Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
specsafe-agentforge
Repository-specific SpecSafe workflow for AgentForge. Use when creating, refining, testing, implementing, or reviewing AgentForge specs so work follows the documented SpecSafe stages, prompt files, and source-of-truth rules consistently.
majiayu000/claude-skill-registry 163
-
d3js-data-visualization
Create interactive, custom data visualizations using d3.js — including charts, graphs, network diagrams, and geographic maps. Use when you need fine-grained control over visual elements, transitions, or interactions beyond what standard charting libraries offer, in any JavaScript environment (vanilla JS, React, Vue, Svelte, etc.).
majiayu000/claude-skill-registry 163
-
xbrl-parser-expert
日本の証券データ（EDINET）のXBRL/iXBRL解析に関する専門スキル。「予測」を排除し、事実（名前空間・スキーマ参照）に基づく厳格なパースを実現します。
majiayu000/claude-skill-registry 163
-
ultrawork
Parallel execution engine for high-throughput task completion
majiayu000/claude-skill-registry 163
-
blogwatcher
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
majiayu000/claude-skill-registry 163
-
mlops-engineer
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.
majiayu000/claude-skill-registry 163
-
media-transcript-search
Extract and search transcripts from multimedia sources (primarily YouTube). Allows finding specific topics within long content without watching the whole video.
majiayu000/claude-skill-registry 163
-
pm-document
Extract structured decisions from source material — sprint outputs, team reports, issue investigations, security audits. Comprehensive extraction is the default. Every architectural decision, tech fact, enforcement lesson, and sprint outcome that serves PM coordination gets documented. Triggers on "/pm-document", "/pm-document [file]", "extract decisions", "document this sprint", "process this report".
majiayu000/claude-skill-registry 163
-
plugin-manifest-schema
Define plugin manifest schema with versioning and dependency declarations.
majiayu000/claude-skill-registry 163
-
clojure-repl
Use this skill whenever you need to evaluate Clojure expressions in a REPL — for iterative development, debugging, API exploration, or validating code before saving to files. Covers nREPL connection, incremental prototyping workflow, and REPL-based testing. Prefer this skill over writing untested Clojure code directly to files. Also invoke when the user asks to "try something in the REPL," "test this function," or "debug this interactively."
majiayu000/claude-skill-registry 163
-
competitor-alternatives
When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' or 'competitive landing pages.' Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. Emphasizes deep research, modular content architecture, and varied section types beyond feature tables.
majiayu000/claude-skill-registry 163
-
address-github-comments
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
majiayu000/claude-skill-registry 163
-
pm-remember
Retrieve specific knowledge from the PM vault — find decisions about a technology, look up the state of an issue, recall what was decided in a sprint, search for enforcement lessons. The semantic recall interface. Triggers on "/pm-remember", "what do we know about", "look up", "recall", "find decisions about", "what's the status of".
majiayu000/claude-skill-registry 163
-
product-launch-strategy
Plan and execute e-commerce product launches. Pre-launch, launch day, and post-launch playbooks for Amazon, Shopify, and multi-channel sellers. Covers inventory, pricing, advertising, and review strategy.
majiayu000/claude-skill-registry 163
-
mastering-langgraph
Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step workflows with conditional branches, (3) adding persistence/memory across turns with checkpointers, (4) implementing human approval with interrupt(), (5) debugging via time-travel or LangSmith. Covers StateGraph, nodes, edges, add_conditional_edges, MessagesState, thread_id, Command objects, and ToolMessage handling. Examples include chatbots, calculator agents, and structured workflows.
majiayu000/claude-skill-registry 163
-
moai-domain-mobile-app
Enterprise mobile development with React Native 0.76+, Flutter 3.24+, Capacitor 6.x, cross-platform patterns, testing, CI/CD
majiayu000/claude-skill-registry 163
-
paper-plan
Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.
majiayu000/claude-skill-registry 163
-
ln-910-community-engagement
Analyzes community health and delegates engagement tasks. Use when managing GitHub issues, discussions, and announcements.
majiayu000/claude-skill-registry 163
-
code-simplifier
Agent that simplifies and refines code for clarity, consistency, and maintainability while preserving functionality
majiayu000/claude-skill-registry 163
-
evo-architect
architect agent
majiayu000/claude-skill-registry 163
-
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
majiayu000/claude-skill-registry 163
-
attack-tree-construction
Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
majiayu000/claude-skill-registry 163
-
google-chat-api
Build Google Chat bots and webhooks with Cards v2, interactive forms, and Cloudflare Workers. Covers Spaces/Members/Reactions APIs, bearer token verification, and dialog patterns.
Use when: creating Chat bots, workflow automation, interactive forms. Troubleshoot: bearer token 401, rate limit 429, card schema validation, webhook failures.
majiayu000/claude-skill-registry 163
-
pdf
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
majiayu000/claude-skill-registry 163