Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
download-transcripts
Download YouTube transcripts for videos tracked in a CSV file. Use when you need to download transcripts in bulk with progress tracking, fetching transcripts overnight, processing video libraries, or when the user mentions "get transcripts", "download captions", or "bulk transcript download".
majiayu000/claude-skill-registry 163
-
decision-archaeology
Investigate why code was written a certain way. Use when tracing decision history through git blame, commit logs, PRs, and issues to understand the reasoning behind code changes.
majiayu000/claude-skill-registry 163
-
gemma_pqn_emergence_detector
Gemma PQN Emergence Detector
majiayu000/claude-skill-registry 163
-
langfuse
Debug AI traces, find exceptions, analyze sessions, and manage prompts via Langfuse MCP. Also handles MCP setup and configuration.
majiayu000/claude-skill-registry 163
-
mouse-movement
Human-like mouse movement patterns. Use when automating browser interactions to avoid bot detection.
majiayu000/claude-skill-registry 163
-
optimizing-code
Improve code performance without changing behavior. Use when code fails latency/throughput requirements. Covers profiling, caching, and algorithmic optimization.
majiayu000/claude-skill-registry 163
-
docs-inda-hr-python-sdk
majiayu000/claude-skill-registry 163
-
github-swarm-pr
Pull request swarm management for multi-agent code review and validation. Use for coordinated PR reviews, automated validation, PR-based swarm creation, and intelligent merge workflows.
majiayu000/claude-skill-registry 163
-
atlas-agent-peer-reviewer
Adversarial quality gate agent for code review - finds flaws before users do
majiayu000/claude-skill-registry 163
-
unknown-lzxaini-wukong-contrib
majiayu000/claude-skill-registry 163
-
agent-config-validator
Validate AgentConfig definitions for the Agent Framework. Use when creating or modifying agent configurations to ensure correct structure, valid tool references, and proper sub-agent composition. Validates TypeScript interfaces and Python Pydantic models.
majiayu000/claude-skill-registry 163
-
Implement Double Number Line Question
Create D3 questions with double number lines showing proportional relationships. Students complete missing values on parallel number lines.
majiayu000/claude-skill-registry 163
-
terraphim-hooks
Knowledge graph-based text replacement using Terraphim hooks.
Intercepts commands and text to apply transformations defined in the knowledge graph.
Works with Claude Code PreToolUse hooks and Git prepare-commit-msg hooks.
majiayu000/claude-skill-registry 163
-
after
majiayu000/claude-skill-registry 163
-
docker-ops
Obsidian LiveSync の Docker Compose 環境を操作・トラブルシューティングします。compose.yaml の構成理解、環境変数（.env）の設定、CouchDB と livesync-proxy のヘルスチェック、バックアップサービスの実行、ログ確認とデバッグを行います。Docker 環境の起動・停止、コンテナの状態確認、トラブルシューティングを依頼されたときに使用してください。
majiayu000/claude-skill-registry 163
-
sdk-apps-openai
majiayu000/claude-skill-registry 163
-
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
majiayu000/claude-skill-registry 163
-
skill-catholic-liturgy-tool
Catholic liturgical CLI tool
majiayu000/claude-skill-registry 163
-
spec-writing
Use during Phase 3 of spec creation to create specification document - searches codebase for reusable patterns, presents spec in validated 150-200 word sections, and saves complete specification following template structure
majiayu000/claude-skill-registry 163
-
cdp-lite-adapter
Adapt the User Explorer (CDP-lite) prototype to new data sources by mapping input exports to the build pipeline, updating adapters/enrichments, and preserving output JSON schemas for the UI. Use when asked to connect real data, replace inputs, or modify the build outputs/UI contracts.
majiayu000/claude-skill-registry 163
-
log-debug-issue
Log problems, bugs, and debugging processes with solutions. Use when encountering issues during development, debugging problems, or documenting solutions for future reference. Maintains DEBUG_LOG.md with structured problem-solution entries.
majiayu000/claude-skill-registry 163
-
leta
Fast semantic code navigation via LSP. Load FIRST before ANY code task - even 'simple' ones. Trigger scenarios: (1) fixing lint/type/pyright/mypy warnings or errors, (2) fixing reportAny/reportUnknownType/Any type errors, (3) adding type annotations, (4) refactoring or modifying code, (5) finding where a function/class/symbol is defined, (6) finding where a symbol is used/referenced/imported, (7) understanding what a function calls or what calls it, (8) exploring unfamiliar code or understanding architecture, (9) renaming symbols across codebase, (10) finding interface/protocol implementations, (11) ANY task where you'd use ripgrep to find code or read-file to view a function. Use `leta show SYMBOL` instead of read-file, `leta refs SYMBOL` instead of ripgrep for usages, `leta grep PATTERN` instead of ripgrep for definitions, `leta files` instead of list-directory.
majiayu000/claude-skill-registry 163
-
fiftyone-dataset-inference
Create a FiftyOne dataset from a directory of media files (images, videos, point clouds), optionally import labels in common formats (COCO, YOLO, VOC), run model inference, and store predictions. Use when users want to load local files into FiftyOne, apply ML models for detection, classification, or segmentation, or build end-to-end inference pipelines.
majiayu000/claude-skill-registry 163
-
create-from-template
Create a new app or package from an existing template in the monorepo. Use when adding new apps or packages to the repository.
majiayu000/claude-skill-registry 163