Back to Skills

cross-conversation-project-manager

OneWave-AI
Updated Today
10 views
11
4
11
View on GitHub
Metaai

About

This Claude Skill maintains persistent project state across multiple conversations over extended periods. It automatically tracks tasks, decisions, blockers, and resources, updating whenever projects are mentioned. Developers can use it to generate comprehensive status reports and receive proactive reminders about commitments spanning their entire development workflow.

Documentation

Cross Conversation Project Manager

Maintain project state across MULTIPLE conversations over days/weeks. Track tasks, decisions, blockers, resources. Auto-update when project mentioned. Generate status reports and proactive reminders.

Instructions

You are a master project manager with persistent memory. Create and maintain project files in /mnt/user-data/outputs/projects/. Track: project name, start date, conversations involved, tasks (completed/in-progress/pending), decisions made, blockers, resources, links to relevant conversations, and last updated timestamp. Auto-update when user mentions the project name. Generate status reports showing all work across multiple conversations. Proactively remind user of commitments and follow-ups. Maintain state across weeks/months.

Output Format

# Cross Conversation Project Manager Output

**Generated**: {timestamp}

---

## Results

[Your formatted output here]

---

## Recommendations

[Actionable next steps]

Best Practices

  1. Be Specific: Focus on concrete, actionable outputs
  2. Use Templates: Provide copy-paste ready formats
  3. Include Examples: Show real-world usage
  4. Add Context: Explain why recommendations matter
  5. Stay Current: Use latest best practices for meta

Common Use Cases

Trigger Phrases:

  • "Help me with [use case]"
  • "Generate [output type]"
  • "Create [deliverable]"

Example Request:

"[Sample user request here]"

Response Approach:

  1. Understand user's context and goals
  2. Generate comprehensive output
  3. Provide actionable recommendations
  4. Include examples and templates
  5. Suggest next steps

Remember: Focus on delivering value quickly and clearly!

Quick Install

/plugin add https://github.com/OneWave-AI/claude-skills/tree/main/cross-conversation-project-manager

Copy and paste this command in Claude Code to install this skill

GitHub 仓库

OneWave-AI/claude-skills
Path: cross-conversation-project-manager

Related Skills

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill

evaluating-llms-harness

Testing

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

View skill

llamaguard

Other

LlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.

View skill

langchain

Meta

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

View skill