Agent Skills
Home /Claude Skills /meridian
Highly Recommended

Meridian

Say goodbye to repeating requirements endlessly
Make AI remember every project detail
Core Principle:
Meridian acts as behavioral guardrails for Claude Code, solving context loss in complex tasks. It automatically preserves session memory, enforces quality gates, and lets Claude retain project history like a seasoned team member. No more repeating requirements or Claude forgetting critical details mid-task.
KEY FEATURES
01Memory Preservation
Auto-saves key decisions to memory.jsonl, loaded automatically in new sessions
02Quality Gates
Mandatory plan-reviewer and code-reviewer checks before submission
03Session Continuity
session-context.md maintains full workflow for resuming anytime
04Smart Alerts
Warns before context compaction to preserve critical info
github.com/markmdev/meridian
testing-security·markmdev·2026-02-06·⭐ 126·🔱 12
Curated by agent-skills.cc
Installation
Download
HTTPS
git clone https://github.com/markmdev/meridian.git
SSH
git clone [email protected]:markmdev/meridian.git
GitHub CLI
gh repo clone markmdev/meridian
FAQ
Q: What are the installation steps for Meridian Agent Skills?
1.Install: One-command Meridian integration
2.Session Start: Auto-loads historical memory
3.Plan Review: Mandatory plan-reviewer approval
4.Implementation: code-reviewer ensures quality
Q: What are the highlights of Meridian Agent Skills?
  • Never lose context
  • Auto quality control
  • Seamless resuming
  • Learns from history
Q: What are the use cases for Meridian Agent Skills?
  • Multi-week feature development
  • Projects requiring strict code review
  • Long-term collaborative projects
  • Technical debt cleanup
Q: What are the limitations of Meridian Agent Skills?
  • Over-engineering for simple tasks
  • Requires initial setup learning
Related Claude Code Skills
openclaw

openclaw/openclaw

openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

157.6k24.4k
awesome-chatgpt-prompts

f/awesome-chatgpt-prompts

f

Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

Validated by 140k users, used by Harvard professors - turn you into an AI conversation expert in 3 seconds

142.4k18.9k
system-prompts-and-models-of-ai-tools

x1xhlol/system-prompts-and-models-of-ai-tools

x1xhlol

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

300k+ lines of real system prompts let you develop from the perspective of AI tool creators

108.4k28.4k
claude-code

anthropics/claude-code

anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Dramatically boosts development efficiency, handles complex Git operations with simple commands

56.7k4.1k
skills

anthropics/skills

anthropics

Public repository for Agent Skills

Official skill repository ensures quality, ready-to-use solutions for 90% professional needs

56.7k5.5k
superpowers

obra/superpowers

obra

An agentic skills framework & software development methodology that works.

Not just coding but organizing development workflow - like getting a free technical lead

45.5k3.4k