Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
roadmap-updating
Use when updating product roadmap with new PRDs - sequences PRDs by timeline, manages roadmap.md structure, and maintains changelog
majiayu000/claude-skill-registry 163
-
structured-output
majiayu000/claude-skill-registry 163
-
semantic-kernel
Build AI applications with Microsoft Semantic Kernel. Create plugins, planners, memory systems, and AI orchestration. Use for enterprise AI integration, .NET/Python AI development, and LLM application frameworks.
majiayu000/claude-skill-registry 163
-
matrix-data-model-progression-testing
Matrix data model verification using ASCII diagrams. Use when working with *Progressions.ts files, defineProgression(), or testing how 2D numeric grids evolve over time. Auto-apply when editing files matching *Progressions.ts or src/test-utils/ascii*.ts.
majiayu000/claude-skill-registry 163
-
openai-whisper
Local speech-to-text with the Whisper CLI (no API key).
majiayu000/claude-skill-registry 163
-
pci-compliance
Implement PCI DSS compliance requirements for secure handling of payment card data and payment systems. Use when securing payment processing, achieving PCI compliance, or implementing payment card security measures.
majiayu000/claude-skill-registry 163
-
questioning-hardcoded-values
Hardcoded strings and numbers need justification - they're either conventions that need documentation, magic numbers that should be constants, or assumptions that need verification
majiayu000/claude-skill-registry 163
-
bio-multi-omics-similarity-network
Similarity Network Fusion (SNF) for patient stratification using multi-omics data. Integrates multiple data types into a unified patient similarity network. Use when performing patient stratification or integrating multi-omics data into unified similarity networks.
majiayu000/claude-skill-registry 163
-
agent-skills
Create, use, and manage Agent Skills for Claude. Use when working with Skills, creating custom capabilities, or understanding how Skills extend Claude's functionality. Covers Skill architecture, file structure, and best practices.
majiayu000/claude-skill-registry 163
-
azure-mgmt-apimanagement-dotnet
Azure Resource Manager SDK for API Management in .NET. Use for MANAGEMENT PLANE operations: creating/managing APIM services, APIs, products, subscriptions, policies, users, groups, gateways, and backends via Azure Resource Manager. Triggers: "API Management", "APIM service", "create APIM", "manage APIs", "ApiManagementServiceResource", "API policies", "APIM products", "APIM subscriptions".
majiayu000/claude-skill-registry 163
-
vercel-management
Use when deploying, managing, or working with Vercel projects without using the dashboard.
Triggers: "vercel deploy", "manage vercel", "vercel project", "vercel domain", "vercel environment",
"vercel ci/cd", "vercel promotion", "vercel rollback", "vercel functions", "vercel edge",
"vercel analytics", "vercel dns", "vercel ssl", "vercel team".
Provides comprehensive workflows for authentication, deployment, domain management, environment variables,
team collaboration, and production-ready CI/CD patterns.
majiayu000/claude-skill-registry 163
-
app-crash-report
Customer reporting application crashes, missing exercises, broken features, StackBlitz issues, or other technical problems with the course platform.
majiayu000/claude-skill-registry 163
-
create-purchase-return
Create purchase return (PRT) when returning defective goods to supplier
majiayu000/claude-skill-registry 163
-
database-schema-generator
Generate ORM models, migrations, and seeds.
majiayu000/claude-skill-registry 163
-
tmux-orchestrator
This skill should be used when orchestrating tmux sessions for multi-component development workflows. Use when creating complex multi-window, multi-pane tmux layouts via the Bash tool, especially for projects requiring simultaneous backend/frontend development, microservices, or parallel task execution. This skill provides patterns for session creation, pane management, and command orchestration using the user's custom tmux configuration.
majiayu000/claude-skill-registry 163
-
agent-exec
Use the agent-exec CLI to run Codex/Claude/Cursor and manage skills for this repo.
majiayu000/claude-skill-registry 163
-
safe-file-operations
Guidelines for safely executing destructive file operations (mv, rm, cp). Use when performing file moves, deletions, or overwrites to prevent accidental data loss. Provides verification steps and best practices for batch operations.
majiayu000/claude-skill-registry 163
-
measuring-product-market-fit
Help users assess and achieve product-market fit. Use when someone is trying to determine if they have PMF, measuring user engagement and retention, running the Sean Ellis survey, or figuring out if they should scale or keep iterating.
majiayu000/claude-skill-registry 163
-
long-task-harness
Maintains continuity across long-running tasks that span multiple agent sessions. Use when starting or resuming a complex project that spans multiple sessions, or for tasks with many discrete features requiring iterative development.
majiayu000/claude-skill-registry 163
-
argparse-patterns
Standard library Python argparse examples with subparsers, choices, actions, and nested command patterns. Use when building Python CLIs without external dependencies, implementing argument parsing, creating subcommands, or when user mentions argparse, standard library CLI, subparsers, argument validation, or nested commands.
majiayu000/claude-skill-registry 163
-
amplifier-modulebuilder-skill
Build amplifier-foundation modules using "bricks and studs" architecture. Covers tool, hook, provider, context, and orchestrator modules with testing, publishing, and best practices.
majiayu000/claude-skill-registry 163
-
test-workflow-parent
Parent skill to test workflow continuation after child returns - CRITICAL BUG TEST
majiayu000/claude-skill-registry 163
-
review-semgrep
Review and triage semgrep security scan results to identify true positive vulnerabilities. Use when analyzing semgrep output, triaging security findings, reviewing static analysis results, or when the user has semgrep-results directories to review. Performs deep code analysis to distinguish real vulnerabilities from false positives with high confidence.
majiayu000/claude-skill-registry 163
-
doc-adr: Create Architecture Decision Records (Layer 5)
Create Architecture Decision Records (ADR) - Layer 5 artifact documenting architectural decisions with Context-Decision-Consequences format
majiayu000/claude-skill-registry 163