Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
simple-gemini
Collaborative documentation and test code writing workflow using zen mcp's clink to launch gemini CLI session in WSL (via 'gemini' command) where all writing operations are executed. Use this skill when the user requests "use gemini to write test files", "use gemini to write documentation", "generate related test files", "generate an explanatory document", or similar document/test writing tasks. The gemini CLI session acts as the specialist writer, working with the main Claude model for context gathering, outline approval, and final review. For test code, codex CLI (also launched via clink) validates quality after gemini completes writing.
majiayu000/claude-skill-registry 163
-
excel
Read, write, edit, and format Excel files (.xlsx). Create spreadsheets, manipulate data, apply formatting, manage sheets, merge cells, find/replace, and export to CSV/JSON/Markdown. Use for any Excel file manipulation task.
majiayu000/claude-skill-registry 163
-
Plugin Settings
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
majiayu000/claude-skill-registry 163
-
sentry-performance-tuning
Optimize Sentry performance monitoring configuration.
Use when tuning sample rates, reducing overhead,
or improving performance data quality.
Trigger with phrases like "sentry performance optimize", "tune sentry tracing",
"sentry overhead", "improve sentry performance".
majiayu000/claude-skill-registry 163
-
virtualization-and-large-data
Implement high-performance virtualization strategies for massive datasets without sacrificing UX.
majiayu000/claude-skill-registry 163
-
streaming-llm-responses
Implement real-time streaming UI patterns for AI chat applications. Use when adding response
lifecycle handlers, progress indicators, client effects, or thread state synchronization.
Covers onResponseStart/End, onEffect, ProgressUpdateEvent, and client tools.
NOT when building basic chat without real-time feedback.
majiayu000/claude-skill-registry 163
-
discovery
Quick user-centric interview to capture requirements from a time-poor stakeholder.
majiayu000/claude-skill-registry 163
-
worker-worktree-examples
Git worktree practical examples for parallel agent development
majiayu000/claude-skill-registry 163
-
coercion-duress
Clerk for forced surrenders, threats, procedural irregularities, and lack of informed consent; use for Coercion_Duress queue.
majiayu000/claude-skill-registry 163
-
nextjs-modal-integration
majiayu000/claude-skill-registry 163
-
property-based-test-helper
Property Based Test Helper - Auto-activating skill for Test Automation.
Triggers on: property based test helper, property based test helper
Part of the Test Automation skill category.
majiayu000/claude-skill-registry 163
-
hr-pro
Professional, ethical HR partner for hiring, onboarding/offboarding, PTO and leave, performance, compliant policies, and employee relations. Ask for jurisdiction and company context before advising; produce structured, bias-mitigated, lawful templates.
majiayu000/claude-skill-registry 163
-
image_concatenator
A utility skill to vertically concatenate multiple images into a single file.
majiayu000/claude-skill-registry 163
-
discord-list
List Discord servers and channels. Use when user asks about available servers, channels, or wants to discover what's accessible.
majiayu000/claude-skill-registry 163
-
send-message
Send messages via Sinch Conversation API over WhatsApp, SMS, RCS, Messenger, Viber, Instagram, Telegram, and other channels. Use when the user wants to send a message, text someone, send a WhatsApp message, send an SMS, or communicate via any messaging channel. Automatically handles contact creation and conversation management.
majiayu000/claude-skill-registry 163
-
banach-spaces
Problem-solving strategies for banach spaces in functional analysis
majiayu000/claude-skill-registry 163
-
run-evaluation
Evaluate the latest Universal Agent run for errors, bottlenecks, and opportunities for improvement. This skill should be used after an agent run completes to perform a critical assessment by analyzing the run.log file, session directory output, and Logfire traces. Use when the user wants to debug issues, understand performance problems, identify exceptions, check if the agent stayed on a happy path, or get recommendations for improving agent behavior.
majiayu000/claude-skill-registry 163
-
plan-validate
Validate plan document structure and frontmatter. Use when checking plans for compliance, ensuring proper formatting, or verifying metadata before commits.
majiayu000/claude-skill-registry 163
-
cyber_security_expert
网络安全与渗透测试专家，专注于漏洞分析、安全防护及代码审计。
majiayu000/claude-skill-registry 163
-
generating-stored-procedures
Execute use when you need to work with stored procedure generation.
This skill provides stored procedure code generation with comprehensive guidance and automation.
Trigger with phrases like "generate stored procedures", "create database functions",
or "write SQL procedures".
majiayu000/claude-skill-registry 163
-
medchem
Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.
majiayu000/claude-skill-registry 163
-
prd-v07-epic-scoping
Transform v0.6 specifications into context-window-sized work packages (EPICs) during PRD v0.7 Build Execution. Triggers on requests to create epics, scope work, break down implementation, or when user asks "create epics", "scope work", "break down work", "context window sizing", "what to build first?", "implementation planning", "epic breakdown". Consumes API-, DBT-, FEA-, ARC-. Outputs EPIC- entries with objectives, ID references, dependencies, and context windows. Feeds v0.7 Test Planning.
majiayu000/claude-skill-registry 163
-
windows-safe-grep
Use when grep/ripgrep fails on Windows due to paths with backslash-space sequences creating malformed paths like 'nul' from \n+ul
majiayu000/claude-skill-registry 163
-
feedback-pedagogy
Give effective feedback that promotes learning and growth. Covers written feedback on student work, rubric design, peer review facilitation, and constructive critique techniques. Triggers on grading, feedback, rubrics, peer review, or critique requests.
majiayu000/claude-skill-registry 163