cat ~/新着

context-saver @mhylle

Save session context to disk for seamless continuation in new chat sessions. This skill should be used when the user...

codebase-research @mhylle

Orchestrates comprehensive codebase research by decomposing user queries into parallel sub-agent tasks and...

code-review @mhylle

Systematic code review for implementation phases verifying architectural principles, framework standards, ADR...

brainstorm @mhylle

Interactive idea refinement using Socratic questioning methodology. This skill should be used when users want to...

agent-creator @mhylle

|

adr @mhylle

Document architectural decisions in standardized ADR format. This skill should be used when making significant...

nextjs-server-side-error-debugging @otahontas

|

workflow-automation @ramidamolis-alt

Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup...

voice-agents @ramidamolis-alt

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge...

verification-before-completion @ramidamolis-alt

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running...

tdd-workflow @ramidamolis-alt

Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.

subagent-driven-development @ramidamolis-alt

Use when executing implementation plans with independent tasks in the current session

state-machine @ramidamolis-alt

Expert in complex state management with Finite State Machines, XState patterns, state persistence, race condition...

security-expert @ramidamolis-alt

Expert security analyst using ALL MCP servers. Uses Memory for known vulnerabilities, UltraThink for threat...

rollback-engine @ramidamolis-alt

Transaction rollback system for safe code operations. Checkpoint creation, selective rollback, state diff analysis,...

requesting-code-review @ramidamolis-alt

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

receiving-code-review @ramidamolis-alt

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or...

prompt-master @ramidamolis-alt

Ultimate prompt engineering with MCP integration. Expert in crafting prompts that leverage UltraThink,...

planning-with-files @ramidamolis-alt

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md....

performance-optimizer @ramidamolis-alt

Expert performance optimizer using ALL MCP servers. Uses MongoDB for metrics, UltraThink for analysis, Memory for...

parallel-agents @ramidamolis-alt

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or...

omega-agent @ramidamolis-alt

Ultimate AGI Evolution - 200 UltraThink thoughts, quantum branching, self-improvement loops, cross-skill...

nlp-master @ramidamolis-alt

Advanced NLP skill - Text classification, NER, sentiment analysis, document summarization, embeddings, and...

multi-agent-brainstorming @ramidamolis-alt

>