Agent Skills Hub

notion-knowledge-capture

Transforms chat conversations into structured Notion documentation, saving insights, decisions, and knowledge to your workspace with proper organization.

translate

Translate research papers (markdown) while preserving LaTeX formulas, code blocks, and images, with support for batch processing, retries, and portable bundles.

wiki-architect

Analyzes codebases to generate hierarchical documentation, onboarding guides, and architectural mapping, helping teams understand and document their projects efficiently.

requirements-clarity

Clarify ambiguous requirements through systematic dialogue and scoring to ensure high-quality, actionable PRDs before starting implementation.

ai-collaboration-standards

Prevents AI hallucination and ensures evidence-based, verifiable outputs when analyzing code, reviewing technical documents, or providing recommendations.

visual-design-foundations

Establish cohesive visual systems using design tokens, modular typography scales, 8-point spacing grids, and accessible color palettes for consistent UI development.

self-improve

Self-maintaining skill for OpenCode agents to update documentation, capture learnings, and extend tool/agent capabilities dynamically.

batch-coordinator

Validates and coordinates batch study guide operations, preventing errors by enforcing template compatibility, file availability, and source-only policies before agent execution.

clean-code

Pragmatic AI-assisted coding standards focused on clean code, simplicity, and maintainability. Enforces best practices like SRP, DRY, and KISS to prevent over-engineering.

skill-creator

A framework for building modular, reusable agent skills. Provides guidelines for structuring SKILL.md, bundled scripts, references, and assets to extend Claude's capabilities.

stats-tracker

Monitor Claude Code usage, token consumption, productivity streaks, and skill effectiveness metrics to optimize your development workflow.

vibe-build

The final execution agent for the vibe-coding workflow. Builds your MVP incrementally by following the AGENTS.md master plan, managing session continuity, and verifying each feature via testing.