Skillget

claude-best-practices

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Uyari
  • Code scan incomplete — No supported source files were scanned during light audit
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This is a reference repository containing a curated collection of Markdown files detailing best practices, workflows, and tips for using Claude Code and agentic workflows. It serves as a knowledge base rather than an executable software package or traditional MCP server.

Security Assessment
Because this project consists entirely of educational Markdown files, it poses essentially no security threat. It does not execute shell commands, make network requests, access sensitive local data, or contain hardcoded secrets. No dangerous permissions are required to view or download these files. Overall risk: Low.

Quality Assessment
The repository is actively maintained, with the most recent updates pushed today. However, there are a few notable drawbacks regarding long-term reliability. It currently has no license file, which means users do not have formal legal permission to copy, distribute, or modify the content. Additionally, it has low community visibility with only 5 GitHub stars, indicating it has not been widely peer-reviewed. As a personal knowledge base compiled by an individual, its quality depends entirely on the creator's curation.

Verdict
Safe to use as a helpful learning and reference guide, though you should be mindful of its unlicensed status if you plan to integrate its content into team documentation or commercial projects.
SUMMARY

A living knowledge base of Claude, Claude Code, skills, MCP, and agentic workflow best practices collected from practitioners and kept updated.

README.md

Claude & Claude Code Best Practices

A living knowledge base of best practices for working with Claude, Claude Code, skills, MCP tools, and agentic workflows that I PERSONALLY collected from practitioners, researchers and the community.

This is different from ecosystem trackers or reference indexes. Everything here is
there for people who are learning, not people who already know the landscape.

What This Is

This repo is a personal knowledge base I've been building while learning Claude Code and agentic workflows. Everything here comes from real practitioners sharing what actually works.... Twitter threads, blog posts, Anthropic's official guides and my own experience.

It's not a tutorial. It's a decision guide organized so you can find the right practice for the situation you're in right now.

I'm keeping this updated as I learn more. If you've found something that works, contributions are welcome.

How to Use This

Start with 00-index.md it maps every common situation to the right file and section. Don't read everything at once. Find your situation, go to the relevant file.

With Claude Code: point Claude at this repo before starting work:

"Read my knowledge base at github.com/[your-username]/claude-best-practices and use it to inform how we work together."

With claude.ai Projects: upload the .md files to your Project Knowledge so Claude can reference them in chat.

Files

File What's Inside
00-index.md Decision guide. Start here
claude-md-best-practices.md CLAUDE.md line limits, lazy loading, rewrite cadence
agentic-workflow-best-practices.md Planning, parallel agents, bug handling, multi-agent structure
skills-best-practices.md Skill authoring, skill-creator, self-improving skills
anthropic-skills-guide.md Anthropic's official 33-page guide distilled
project-docs-structure.md /documents/ folder, onboarding existing projects
skill-graphs.md Wikilink networks, MOCs, when single skill files aren't enough
mcp-tools.md MCP server setup, Exa, GitHub, and more
learning-resources.md Books, papers, videos, courses, newsletters
claude-code-2026-update.md NEW - Hooks, Auto Mode, scheduled tasks, BMAD, Skills 2.0 evals, MCP lazy loading, agent teams, context management

Contributing

If you've found a good practice that belongs here. It can be a workflow, a pattern, a tool, a tip from someone in the community. Please feel free to open a PR or an issue.

This repo grows through people sharing what actually works. If something in here is wrong or outdated, flag it.

Status

Actively updated. Started March 2026.

Sources include: Anthropic's official guides, practitioner tweets, community blogs and personal experience building with Claude Code

Yorumlar (0)

Sonuc bulunamadi