Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
create-blog
Orchestrate blog post creation with research, writing, compliance, and SEO
majiayu000/claude-skill-registry 163
-
aget-file-issue
File issues with L520 governance compliance
majiayu000/claude-skill-registry 163
-
kb-fediverse-federation-md
Background knowledge about FEP-67ff FEDERATION.md, the convention for documenting federation behavior in Fediverse projects. Covers the specification requirements (valid Markdown, repository root location), suggested template sections (protocols, FEPs, ActivityPub details), machine-readable discovery via NodeInfo 2.1 software.repository, the companion FEP-c893 (DOAP JSON-LD for automated capability discovery), the origin story (Darius Kazemi's 2020 proposal, WriteFreely as first adopter), the interoperability documentation gap FEDERATION.md solves, real-world examples from Mastodon and WordPress, and the 40+ implementations that have adopted it. Load when the user asks about FEDERATION.md; how to document federation behavior; FEP-67ff; what protocols or FEPs a project supports; how to create interoperability documentation for a Fediverse project; how other projects document their ActivityPub implementation; or machine-readable federation capability discovery with DOAP.
majiayu000/claude-skill-registry 163
-
get-available-resources
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
majiayu000/claude-skill-registry 163
-
re
Explicit extra-research mode. Use only when the user says `/re` or clearly asks for a research-heavy pass before coding. This skill should bias Codex toward more source-checking and justification without replacing its normal orchestration.
majiayu000/claude-skill-registry 163
-
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
majiayu000/claude-skill-registry 163
-
sql-optimization-patterns
Transform slow database queries into lightning-fast operations through systematic optimization, proper indexing, and query plan analysis.
majiayu000/claude-skill-registry 163
-
ln-813-optimization-plan-validator
Validates optimization plan via multi-agent review before execution. Use when verifying feasibility of optimization hypotheses.
majiayu000/claude-skill-registry 163
-
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
majiayu000/claude-skill-registry 163
-
n8n-syntax-extension-methods
Use when transforming data in expressions, formatting dates, manipulating arrays/objects, or working with binary file metadata. Prevents using unavailable methods and incorrect method signatures. Covers 17 string methods (.extractEmail, .hash, .toDateTime, .urlEncode), 21 array methods (.pluck, .removeDuplicates, .chunk, .smartJoin), 13 number methods, 12 object methods (.compact, .keepFieldsContaining), 3 boolean methods, 25+ DateTime/Luxon methods (.plus, .minus, .format, .diffTo), and 7 BinaryFile properties. Keywords: n8n, extension methods, string, array, DateTime, Luxon, pluck, extractEmail, removeDuplicates, binary file.
majiayu000/claude-skill-registry 163
-
implementing-realtime-sync
Real-time communication patterns for live updates, collaboration, and presence. Use when building chat applications, collaborative tools, live dashboards, or streaming interfaces (LLM responses, metrics). Covers SSE (server-sent events for one-way streams), WebSocket (bidirectional communication), WebRTC (peer-to-peer video/audio), CRDTs (Yjs, Automerge for conflict-free collaboration), presence patterns, offline sync, and scaling strategies. Supports Python, Rust, Go, and TypeScript.
majiayu000/claude-skill-registry 163
-
code-quality
Provides code quality principles including SOLID, DRY, testing strategies, and best practices for implementation review. Use when reviewing code or applying quality standards.
majiayu000/claude-skill-registry 163
-
hook-and-headline-writing
majiayu000/claude-skill-registry 163
-
orchardcore-menus
Skill for creating and managing menus in Orchard Core. Covers menu content types, menu item types, menu widgets, navigation rendering, pager shapes, breadcrumbs, and menu customization via shapes and alternates.
majiayu000/claude-skill-registry 163
-
springboot-verification
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
majiayu000/claude-skill-registry 163
-
Skill Development
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
majiayu000/claude-skill-registry 163
-
context-optimize-sirejeff-k0ntext
Context Optimization - Orchestrate RPI workflow TODO generation with interactive scoping
majiayu000/claude-skill-registry 163
-
scientific-brainstorming
Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.
majiayu000/claude-skill-registry 163
-
mastering-github-cli
GitHub CLI (gh) command reference for repository search, code discovery, CI/CD monitoring, workflow authoring, and automation. Triggers on "gh" commands, "github cli", searching repos for files/directories (.skilz, .cursor, .codex, Dockerfile), monitoring GitHub Actions workflows, checking PR CI status, downloading artifacts, creating PRs/issues/repos from command line, triggering workflows, forking repos, batch operations, "write a workflow", "github actions", "CI/CD pipeline", "workflow yaml", and "matrix builds". Use for gh search, gh run, gh pr, gh issue, gh repo, gh workflow, gh api, workflow authoring, and automating GitHub operations.
majiayu000/claude-skill-registry 163
-
feature
Generates lightweight, implementation-ready feature specifications. A feature spec is the bridge between spec-forge's formal documentation chain (PRD/SRS/Tech Design/Test Plan) and code-forge's implementation planning. It distills what a module or component must do into a concise, language-agnostic document that code-forge:plan can consume directly. Supports two modes: standalone creation through a brief Q&A interview, or automatic extraction from an existing tech-design document. Output lives in docs/features/ and is shared across all language-specific implementations.
majiayu000/claude-skill-registry 163
-
orchestrate
Run the full product→plan→validate→implement→verify workflow by delegating to subagents.
majiayu000/claude-skill-registry 163
-
plan-risk
Identify risks before building. Flag third-party dependencies, API limits, and cost traps.
majiayu000/claude-skill-registry 163
-
github-automation
Automate GitHub repositories, issues, pull requests, branches, CI/CD, and permissions via Rube MCP (Composio). Manage code workflows, review PRs, search code, and handle deployments programmatically.
majiayu000/claude-skill-registry 163
-
advanced-skill-builder
Guides users through creating production-ready Claude skills via interactive dialogue. Use when user wants to build a new skill, needs help structuring a skill, or asks "how do I create a skill?" Covers requirements gathering, planning, YAML frontmatter generation, instruction writing, testing, and iterative refinement. Works with or without MCP integration.
majiayu000/claude-skill-registry 163