Loading...
Loading...
Found 1,115 Skills
Automate Codeinterpreter tasks via Rube MCP (Composio). Always search tools first for current schemas.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
Analyzes search engine results pages (SERPs) to understand ranking factors, SERP features, user intent patterns, and AI overview triggers. Essential for understanding what it takes to rank.
Error handling patterns for ERPNext Document Controllers. Use when implementing try/except, validation errors, permission errors, and transaction management. Covers rollback patterns, error logging, and user feedback. V14/V15/V16 compatible. Triggers: controller error, try except catch, ValidationError, PermissionError, rollback, error handling.
Error handling patterns for ERPNext/Frappe API development (v14/v15/v16). Covers whitelisted method errors, REST API errors, client-side handling, external integrations, and webhooks. Triggers: API error, whitelisted method error, frappe.call error, REST API error, webhook error, external API error, HTTP status codes.
Deterministic syntax for building Frappe custom apps including app structure, pyproject.toml, modules, patches and fixtures
Automates Microsoft PowerPoint via JXA with AppleScript dictionary discovery. Use when asked to "automate PowerPoint presentations", "create slides programmatically", "JXA PowerPoint scripting", or "export PowerPoint to PDF". Covers presentations, slides, shapes, text, tables, export enums, and interop with Excel.
Perplexity AI search and research. Use for AI search.
Expert guidance for building production-ready FastAPI applications with modular architecture where each business domain is an independent module with own routes, models, schemas, services, cache, and migrations. Uses UV + pyproject.toml for modern Python dependency management, project name subdirectory for clean workspace organization, structlog (JSON+colored logging), pydantic-settings configuration, auto-discovery module loader, async SQLAlchemy with PostgreSQL, per-module Alembic migrations, Redis/memory cache with module-specific namespaces, central httpx client, OpenTelemetry/Prometheus observability, conversation ID tracking (X-Conversation-ID header+cookie), conditional Keycloak/app-based RBAC authentication, DDD/clean code principles, and automation scripts for rapid module development. Use when user requests FastAPI project setup, modular architecture, independent module development, microservice architecture, async database operations, caching strategies, logging patterns, configuration management, authentication systems, observability implementation, or enterprise Python web services. Supports max 3-4 route nesting depth, cache invalidation patterns, inter-module communication via service layer, and comprehensive error handling workflows.
Google search via Serper API with full page content extraction. Fast API lookup + concurrent page scraping (3s timeout). One well-crafted query returns rich results — avoid multiple calls. Two modes, explicit locale control. API key via .env.
Use when interpreting Culture Index surveys, CI profiles, behavioral assessments, or personality data. Supports individual interpretation, team composition (gas/brake/glue), burnout detection, profile comparison, hiring profiles, manager coaching, interview transcript analysis for trait prediction, candidate debrief, onboarding planning, and conflict mediation. Handles PDF vision or JSON input.