Agent skills for Claude Code

Design a source evaluation protocol using lateral reading and credibility checks for digital information.

Grounds every implementation decision in official documentation.

Source-driven technical research and Chinese reporting for open-source projects, frameworks, libraries, applications, and infrastructure…

Cross-validates research facts and evaluates source credibility before content creation to ensure factual accuracy.

Publish static page artifacts to SourceCraft Sites (Yandex infrastructure, works in Russia), with advisory image optimization and an…

Optimizes economics manuscripts for submission to the South China Journal of Economics (《南方经济》) using CSSCI standards.

API design principles and decision-making.

Game development orchestrator. Routes to platform-specific skills based on project needs.

Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).

Skill for spacecraft power system sizing and analysis

Manages spaced repetition review sessions and calculates recall intervals to ensure long-term knowledge retention.

Generous whitespace, consistent padding, and grid-based layouts for clean, readable, and breathing interfaces.

Write Spanish that sounds human. Not formal, not robotic, not AI-generated.

Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration

Agent skill for sparc-coordinator - invoke with $agent-sparc-coordinator

Run the SPARC Refinement and Completion phases — review code, improve test coverage, validate against specification, and generate…

Agent skill for specification - invoke with $agent-specification

Troubleshoot Spark applications on AWS EMR, Glue, and SageMaker - analyze failures, identify bottlenecks, get code recommendations.

Help users build sparse Merkle trees with Poseidon or SHA-256 hashing for ZK circuits, privacy pools, and state commitments using…

Minimal SPARV workflow (Specify→Plan→Act→Review→Vault) with 10-point spec gate, unified journal, 2-action saves, 3-failure protocol, and…