Loading...
Loading...
Found 515 Skills
Create a safe implementation plan as both markdown and JSON DAG artifacts. Challenge scope with the user first, explore real code before decomposing, then emit atomic TASK-NNN entries with explicit dependencies, write scope, validation, and assigned agents. Use when the user asks to plan, decompose, or break work into execution-ready tasks.
Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand unfamiliar code, create onboarding docs, document architecture, or explain how the system works.
Explore and investigate ideas before committing to a change. Trigger: When the orchestrator launches you to think through a feature, investigate the codebase, or clarify requirements.
Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
Navigate unfamiliar code using GitNexus knowledge graph
Analyze and explore codebases using Repomix CLI. Use when: analyzing repositories, exploring code structure, finding patterns. Triggers on: 'analyze this repo', 'explore codebase', 'what's the structure'.
Separate WHAT from HOW before planning. Clarify goals, explore approaches, capture structured design decisions. Triggers: brainstorm, explore idea, clarify goal, idea phase.
Interview user to clarify any topic - exploring codebase, investigating issues, planning features, understanding requirements, or drilling into plans. Socratic questioning to uncover details.
Execute read-only SQL queries against multiple Microsoft SQL Server databases. Use when: (1) querying MSSQL/SQL Server databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.
Visualizes datasets in 2D using embeddings with UMAP or t-SNE dimensionality reduction. Use when exploring dataset structure, finding clusters, identifying outliers, or understanding data distribution.
Systematically explore and evaluate a library, tool, or GitHub repo in an isolated scratch environment. Use this skill whenever the user asks to "try", "evaluate", "explore", or "kick the tires" on a library/repo/tool, especially when they provide a GitHub URL, npm/pip package name, or repo shorthand like "owner/repo". Use it when they want real primitives, failure modes, and composability beyond quickstarts before deciding on integration. Produces runnable scratch/ scripts demonstrating key primitives, a composition script, and a Tutorial.md with honest findings. This is NOT for full integration into an existing codebase.
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, designing systems, or making architectural decisions. Enters plan mode, reads all available docs, explores the codebase deeply, then interviews the user relentlessly with ultrathink-level reasoning on every decision until a shared understanding is reached. Produces a validated design spec before any implementation begins. Triggers on feature requests, design discussions, refactors, new projects, component creation, system changes, and any task requiring design decisions.