Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
discovery-sales-expert
Unified discovery and sales execution expert consolidating 38 Questions,
CVM White Glove methodology, email patterns, and stage playbooks.
Use when: discovery calls, pipeline execution, email drafting, stage transitions
Triggers on: "discovery call", "38 questions", "volume commitment", "white glove",
"follow-up email", "proposal", "stage transition", "win-back",
"implementation", "test-to-ramp", "GRI", "outreach"
majiayu000/claude-skill-registry 163
-
faion-net
Universal orchestrator for software projects: SDD workflow, research, product planning, development, marketing, project/business analysis, UX. 60+ agents, 40+ skills, 250+ methodologies.
majiayu000/claude-skill-registry 163
-
design-exploration
Generate visual design proposal catalogues for existing projects. Use when:
- User wants to explore design directions before implementation
- Redesigning or refreshing an existing interface
- Starting /aesthetic or /polish without clear direction
- User says "explore designs", "show me options", "design directions"
Keywords: design catalogue, proposals, visual exploration, aesthetic directions, DNA
majiayu000/claude-skill-registry 163
-
convex-realtime
Patterns for building reactive apps including subscription management, optimistic updates, cache behavior, and paginated queries with cursor-based loading
majiayu000/claude-skill-registry 163
-
form-state-management-engine
Architect a high-performance form engine handling validation, dirtiness, and dependent fields.
majiayu000/claude-skill-registry 163
-
typescript-advanced-patterns
Advanced TypeScript patterns for type-safe, maintainable code using sophisticated type system features. Use when building type-safe APIs, implementing complex domain models, or leveraging TypeScript's advanced type capabilities.
majiayu000/claude-skill-registry 163
-
lindy-local-dev-loop
Set up local development workflow for Lindy AI agents.
Use when configuring local testing, hot reload, or development environment.
Trigger with phrases like "lindy local dev", "lindy development",
"lindy hot reload", "test lindy locally".
majiayu000/claude-skill-registry 163
-
creating-components
React component architecture for creating composable, accessible components with data attributes. Use when creating/updating composable components, not for higher-level feature/page components.
majiayu000/claude-skill-registry 163
-
wcag-robust
Principio 4 de WCAG - compatibilidad con tecnologías actuales y futuras. Use cuando implemente HTML, ARIA, o componentes custom para asegurar compatibilidad.
majiayu000/claude-skill-registry 163
-
manage-client-state
クライアント状態をグローバル/URL状態で型安全に管理します。サイドバーやフィルタはuseSWRImmutable、ページネーションはnuqs。
majiayu000/claude-skill-registry 163
-
moai-project-batch-questions
Standardize AskUserQuestion patterns and provide reusable question templates for batch optimization
majiayu000/claude-skill-registry 163
-
test-orchestrator
Coordinates testing strategy and execution across all test types. Use when creating test plans, implementing tests (unit/integration/E2E), or enforcing coverage requirements (80% minimum). Applies testing-requirements.md.
majiayu000/claude-skill-registry 163
-
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
majiayu000/claude-skill-registry 163
-
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
majiayu000/claude-skill-registry 163
-
session-replay
Analyze claude-trace JSONL files for session health, patterns, and actionable insights.
Use when debugging session issues, understanding token usage, or identifying failure patterns.
majiayu000/claude-skill-registry 163
-
rust-cargo-check
Prefer `cargo check` over `cargo build` when making Rust code changes. Use `cargo check` to quickly verify code compiles; only use `cargo build` when you need to run the executable.
majiayu000/claude-skill-registry 163
-
ml-pipeline-workflow
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
majiayu000/claude-skill-registry 163
-
ln-750-commands-generator
Generates project-specific .claude/commands for Claude Code
majiayu000/claude-skill-registry 163
-
advertisement
Objects announce what they can do — The Sims style
majiayu000/claude-skill-registry 163
-
Confidence Scoring
See the main Model Explainability skill for comprehensive coverage of confidence scoring and calibration.
majiayu000/claude-skill-registry 163
-
shift-gate
majiayu000/claude-skill-registry 163
-
OpenAI AgentKit Expert
Build production-ready multi-agent systems using OpenAI AgentKit and Agents SDK with best practices for agent orchestration, handoffs, and routines
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
-
performance-trace-guide
Guide collection and analysis of performance traces. Use when a mid-level developer needs to diagnose slowness.
majiayu000/claude-skill-registry 163