Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
task-clarity-scanner
Scans daily notes using Personal Kanban structure. Clarifies tasks, manages Today's 3 vs Ready, flags stale items, and helps swap between columns. Use when reviewing todos, scanning task lists, or managing your Kanban board.
majiayu000/claude-skill-registry 163
-
openspec-cli
Guidelines for using the OpenSpec CLI tool in non-interactive environments. Use this skill when validating specifications or changes to ensure commands run successfully without user intervention.
majiayu000/claude-skill-registry 163
-
mistral-webhooks-events
Implement event handling patterns for Mistral AI integrations.
Use when building async workflows, implementing queues,
or handling long-running Mistral AI operations.
Trigger with phrases like "mistral events", "mistral async",
"mistral queue", "mistral background jobs", "mistral webhook".
majiayu000/claude-skill-registry 163
-
html-visualization
Create interactive HTML visualizations for any concept - technical documentation, business processes, tutorials, architecture diagrams, or educational content. Supports multiple formats (long-page, slideshow, dashboard, infographic) with Mermaid diagrams, syntax highlighting, and responsive design. Use when user requests visual documentation, presentations, learning materials, or disposable HTML documents. Triggers include "create visualization", "HTML document", "presentation", "onboarding guide", "tutorial page", "explain with diagrams", or "interactive documentation".
majiayu000/claude-skill-registry 163
-
Achievements System
Rewarding players for completing specific goals through progress tracking, unlocking logic, rarity calculation, and achievement display for gamification and player engagement.
majiayu000/claude-skill-registry 163
-
vision-to-execution-pyramid
A framework for translating high-level product vision into actionable goals and execution steps. Use this when defining a new product direction, aligning cross-functional teams, or setting quarterly OKRs to ensure daily tasks ladder up to long-term strategy.
majiayu000/claude-skill-registry 163
-
pubmed-multi-source-search
majiayu000/claude-skill-registry 163
-
knowledge-extractor
Extracts key learnings from conversations, debugging sessions, and failed attempts.
Use at session end or after solving complex problems to capture insights.
Automatically suggests updates to: DISCOVERIES.md (learnings), PATTERNS.md (reusable solutions), new agent creation (repeated workflows).
Ensures knowledge persists across sessions.
majiayu000/claude-skill-registry 163
-
Locale Extractor
Tools to extract hardcoded text from Liquid files and replace them with translation keys.
majiayu000/claude-skill-registry 163
-
throughput-calculator
Throughput Calculator - Auto-activating skill for Performance Testing.
Triggers on: throughput calculator, throughput calculator
Part of the Performance Testing skill category.
majiayu000/claude-skill-registry 163
-
Elasticsearch
Elasticsearch 5.2 operations using HTTP API - searching, indexing, bulk operations, scroll API, and alias management
majiayu000/claude-skill-registry 163
-
automation-language-selection
Choose between Shell and Python for generated automation code based on task traits. Use when automation language selection guidance is required.
majiayu000/claude-skill-registry 163
-
find-current-phase
Find the active phase directory based on status. Use when you need to locate which phase to work on.
majiayu000/claude-skill-registry 163
-
implement-paper-from-scratch
Guides you through implementing a research paper step-by-step from scratch. Use when asked to implement a paper, code up a paper, reproduce research results, or build a model from a paper. Focuses on building understanding through implementation with checkpoint questions.
majiayu000/claude-skill-registry 163
-
x-posting
Compose and publish posts on X (Twitter) with validation
majiayu000/claude-skill-registry 163
-
laravel-mcp
Laravel v12 - The PHP Framework For Web Artisans (project, gitignored)
majiayu000/claude-skill-registry 163
-
comparing-branches
Use when user wants to compare two autonomy branches to see different approaches, metrics, and outcomes
majiayu000/claude-skill-registry 163
-
claude-template-skill
Replace with description of the skill and when Claude should use it.
majiayu000/claude-skill-registry 163
-
acc-detect-test-smells
Detects test antipatterns and code smells in PHP test suites. Identifies 15 smells (Logic in Test, Mock Overuse, Fragile Tests, Mystery Guest, etc.) with fix recommendations and refactoring patterns for testability.
majiayu000/claude-skill-registry 163
-
ai-multimodal
Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.
majiayu000/claude-skill-registry 163
-
passwordless-docs
Bitwarden Passwordless.dev documentation, SDKs, and React examples
majiayu000/claude-skill-registry 163
-
cicd-pipeline-architecture
Use when setting up CI/CD pipelines, experiencing deployment failures, slow feedback loops, or production incidents after deployment - provides deployment strategies, test gates, rollback mechanisms, and environment promotion patterns to prevent downtime and enable safe continuous delivery
majiayu000/claude-skill-registry 163
-
pdf2audio-parallel
Parallel PDF to MP3 conversion using MiniMax. Convert multiple PDF chapters to audio simultaneously using parallel subagents. Use when: (1) User says 'generate mp3 for the story of [STORY_NAME]', (2) User says '为故事[STORY_NAME]生成mp3', (3) User says '为故事[STORY_NAME]第[X]章生成mp3', (4) User says 'generate mp3 for story of [STORY_NAME], chapter [X]', (5) Converting a range of PDFs like 'story-[01-05].pdf' to MP3, (6) Batch audiobook creation from PDF chapters.
majiayu000/claude-skill-registry 163
-
mock-detector
majiayu000/claude-skill-registry 163