Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
plugin-test
Run comprehensive tests on plugin components using the modular test runner. Validates hooks, agents, skills, and plugin structure across all PopKit plugin packages.
majiayu000/claude-skill-registry 163
-
log-analyzer
解析和分析日志文件，支持模式匹配、过滤、统计和错误检测。
majiayu000/claude-skill-registry 163
-
convert-pdf-to-epub
Convert PDF books to EPUB format for e-readers. Use when user asks to convert PDF to EPUB, create an e-book from PDF, make PDF readable on Kindle/phone/tablet, or extract book content from PDF. Handles: chapter detection, image extraction with optimization, footnotes/endnotes with hyperlinks, reading order for multi-column layouts. Validates conversion quality automatically.
majiayu000/claude-skill-registry 163
-
gifgrep
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.
majiayu000/claude-skill-registry 163
-
backend-nodejs
Modern Node.js backend stack: NestJS/Hono, Drizzle ORM, Vitest, TypeScript.
Use when: building Node.js APIs, TypeScript backends, or serverless functions.
Triggers: "nestjs", "node backend", "express", "hono", "drizzle", "vitest",
"typescript api", "node api", "bun".
majiayu000/claude-skill-registry 163
-
drafts-actions
Create and script actions for the Drafts app. Use this skill when the user needs help creating custom Drafts actions, understanding action steps, using template tags, scripting with JavaScript, or configuring action workflows for automation and productivity.
majiayu000/claude-skill-registry 163
-
subagent-teams
Orchestrate complex tasks by delegating work to parallel subagent teams, preserving the main context window and preventing auto-compact.
This skill should be used when users ask to apply subagent-teams, when performing complex multi-step tasks, when context window is getting large, or when independent subtasks can run in parallel.
majiayu000/claude-skill-registry 163
-
patterns/opaque-pointer
Opaque Pointer Pattern pattern for C development
majiayu000/claude-skill-registry 163
-
business-writing
Use when writing B2B sales emails, professional communication, or business correspondence. Applies Sid's direct voice (simple, brief, human) with Grand Slam Offer strategy (never salesy).
majiayu000/claude-skill-registry 163
-
vercel-known-pitfalls
Execute identify and avoid Vercel anti-patterns and common integration mistakes.
Use when reviewing Vercel code for issues, onboarding new developers,
or auditing existing Vercel integrations for best practices violations.
Trigger with phrases like "vercel mistakes", "vercel anti-patterns",
"vercel pitfalls", "vercel what not to do", "vercel code review".
majiayu000/claude-skill-registry 163
-
convert-python-rust
Convert Python code to idiomatic Rust. Use when migrating Python projects to Rust, translating Python patterns to idiomatic Rust, or refactoring Python codebases for performance, safety, and concurrency. Extends meta-convert-dev with Python-to-Rust specific patterns.
majiayu000/claude-skill-registry 163
-
email-anti-slop
Prevent generic AI-generated email aesthetics and enforce distinctive, handcrafted design quality. Use when generating HTML emails, email templates, newsletters, marketing emails, or any email content. Ensures emails look professionally designed, not machine-generated. Applies anti-pattern detection and distinctive design requirements.
majiayu000/claude-skill-registry 163
-
error-states
Error handling patterns for Astro sites. 404/500 pages, form errors, offline states, loading failures. Use for graceful degradation and user experience.
majiayu000/claude-skill-registry 163
-
pyramid-principle
Hierarchical content structure - answer first, then supporting arguments, then details
majiayu000/claude-skill-registry 163
-
handler-work-tracker-github
[DEPRECATED] GitHub Issues handler - Use Fractary CLI instead
majiayu000/claude-skill-registry 163
-
requirements-analyst
Copilot agent that assists with requirements analysis, user story creation, specification definition, and acceptance criteria definition
Trigger terms: requirements, EARS format, user stories, functional requirements, non-functional requirements, SRS, requirement analysis, specification, acceptance criteria, requirement validation
Use when: User requests involve requirements analyst tasks.
majiayu000/claude-skill-registry 163
-
episode-start
Start a new learning episode in the self-learning memory system with proper context. Use this skill when beginning a new task that should be tracked for learning from execution patterns.
majiayu000/claude-skill-registry 163
-
knowledge-synthesizer
Expert knowledge synthesizer specializing in extracting insights from multi-agent interactions, identifying patterns, and building collective intelligence. Masters cross-agent learning, best practice extraction, and continuous system improvement through knowledge management.
majiayu000/claude-skill-registry 163
-
nginx-default-conf
Generates nginx.default.conf in project root for nginx conf.d directory configuration. Serves static files from /usr/share/nginx/html.
majiayu000/claude-skill-registry 163
-
document-creation
Create structured documents from conversations, summaries, or content in open formats (markdown, PDF, text). Use when the user requests document creation, report generation, content export, conversation summaries, or structured documentation. Triggers include "create a document", "make a report", "summarize this conversation", "export to PDF/markdown", or any request to formalize content into a document. Works independently or integrates with design-assistant skill for polished visual output.
majiayu000/claude-skill-registry 163
-
nuxt-errors
Error handling with error classes, handlers, and interceptors. Use when handling API errors, displaying validation errors, configuring error handlers, or implementing error interceptors.
majiayu000/claude-skill-registry 163
-
comp-mechanics
Use to assemble rate tables, accelerator logic, and plan governance templates.
majiayu000/claude-skill-registry 163
-
dag-performance-profiler
Profiles DAG execution performance including latency, token usage, cost, and resource consumption. Identifies bottlenecks and optimization opportunities. Activate on 'performance profile', 'execution metrics', 'latency analysis', 'token usage', 'cost analysis'. NOT for execution tracing (use dag-execution-tracer) or failure analysis (use dag-failure-analyzer).
majiayu000/claude-skill-registry 163
-
cloud-metrics
Query Google Cloud Monitoring metrics using the cloud_metrics.py tool. Use when users ask about GCP metrics, Cloud Monitoring, Kubernetes metrics (CPU, memory, network), container resource usage, or need to export monitoring data. Triggers on requests like "show me CPU usage", "list available metrics", "describe this metric", "top memory consumers", or any Google Cloud Monitoring queries.
majiayu000/claude-skill-registry 163