daily-review
About
The daily-review skill helps developers conduct end-of-day journaling by automatically creating dated journal entries and pulling GitHub commit summaries. It prompts users through a conversational workflow to review daily accomplishments and plan tomorrow's tasks. Key features include date verification, template-based journal creation, and integration with GitHub activity via CLI tools.
Quick Install
Claude Code
Recommended/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/daily-reviewCopy and paste this command in Claude Code to install this skill
Documentation
Run the Daily Review Workflow. Keep it conversational - ask one thing at a time.
Steps
-
Get current date first
- Run
date +%Y-%m-%dto confirm today's date - DO NOT assume the date - always verify
- Run
-
Journal Entry Setup
- Check if today's entry exists (
my-vault/02 Calendar/YYYY-MM-DD.md) - Create from template if not (see
references/template.md) - If morning reviewing yesterday: use yesterday's date
- Check if today's entry exists (
-
What Did I Work On?
- Pull GitHub commits:
gh search commits --author=TaylorHuston --committer-date=YYYY-MM-DD - Summarize into meaningful bullets (not raw commit messages)
- Ask: "Any other technical work? (studying, courses, side projects not on GitHub)"
- Pull GitHub commits:
-
What Did I Do?
- Ask: "How about personal stuff? (errands, social, health, appointments, etc.)"
-
Daily Highlight Check
- Review the day's highlight if set
- Ask: "Did you accomplish your highlight? Want to carry it to tomorrow?"
-
Quick Inbox Scan (offer, don't force)
- "Want me to check your inbox for anything to quickly process?"
-
Tomorrow's Highlight (offer, don't force)
- "Do you know what tomorrow's focus should be?"
-
Memory Capture Check
- Review the conversation for anything memory-worthy:
- New preferences expressed
- Corrections to how you understood something
- Life/job updates
- Workflow insights
- Project decisions
- If anything qualifies, create a memory file in
.claude/memories/ - Check if
about-taylor.mdneeds updating (job status, current focus, etc.) - Do this silently unless there's something significant to confirm
- Review the conversation for anything memory-worthy:
Use bulleted lists in the journal.
GitHub Repository
Related Skills
sglang
MetaSGLang 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.
evaluating-llms-harness
TestingThis 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.
langchain
MetaLangChain 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.
llamaguard
OtherLlamaGuard 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.
