Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
pihole-dns-troubleshoot-ipv6
Diagnoses and fixes IPv6 DNS issues causing clients to connect to Cloudflare OAuth
instead of using local network access. Use when services show OAuth login prompt on
local WiFi, slow initial connection followed by authentication, or Chrome shows "error
with retry". Triggers on "connecting to Cloudflare instead of local", "OAuth prompt on
WiFi", "IPv6 DNS issue", "clients prefer IPv6", "disable IPv6 DNS", or "fix local access".
Works with Pi-hole FTLCONF_misc_dnsmasq_lines filter-AAAA configuration and client DNS
cache management.
majiayu000/claude-skill-registry 163
-
create-feature-branch
Create properly named feature branch from development with remote tracking, following WescoBar naming conventions and git best practices
majiayu000/claude-skill-registry 163
-
decomp-fixup
Fix build issues for matched functions in the Melee decompilation project. Use this skill when builds are failing due to header mismatches, signature issues, or caller updates needed after a function has been matched. Invoked with /decomp-fixup [function_name] or automatically when diagnosing build failures.
majiayu000/claude-skill-registry 163
-
create-script
TikTok/릴스용 숏폼 영상 스크립트 생성. 리서치 데이터를 기반으로 60초 이내의 후킹-본문-CTA 구조 스크립트를 작성합니다.
majiayu000/claude-skill-registry 163
-
moai-internal-comms
AI-powered enterprise internal communications orchestrator with Context7 integration, intelligent content generation, automated workflow optimization, multi-format support (reports, newsletters, FAQs), and enterprise-grade communication intelligence
majiayu000/claude-skill-registry 163
-
async-boundary-optimization
Optimize async boundaries to balance responsiveness, streaming, and error containment.
majiayu000/claude-skill-registry 163
-
google-adk
Guide for building AI agents with Google ADK (Agent Development Kit). Use when creating multi-agent pipelines, implementing conditional agent branching, designing agent tools with FunctionTool, or debugging agent data flow issues. Covers SequentialAgent, LoopAgent, ParallelAgent patterns, session.state management, output_key chaining, and transfer_to_agent for control flow. Essential for understanding non-obvious ADK behaviors like why SequentialAgent runs ALL agents even after rejection.
majiayu000/claude-skill-registry 163
-
engine-superpower-profiling
Profile AI engine superpowers and capability boundaries.
majiayu000/claude-skill-registry 163
-
chartjs-tooltips
This skill should be used when the user asks "Chart.js tooltips", "Chart.js tooltip callbacks", "custom Chart.js tooltip", "HTML tooltip Chart.js", "Chart.js tooltip formatting", "Chart.js tooltip position", "Chart.js tooltip label", "external tooltip", "Chart.js tooltip styling", or needs help configuring tooltips in Chart.js v4.5.1.
majiayu000/claude-skill-registry 163
-
midjourney-replicate-flux
Generate highly detailed, Midjourney-style image prompts optimized for the FLUX 1.1 Pro model on Replicate. Transform basic user descriptions into rich, cinematic prompts with professional photography qualities, dramatic lighting, and editorial-quality aesthetics. Use when users request image generation, need prompt enhancement, or want Midjourney-quality outputs via FLUX 1.1 Pro.
majiayu000/claude-skill-registry 163
-
julien-calibre
Complete Calibre library management - add/remove books, convert PDF to EPUB, metadata editing, library analysis, cleanup, and e-reader sync (Sony PRS-T1). Use for any ebook or Calibre operation.
majiayu000/claude-skill-registry 163
-
store-lifecycle
Best practices for creating, indexing, and managing Bluera Knowledge stores. Covers when to use clone vs crawl vs folder, naming conventions, indexing strategies, storage management, background job monitoring, and handling indexing failures.
majiayu000/claude-skill-registry 163
-
overnight-dev-autonomous-sessions
Comprehensive autonomous development skill for running 6-8 hour overnight coding sessions with enforced test-driven development through Git hooks.
Activates when: setting up overnight development, configuring TDD workflows, running autonomous sessions, debugging test failures iteratively, enforcing code quality through hooks.
Transforms "should work" into "does work" by continuously iterating until all tests pass.
majiayu000/claude-skill-registry 163
-
dataset-engineering
Create, clean, and optimize datasets for LLM fine-tuning. Covers formats (Alpaca, ShareGPT, ChatML), synthetic data generation, quality assessment, and augmentation. Use when preparing data for training.
majiayu000/claude-skill-registry 163
-
backlog-grooming-assistant
Execute backlog grooming assistant operations. Auto-activating skill for Enterprise Workflows.
Triggers on: backlog grooming assistant, backlog grooming assistant
Part of the Enterprise Workflows skill category. Use when working with backlog grooming assistant functionality. Trigger with phrases like "backlog grooming assistant", "backlog assistant", "backlog".
majiayu000/claude-skill-registry 163
-
status-line-manager
Installs and configures custom status line functionality in Claude Code projects with proper plugin root variable usage
majiayu000/claude-skill-registry 163
-
postgresql-integration
Guide developers through PostgreSQL setup, connection configuration, query patterns, and best practices
majiayu000/claude-skill-registry 163
-
threat-model
majiayu000/claude-skill-registry 163
-
cli-building
Build command-line interfaces with async-first design, composable commands, and proper output formatting. Use when creating CLI tools, commands, or interactive terminal applications.
majiayu000/claude-skill-registry 163
-
running-performance-benchmarks
Use this skill when running performance benchmarks, measuring API endpoint response times, detecting performance regressions, running load tests, comparing performance before/after changes, analyzing performance trends, or validating optimization improvements. Handles baseline comparisons, historical tracking, and report generation.
majiayu000/claude-skill-registry 163
-
dialogue-assess-framing
Assess problem framing quality before proceeding with implementation. Captures whether the problem is well-defined per Naur's theory-building principles. Triggers on "assess framing", "check problem framing", "framing assessment", "is the problem well-defined".
majiayu000/claude-skill-registry 163
-
Investigation & Analysis
Analyze feature requests, refactor plans, or technical decisions to determine investment value and provide recommendations. Use when user mentions investigating, analyzing, or asks "should we build this".
majiayu000/claude-skill-registry 163
-
branch-comparison
Use when the user asks to compare branches, analyze git diffs, review changes between branches, update specifications based on code changes, or analyze what changed. Triggers on keywords like "compare branches", "git diff", "what changed", "branch comparison", "code changes", "spec update".
majiayu000/claude-skill-registry 163
-
docx-processor
Process and generate Word documents with formatting, tables, and images. Use when working with Word documents or generating reports.
majiayu000/claude-skill-registry 163