Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
viral-pattern-engine
Iteration 20 of Multiplicity Cascade - Generates self-propagating patterns
majiayu000/claude-skill-registry 163
-
research-with-citations
Conduct thorough research with proper citations and source verification for academic and professional content
majiayu000/claude-skill-registry 163
-
codebase-fix-and-pr
Apply code changes to a GitHub repository and automatically create a pull request. Takes user feedback or fix requirements, clones the repo, makes localized changes, commits to a new branch, and opens a PR via GitHub MCP.
majiayu000/claude-skill-registry 163
-
atxp
Access ATXP paid API tools for web search, AI image generation, music creation, video generation, and X/Twitter search. Use when users need real-time web search, AI-generated media (images, music, video), or X/Twitter search. Requires authentication via `npx atxp login`.
majiayu000/claude-skill-registry 163
-
repository-structure
Monorepo structure, subpackage organization, and dependency rules. Use when creating new packages, understanding project layout, or organizing code.
majiayu000/claude-skill-registry 163
-
writing-plans
Creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps for engineers with zero codebase context. Assumes skilled developers who need domain-specific guidance, following DRY, YAGNI, and TDD principles. Use after brainstorming/design is complete when handing off to another developer or planning complex multi-step work. Do NOT use for simple tasks, quick fixes, or when you're implementing yourself and already understand the codebase - just start coding instead.
majiayu000/claude-skill-registry 163
-
skills-repo-maintenance
Add or update skills in a skills repository for Codex and/or Claude Code. Use when creating new skills, packaging .skill files for Codex, or converting a skill into a Claude Code plugin (marketplace.json + plugin.json).
majiayu000/claude-skill-registry 163
-
security-incident-playbook-generator
Creates response procedures for security incidents with containment steps, communication templates, and evidence collection. Use for "incident response", "security playbook", "breach response", or "IR plan".
majiayu000/claude-skill-registry 163
-
osgrep
Semantic search for local files. Backed by a background osgrep server with live indexing. Always use osgrep instead of grep/find.
majiayu000/claude-skill-registry 163
-
nosql-expert
Expert guidance for distributed NoSQL databases (Cassandra, DynamoDB). Focuses on mental models, query-first modeling, single-table design, and avoiding hot partitions in high-scale systems.
majiayu000/claude-skill-registry 163
-
define-customer-profile
Iteratively craft a CUSTOMER.md document that precisely defines your ideal customer profile (ICP). This is the foundational document from which everything else (product, features, brand) derives. Uses parallel research agents and multi-choice workflow with feedback cycles.
majiayu000/claude-skill-registry 163
-
fusion-test
Compare testing strategies and choose the best coverage plan; use when deciding how to test a feature or fix.
majiayu000/claude-skill-registry 163
-
active-record-db
majiayu000/claude-skill-registry 163
-
umap-learn
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
majiayu000/claude-skill-registry 163
-
senior-prompt-engineer
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
majiayu000/claude-skill-registry 163
-
obsidian-read-context
Analyze Obsidian vault documentation to understand current knowledge state. Use when exploring documentation structure, identifying gaps, or planning documentation consolidation.
majiayu000/claude-skill-registry 163
-
browserslistrc
Defines target browser versions for CSS autoprefixing and JavaScript transpilation. Generates .browserslistrc configuration file.
majiayu000/claude-skill-registry 163
-
systemd
Systemd 服务管理
majiayu000/claude-skill-registry 163
-
automating-reminders
Automates Apple Reminders using JavaScript for Automation (JXA). Use when asked to "create reminders programmatically", "automate reminder lists", "JXA Reminders scripting", or "manage reminders via automation". Covers list/reminder management, filtering with 'whose' queries, efficient creation via constructors and push operations, and copy-delete patterns for moving items.
majiayu000/claude-skill-registry 163
-
output-style-builder
Creates structured output formats (JSON, YAML, Markdown-KV, XML) and response style configurations for Claude. Use when: (1) defining agent output schemas (.json, .yaml, .xml), (2) configuring response style scope hierarchy, (3) embedding formats in agents/commands, (4) building CLAUDE.md output sections, (5) creating format definitions in .claude/styles/, or (6) standardizing structured data serialization.
majiayu000/claude-skill-registry 163
-
extracting-hecras-results
Extract HEC-RAS hydraulic results from HDF files including water surface elevations (WSE),
depths, velocities, and flows for both steady and unsteady simulations. Handles cross section
time series, 2D mesh results, maximum envelopes, and dam breach results. Use when you need to
extract, analyze, or post-process HEC-RAS simulation outputs, retrieve water levels, query
velocity fields, get depth grids, extract flow data, analyze breach hydrographs, or pull
hydraulic variables from .hdf result files.
majiayu000/claude-skill-registry 163
-
sentry-load-scale
Manage scale Sentry for high-traffic applications.
Use when optimizing for high event volumes,
managing costs at scale, or tuning for performance.
Trigger with phrases like "sentry high traffic", "scale sentry",
"sentry high volume", "sentry millions events".
majiayu000/claude-skill-registry 163
-
opentofu
Open-source Terraform alternative for infrastructure provisioning with installation and workflow commands.
majiayu000/claude-skill-registry 163
-
search-driving-distance
Estimate driving/taxi duration, distance, and rough cost between two cities using the bundled distance matrix CSV. Use this skill when comparing ground travel options or validating itinerary legs.
majiayu000/claude-skill-registry 163