-
lang-go
Go 1.23+ development specialist covering Chi, GORM, and concurrent programming patterns. Use when building high-performance microservices, CLI tools, or cloud-native applications.
majiayu000/claude-skill-registry 163
-
Cursor Development Rules
Provides comprehensive development rules and guidelines for Cursor project development. Use when working on Cursor projects, setting up development environments, or implementing coding standards.
majiayu000/claude-skill-registry 163
-
HLS Troubleshooting
This skill should be used when the user mentions "HLS not working", "haskell-language-server issues", "Haskell LSP problems", "no completions in Haskell", "HLS diagnostics not showing", "troubleshoot HLS", "Haskell code analysis not working", or asks why HLS features aren't available in Claude Code.
majiayu000/claude-skill-registry 163
-
playwright-browser-install
To install the Playwright browser defined in config, run this when the browser is missing or not installed.
majiayu000/claude-skill-registry 163
-
extension-assessment
評估日文詞彙卡片的語用延伸需求。
分析六個面向：敬語、語氣、語域、褒貶義、暗喻、同義詞對比。
使用時機：
- 當想了解某個詞彙需要哪些延伸卡片
- 當需要評估詞彙的語用複雜度
- 當探索詞彙的社會語言學特徵
- 當人工判斷是否需要建立延伸卡片
關鍵字：延伸需求、敬語延伸、同義詞對比、語域分析、延伸卡片、語用分析
majiayu000/claude-skill-registry 163
-
eleventy
Build content-focused websites with Eleventy (11ty). Use when creating templates (.njk, .liquid), working with data cascade, collections, or deploying static sites.
majiayu000/claude-skill-registry 163
-
caching-optimizer
Optimize caching strategies for performance. Use when analyzing cache effectiveness, implementing multi-layer caching, optimizing Redis/memory caches, or troubleshooting slow response times.
majiayu000/claude-skill-registry 163
-
python-project-setup
Sets up a new Python project with uv, virtual environment, and best practices for Windows 11. Use this when creating a new Python project or helping users set up their Python development environment with modern tooling.
majiayu000/claude-skill-registry 163
-
Native Code Patterns
This skill provides Kotlin and Swift code patterns for NativePHP plugins. Use when the user asks about "bridge function pattern", "kotlin bridge", "swift bridge", "BridgeFunction class", "BridgeResponse", "execute method", "parameter extraction", "dispatch event", "NativeActionCoordinator", "LaravelBridge", "Activity pattern", "ViewController pattern", threading in native code, or how to write native code for NativePHP plugins.
majiayu000/claude-skill-registry 163
-
pdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
majiayu000/claude-skill-registry 163
-
effect-concurrency-fibers
Concurrency with Effect.all, forEach concurrency, Fiber lifecycle, race and timeouts. Use for parallelizing tasks safely.
majiayu000/claude-skill-registry 163
-
torchtext
Natural Language Processing utilities for PyTorch (Legacy). Includes tokenizers, vocabulary building, and DataPipe-based dataset handling for text processing pipelines. (torchtext, tokenizer, vocab, datapipe, regextokenizer, nlp-pipeline)
majiayu000/claude-skill-registry 163
-
receiving-code-review
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
majiayu000/claude-skill-registry 163