Agent Skills
Instruction packs that give your AI agent know-how. Three different kinds — pick the right one below.
✦ Standalone skills2,933
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons725
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
prototype
★ 155,900by mattpocock
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
power-bi-performance-troubleshooting
✓★ 36,200by github
Systematic framework for diagnosing and resolving Power BI performance bottlenecks across models, reports, and infrastructure. Covers four diagnostic areas: model design and DAX efficiency, report layout and visual complexity, infrastructure capacity, and data source connectivity Includes step-by-step troubleshooting methodology with issue classification, baseline metrics collection, and targeted diagnosis workflows Provides concrete optimization patterns for DAX formulas, storage mode...
dotnet-design-pattern-review
✓★ 36,200by github
Comprehensive C#/.NET design pattern analysis with actionable improvement recommendations. Evaluates six core patterns: Command, Factory, Dependency Injection, Repository, Provider, and Resource patterns against GoF and SOLID principles Analyzes architecture compliance including namespace conventions, project separation, async/await patterns, and structured logging implementation Reviews code quality across security, testability, maintainability, and performance dimensions with specific...
java-springboot
✓★ 36,200by github
Comprehensive best practices guide for building production-ready Spring Boot applications. Covers project structure, dependency injection patterns, and configuration management including externalized config, type-safe properties, and environment profiles Details web layer design with RESTful APIs, DTOs, validation, and global exception handling Addresses service layer statelessness, transaction management, and data access patterns using Spring Data JPA with custom queries and projections...
breakdown-feature-implementation
✓★ 36,200by github
Detailed feature implementation plan generator following Epoch monorepo conventions. Generates comprehensive markdown implementation plans with system architecture, database schema, and API design specifications Includes Mermaid diagrams for system architecture, entity relationships, and component hierarchies with shadcn/ui integration Covers frontend component structure, state management patterns, backend service design, and deployment strategies Outputs structured plans to...
context-map
✓★ 36,200by github
Analyze codebases and map task-relevant files before implementing changes. Automatically searches for related files, dependencies, tests, and similar code patterns to establish full context Generates structured markdown output with files to modify, dependency relationships, test coverage, and reference patterns Includes risk assessment checklist for breaking changes, migrations, and configuration updates Designed as a pre-implementation step to prevent missed dependencies and unintended side...
dotnet-best-practices
✓★ 36,200by github
Validate .NET/C# code against comprehensive best practices for your solution and project. Covers 10+ practice areas including XML documentation, design patterns, dependency injection, async/await, testing standards, and error handling Enforces specific patterns: primary constructors for DI, Command Handler pattern with generics, interface segregation, and Factory pattern for object creation Includes resource management with ResourceManager for localization, structured logging via...
ef-core
✓★ 36,200by github
Entity Framework Core best practices guide covering design, performance, security, and testing patterns. Covers eight core areas: DbContext design, entity modeling, performance optimization, migrations, querying strategies, change tracking, security, and testing approaches Emphasizes practical patterns like DbContextFactory, IEntityTypeConfiguration separation, AsNoTracking() for read-only queries, and compiled queries for frequently executed operations Includes migration best practices such...
supabase-postgres-best-practices
✓★ 4,000by openai
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or…
golang-context
★ 2,400by samber
Idiomatic context.Context usage in Golang — propagation through API boundaries, cancellation, timeouts and deadlines, request-scoped values, context.WithoutCancel for background work outliving requests. Apply when designing context propagation across layers, debugging leaked or unexpired contexts, choosing between context.Background/TODO/WithoutCancel, or storing values in context. Not for code that merely accepts ctx as first parameter.
golang-safety
★ 2,400by samber
Defensive Golang coding to prevent panics, silent data corruption, and subtle runtime bugs. Use when encountering nil panics, append aliasing, map concurrent access, float comparison pitfalls, or zero-value design questions. Also use when reviewing code for nil-safety, numeric conversion overflow, resource lifecycle issues (defer in loops), or defensive copying of slices and maps.
supabase-postgres-best-practices
✓★ 2,300by supabase
Postgres performance optimization rules across 8 priority categories, from query tuning to advanced features. Organized into 8 rule categories prioritized by impact: query performance and connection management (critical), security and RLS, schema design, concurrency, data access patterns, monitoring, and advanced features Each rule includes detailed explanations, incorrect vs. correct SQL examples, EXPLAIN output analysis, and performance metrics to guide optimization decisions Covers query...
azure-prepare
✓★ 1,300by microsoft
Prepare Azure applications for deployment with infrastructure-as-code, configuration, and containerization. Generates Bicep or Terraform infrastructure code, azure.yaml configuration, and Dockerfiles based on application type and deployment target Requires mandatory plan-first workflow: analyze workspace, gather requirements, select recipe (AZD, AZCLI, Bicep, or Terraform), design architecture, then execute only after user approval Covers new app creation, modernization, and updates; routes...
code-review
✓★ 844by sentry
Code review framework following Sentry engineering practices for pull requests and code quality assessment. Covers six key problem areas: runtime errors, performance bottlenecks, side effects, backwards compatibility, ORM query issues, and security vulnerabilities Includes design assessment guidance for component interactions, architectural alignment, and requirement conflicts Requires appropriate test coverage across functional, integration, and end-to-end tests with verification of edge...
clickhouse-best-practices
✓★ 482by clickhouse
28 ClickHouse best practices rules organized by schema design, query optimization, and data ingestion strategy. Covers three critical areas: primary key and data type selection (immutable design decisions), JOIN and query optimization, and insert batching with mutation avoidance Includes 28 rules prioritized by impact, with schema design and query optimization rules marked CRITICAL due to ClickHouse's columnar storage and sparse index mechanics Provides structured review procedures for...
db-migrate
★ 195by medusajs
Execute pending Medusa database migrations and report results. Runs npx medusa db:migrate via Bash to apply all pending migrations to your Medusa database Reports migration outcomes including count of applied migrations, any errors encountered, and success confirmation Designed for Medusa projects with standard npm/npx setup
skill-progressive-disclosure-design
★ 157by samber
Decide how to split skill content between SKILL.md and reference files for context efficiency and reliable triggering. Use this whenever creating a new Claude skill, refactoring an existing one, or when a SKILL.md is growing past 300-400 lines. Also trigger when the user mentions "progressive disclosure", "reference files", "splitting skills", "skill bundling", "context window for skills", "SKILL.md too long", "what goes in references/", "skill structure", or expresses any uncertainty about...
postgres-best-practices
✓★ 16by neondatabase
Best practices and guidelines for working with Postgres. Covers schema design, indexing strategies, query optimization, migrations, and common pitfalls. Use…