Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
sayt-ide
How to write .vscode/tasks.json — build/test task schema, dependsOn chains, per-language examples (Gradle, Go, Node/pnpm, Python, Zig). Use when creating build tasks, test tasks, or fixing compilation/test failures.
majiayu000/claude-skill-registry 163
-
managing-artifacts
Use when generating documents, reports, plans, audits, or when asked where to save files. Triggers on "save report", "write plan", "where should I put", "project-encoded path"
majiayu000/claude-skill-registry 163
-
async-python-patterns
Python asyncio and concurrent programming patterns for high-performance applications. Use when building async APIs, concurrent systems, or I/O-bound applications requiring non-blocking operations.
majiayu000/claude-skill-registry 163
-
quant-analyst
Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis.
majiayu000/claude-skill-registry 163
-
create-usercontext-instructions
Create complete user-context instruction files using a structured discovery workflow and repository format rules.
majiayu000/claude-skill-registry 163
-
capability-diagnostic
Diagnose agent failures by identifying missing capabilities. Use when an agent fails a task, produces wrong output, or needs escalation. Provides a decision tree for failure analysis.
majiayu000/claude-skill-registry 163
-
gcp-cloud-run
Specialized skill for building production-ready serverless applications on GCP. Covers Cloud Run services (containerized), Cloud Run Functions (event-driven), cold start optimization, and event-dri...
majiayu000/claude-skill-registry 163
-
www
Worker Watcher - Check and manage MCP worker status (diagnostics and auto-restart). Use when user types 'www' or when MCP worker issues occur.
majiayu000/claude-skill-registry 163
-
temporal-evaluation
Calculates time-based task status including overdue detection, urgency levels (urgent/upcoming/soon), and relative time displays. Updates temporal status every 60 seconds with timezone-aware comparisons and edge case handling for tasks without due dates.
majiayu000/claude-skill-registry 163
-
n8n-syntax-code-node
Use when writing Code node logic in n8n workflows with JavaScript or Python. Prevents misuse of unavailable variables ($itemIndex, $secrets) or restricted modules (fs, http). Covers runOnceForAllItems vs runOnceForEachItem execution, available variables ($input, $json, items), binary data handling, built-in modules, $() node access, Python _ prefix convention, and restrictions. Keywords: n8n, Code node, JavaScript, Python, $input, $json, items.
majiayu000/claude-skill-registry 163
-
check-pod-resources
Check resource usage (CPU, memory) for pods. Used to identify pods consuming excessive resources. Keywords: pod resources, cpu, memory, consumption, metrics, resource usage, top pods.
majiayu000/claude-skill-registry 163
-
cost-optimization
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing c...
majiayu000/claude-skill-registry 163
-
Property Testing
Property-based testing with fast-check for business logic validation
majiayu000/claude-skill-registry 163
-
cost-tracker
Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.
majiayu000/claude-skill-registry 163
-
audit-cohesion
Audit codebase for internal cohesion - how well components fit together and maintain consistent patterns. Distinct from audit-arch (which checks rule violations); this checks integration fitness and convergence. Use when user says "audit cohesion", "check cohesion", "cohesion audit", or "alignment check".
majiayu000/claude-skill-registry 163
-
Figma to Streamlit Component
This skill should be used when "generating components from Figma", "implementing Figma designs", "importing Figma frames", "converting Figma to code", or when creating Streamlit components from design specifications.
majiayu000/claude-skill-registry 163
-
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
majiayu000/claude-skill-registry 163
-
azure-mgmt-apicenter-py
Azure API Center Management SDK for Python. Use for managing API inventory, metadata, and governance across your organization.
Triggers: "azure-mgmt-apicenter", "ApiCenterMgmtClient", "API Center", "API inventory", "API governance".
majiayu000/claude-skill-registry 163
-
sayt-cnt
How to write Dockerfile + compose.yaml — the develop/integrate service convention, multi-stage targets, dind helpers. Use when containerizing a project, writing docker compose services, or setting up integration tests.
majiayu000/claude-skill-registry 163
-
tldr-prompt
Create tldr summaries for GitHub Copilot files (prompts, agents, instructions, collections), MCP servers, or documentation from URLs and queries.
majiayu000/claude-skill-registry 163
-
nfs-storage
Configure NFS servers and clients. Implement network file sharing for Linux systems. Use when setting up shared storage.
majiayu000/claude-skill-registry 163
-
fuzzing-obstacles
Techniques for patching code to overcome fuzzing obstacles. Use when checksums, global state, or other barriers block fuzzer progress.
majiayu000/claude-skill-registry 163
-
agent-teams
Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement
majiayu000/claude-skill-registry 163
-
pytorch-lightning
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
majiayu000/claude-skill-registry 163