Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
claude-code-coagent
Use claude_code MCP as a third-party co-agent to gather alternative opinions, unblock stalemates, or delegate scoped tasks (reviews, ideas, draft edits) while you remain the decision-maker. Trigger when seeking another perspective or backup executor: "他の意見", "別の人", "違う観点", "打開策ない?", "別LLMの見解", "claudeに頼んで".
majiayu000/claude-skill-registry 163
-
neovim-debugging
Debug Neovim/LazyVim configuration issues. Use when: user reports Neovim errors, keymaps not working, plugins failing, or config problems. Provides systematic diagnosis through hypothesis testing, not just checklists. Think like a detective narrowing down possibilities.
majiayu000/claude-skill-registry 163
-
proof-composer
Validates entire engineering proof chain. Verifies architecture, backend maps, backend code, standardization, frontend types, infrastructure topology all compose correctly. This is the final DEPLOYMENT GATE - deployment blocked if proof chain invalid. Use when engineering thread completes all actions.
majiayu000/claude-skill-registry 163
-
Prow Job Analyze Test Failure
Analyze a failed test by inspecting the code in the current project and artifacts in Prow CI job. Provide a detailed analysis of the test failure in a pre-defined format.
majiayu000/claude-skill-registry 163
-
forge-lang-terraform
Terraform infrastructure-as-code safety practices. Enforces plan-before-apply workflow. Use when working with .tf files or infrastructure commands.
majiayu000/claude-skill-registry 163
-
ai-vendor-evaluation
Comprehensive framework for evaluating AI vendors and solutions to avoid costly mistakes. Use this skill when assessing AI vendor proposals, conducting due diligence, evaluating contracts, comparing vendors, or making build-vs-buy decisions. Helps identify red flags, assess pricing models, evaluate technical capabilities, and conduct structured vendor comparisons.
majiayu000/claude-skill-registry 163
-
security-audit
Audit code for security vulnerabilities (SQL injection, XSS, OWASP Top 10). Use when adding authentication logic, handling user input, or before production deployments.
majiayu000/claude-skill-registry 163
-
jira-search
Search Jira issues using JQL queries. Use when filtering issues by project, status, assignee, date, or building reports.
majiayu000/claude-skill-registry 163
-
android-emulator-skill
Production-ready scripts for Android app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and emulator lifecycle management. Optimized for AI agents with minimal token output. Android equivalent of ios-simulator-skill.
majiayu000/claude-skill-registry 163
-
oblique
This skill should be used when the user asks to "/oblique", "oblique strategy", "give me an oblique strategy", "give me a creative prompt", or wants lateral thinking inspiration for their coding session.
majiayu000/claude-skill-registry 163
-
aip
Google API Improvement Proposals (AIP) reference. Use BEFORE designing or reviewing APIs, protobuf definitions, or any work involving Google API design standards. Fetches relevant AIP rules from https://google.aip.dev for the task at hand.
majiayu000/claude-skill-registry 163
-
new-plugin
Create a new iPlug2 plugin project by duplicating TemplateProject in the iPlug2OOS repository
majiayu000/claude-skill-registry 163
-
playwright-browser-close
To close the current Playwright page, close the page to end the session or free resources.
majiayu000/claude-skill-registry 163
-
timezone
REQUIRED for ANY date/time code - prevents timezone bugs by enforcing Mountain Time utilities instead of native Date objects. Use when working with dates, times, timestamps, scheduling, cutoffs, date inputs, or API date serialization.
majiayu000/claude-skill-registry 163
-
create-agent-skills
Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
majiayu000/claude-skill-registry 163
-
Palace Python Expert
Expert in Python development with focus on best practices, testing, and modern Python features
majiayu000/claude-skill-registry 163
-
atomic-bead-filing
Use when noticing something off (code smell, design smell, workaround) while working and want to capture it without losing flow - grounds observation in codebase and files a proper bead that future agents can execute
majiayu000/claude-skill-registry 163
-
git-analysis
Analyze git repository changes, branch differences, and commit history. Use when analyzing branches, comparing changes, examining commit history, or preparing for PR/commit operations.
majiayu000/claude-skill-registry 163
-
docs-sync
Analyze main branch implementation and configuration to find missing, incorrect, or outdated documentation in docs/. Use when asked to audit doc coverage, sync docs with code, or propose doc updates/structure changes. Only update English docs under docs/** and never touch translated docs under docs/ja, docs/ko, or docs/zh. Provide a report and ask for approval before editing docs.
majiayu000/claude-skill-registry 163
-
multi-agent-observability
Build observability interfaces for multi-agent systems. Use when monitoring multi-agent execution, tracking agent metrics, implementing logging for parallel agents, or debugging agent workflows.
majiayu000/claude-skill-registry 163
-
agent-comms
Send messages to other Claude Code sessions via tmux. Hand off complex debugging context, get second opinions, share detailed technical findings across sessions.
majiayu000/claude-skill-registry 163
-
github-info
Retrieve GitHub user profile and repository information using the gh CLI tool. Use when the user asks about their GitHub profile, statistics, repositories, or wants to view their GitHub information. Examples: Show me my GitHub profile, What are my top repositories, Get my GitHub stats.
majiayu000/claude-skill-registry 163
-
ansible-role-init
Scaffold a new Ansible role via ansible-galaxy init
majiayu000/claude-skill-registry 163
-
bias-assessor
Add bias/risk-of-bias assessment fields to an extraction table and populate them consistently.
**Trigger**: bias, risk-of-bias, RoB, evidence quality, 偏倚评估, 证据质量.
**Use when**: systematic review 已生成 `papers/extraction_table.csv`，需要在 synthesis 前补齐偏倚/质量字段。
**Skip if**: 不是 systematic review，或还没有 `papers/extraction_table.csv`。
**Network**: none.
**Guardrail**: 使用简单可复核刻度（low/unclear/high）+ 简短 notes；保持字段一致性。
majiayu000/claude-skill-registry 163