Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
dev-design
This skill should be used when the user asks to "propose architecture", "design implementation approach", "choose between approaches", or in Phase 4 of /dev workflow after exploration is complete. Proposes 2-3 architecture approaches with clear trade-offs, decomposes features into independent tasks, and obtains explicit user approval before implementation begins.
majiayu000/claude-skill-registry 163
-
microservices-architect
Use when designing distributed systems, decomposing monoliths, or implementing microservices patterns. Invoke for service boundaries, DDD, saga patterns, event sourcing, service mesh, distributed tracing.
majiayu000/claude-skill-registry 163
-
managing-tech-debt
Manage technical debt by producing a Tech Debt Management Pack (debt register, scoring/prioritization, refactor vs rewrite decision memo, incremental paydown plan, migration/rollback plan, metrics, and stakeholder cadence). Use for tech debt, refactoring, legacy modernization, and migrations.
majiayu000/claude-skill-registry 163
-
vector-index-tuning
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
majiayu000/claude-skill-registry 163
-
synthetic-data-generation
Generate realistic synthetic data using Faker and Spark, with non-linear distributions, integrity constraints, and save to Databricks. Use when creating test data, demo datasets, or synthetic tables.
majiayu000/claude-skill-registry 163
-
bio-small-rna-seq-mirdeep2-analysis
Discover novel miRNAs and quantify known miRNAs using miRDeep2 de novo prediction from small RNA-seq data. Use when identifying new miRNAs or performing comprehensive miRNA profiling with discovery.
majiayu000/claude-skill-registry 163
-
treesitter
Parse and extract code symbols using tree-sitter. Use when you need to extract functions, classes, or understand code structure from files or code blocks.
majiayu000/claude-skill-registry 163
-
devops-platform-patterns
Platform-specific IaC checklists for DigitalOcean, Hetzner, AWS, and Cloudflare.
majiayu000/claude-skill-registry 163
-
plutonium-create-resource
Generate Plutonium resources with models, migrations, controllers, policies, and definitions
majiayu000/claude-skill-registry 163
-
action_logger
Keep an audit trail of changes, commands, and verification.
majiayu000/claude-skill-registry 163
-
lease-abstraction-specialist
Expert in lease abstraction and critical terms extraction. Use when abstracting lease agreements, extracting key dates, identifying critical provisions, or creating lease summaries. Key terms include lease abstraction, critical dates, rent schedule, operating costs, renewal options, termination rights, default provisions, use clause, assignment clause, Schedule G special provisions
majiayu000/claude-skill-registry 163
-
rendering-conditional-render
Use explicit ternary operators instead of && for conditional rendering. Apply when rendering values that could be 0, NaN, or other falsy values that might render unexpectedly.
majiayu000/claude-skill-registry 163
-
grove-testing
Write effective, maintainable tests that catch real bugs and enable confident refactoring. Use when deciding what to test, reviewing test quality, or writing tests for Grove features. Focuses on philosophy and strategy—pair with javascript-testing for implementation details.
majiayu000/claude-skill-registry 163
-
clarify-spec
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren.
Erkennungsmerkmale (EINES genuegt!):
- Auftrag <25 Woerter
- Keine konkreten Dateinamen/Pfade
- Vage Verben: besser, optimieren, fixen, machen, aendern, verbessern, anpassen, erweitern, refactoren, aufraumen, ueberarbeiten
- Unsichere Sprache: irgendwie, vielleicht, mal eben, schnell, einfach, bisschen, koennte, sollte
- Fehlende Erfolgskriterien: Kein damit, sodass, weil, um zu
- Relative Begriffe ohne Kontext: schneller, besser, schoener, einfacher
Output ist STRUKTURIERTES JSON fuer prompt-architect Skill.
Escape: mach einfach, keine Rueckfragen, entscheide selbst ueberspringt Klaerung.
majiayu000/claude-skill-registry 163
-
migration-generator
Create database migrations from model changes, schema diffs, and migration best practices.
majiayu000/claude-skill-registry 163
-
blockrun
Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")
majiayu000/claude-skill-registry 163
-
bear-notes
Create, search, and manage Bear notes via grizzly CLI.
majiayu000/claude-skill-registry 163
-
instantly-sdk-patterns
Apply production-ready Instantly SDK patterns for TypeScript and Python.
Use when implementing Instantly integrations, refactoring SDK usage,
or establishing team coding standards for Instantly.
Trigger with phrases like "instantly SDK patterns", "instantly best practices",
"instantly code patterns", "idiomatic instantly".
majiayu000/claude-skill-registry 163
-
typescript
Provides comprehensive TypeScript development expertise and coding standards. Ensures type safety through strict type checking, implements clean code patterns, and maintains consistent architectural decisions. Specializes in advanced type system features including generics, conditional types, mapped types, and template literal types.
Use when: working with TypeScript files (.ts/.tsx), defining type definitions and interfaces, implementing generic programming patterns, designing type-safe APIs, handling complex type transformations, integrating TypeScript with React/Vue/Angular frameworks, configuring strict mode settings, resolving type errors, or optimizing type performance in large codebases.
majiayu000/claude-skill-registry 163
-
write-issue
Writing and maintaining GitHub issues for the tldraw repository. Use when creating new issues, editing issue titles/bodies, triaging issues, or cleaning up issue metadata (types, labels).
majiayu000/claude-skill-registry 163
-
sympy
Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters.
majiayu000/claude-skill-registry 163
-
track-generation
This skill generates normalized BigWig (.bw) tracks (and/or fold-change tracks) from BAM files for ATAC-seq and ChIP-seq visualization. It handles normalization (RPM or fold-change) and Tn5 offset correction automatically. Use this skill when you have filtered and generated the clean BAM file (e.g. `*.filtered.bam`).
majiayu000/claude-skill-registry 163
-
radix-ui
Build accessible, unstyled React UI components with Radix Primitives
majiayu000/claude-skill-registry 163
-
logit-lens
Decode intermediate layer predictions using the Logit Lens technique. Use when analyzing what a model predicts at each layer, understanding information flow, or visualizing layer-wise processing.
majiayu000/claude-skill-registry 163