explorador de repositorios

codejunkie99 · Repositorios y skills representativas - Página 2

Vista por repositorio de 142 skills recopiladas en 25 repositorios de GitHub.

#13codejunkie99/graph-engineering1 skills

graph-engineeringTeaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course,…23 jul 2026

#14codejunkie99/agentic-harness1 skills

greetGreeting workflow for the native hello-world agent12 may 2026

#15codejunkie99/familiar-second-brain1 skills

familiar-second-brainAlways use when working in Kimi Work desktop sessions that should read from or save to the user's Familiar second brain. Trigger for memory, notes, projects, prior work, research, summaries, durable outputs, "save this", "remember this", "from my brain",…14 jun 2026

#16codejunkie99/tokensavings-pro1 skills

dualmodeRun the Luna execution + Sol reasoning dual-model loop. Use when the user invokes $dualmode or /dualmode, asks to set up Luna + Sol handoffs, wants to split reasoning from execution to stretch Codex quota, or asks for the task packet loop. Resident in Codex…31 ago 2026

#17codejunkie99/union-crew1 skills

union-crewCoordinate work with Union Alpha as the orchestrator and DeepSeek V4.1 Flash subagents. Use when the user invokes /union-crew or $union-crew, or requests this specific model team.17 sept 2026

#18codejunkie99/voice-agent-builder1 skills

voice-agent-builderBuild a production voice agent step by step. Use when the user wants to build, ship, or productionize a real-time voice AI agent — chained pipeline, speech-to-speech, or hybrid. Covers the full stack: streaming STT, LLM, RAG, TTS, function calling, safety,…18 may 2026

#19codejunkie99/quota-flow1 skills

quota-flowImplement features, fix bugs, create skills, and verify deliverables with Astra orchestration, Sol implementation, and narrowly scoped DeepSeek V4.1 Flash and Luna subagents while minimizing avoidable usage.12 sept 2026

#20codejunkie99/system-design-skill1 skills

system-designUse before writing code for any new app, service, or major feature (or when someone says "design", "architecture", "how should I build", "plan this system") to interview the person stage by stage, size the design to their real scale, record trade-offs, and…1 nov 2026

#21codejunkie99/codex-model-routing1 skills

model-routingChoose a coding model and suggest effort using a source-backed routing registry, with the current Codex LLM by default or optional direct Jev assessment. Use when asked to route coding tasks, choose subagent models, or set up MiMo in Codex.22 sept 2026

#22codejunkie99/image-reconstruction1 skills

image-reconstructionAnalyze image references into named visual elements and reconstruction JSON, then compile prompts for recreating, remixing, or selectively editing them. Use when the user wants to understand a reference, reuse its visual decisions, or preserve specific parts…12 sept 2026

#23codejunkie99/avids-essential-skills1 skills

claude-code-hygieneAudit and enforce 7 Claude Code best practices that most users get wrong. Checks for CLAUDE.md quality, session hygiene, feedback loops, worktree usage, permission config, prompt specificity, and parallel session opportunities. Use when: starting a new…6 abr 2026

#24codejunkie99/cracked-engineer1 skills

cracked-engineerRecords system design decisions in SYSTEM.md and MODULES.md and proves each rule with a red test that fails on a planted fault. Use when starting a service, auditing a repo for reliability gaps, changing code that touches data, money, queues, caches, or…6 nov 2026