KangDongGwon/claude-skills
Custom Claude Code skills & subagents from a real research workflow — scientific writing, citation cross-check, fit validation, figures, slide QA, media pipelines
Custom Claude Code skills & subagents from a real research workflow — scientific writing, citation cross-check, fit validation, figures, slide QA, media pipelines
npx skills add KangDongGwon/claude-skillsCustom Claude Code skills & subagents from a real research workflow — scientific writing, citation cross-check, fit validation, figures, slide QA, media pipelines
A capability-based operating layer for long-running autonomous software engineering agents. Rust daemon, signed capabilities, append-only audit, drift-aware memory, fail-closed sandbox dispatch, commit-scoped provenance.
A high-performance code intelligence graph for LLMs and AI agents. Sub-second structural queries, impact analysis, and cross-repo API contracts for autonomous coding workflows.
A Claude Code skill family for generating PRD-based reports (research-prd + engineering-prd) from LaTeX source
All-in-one Codex skills for research, planning, native execution, verification, and evidence
Give your AI tools architecture-aware reasoning. Knowledge graph from any codebase — 14 LLM backends, impact analysis, confidence scores. Works with Claude Code, Cursor, VS Code Copilot.
Agent Powerup Vetting Pack for AI coding agents: ready-to-use AGENTS.md, CLAUDE.md, evals, and pitfall recovery for yeaight7/agent-powerups.