Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Agent Caffeine
  • knobs
  • Wax
  • Snug
  • mertduzgun.com
Made by mertduzgun.com
Skills
ganyuanran avatar

Update Aegis

ganyuanran/aegis

Handles explicit Aegis method-pack updates when you say `aegis:update` or ask whether your install is current.

GitHub stars
492
last updated
Jun 11, 2026
View on GitHubSave

Install

$ npx -y skills add ganyuanran/aegis --skill update-aegis --agent claude-code

Installs into .claude/skills of the current project.

Sponsors

CodeRabbitSponsoredTry For FreeLid closed, agents workingTry itOpen StepsSponsoredDownload for freeAppSignalSponsoredStart Free TrialKeep API keys from agentsGet SnugBlock apps on your iPhoneGet WaxDevtools for design engineersTry it livebelt - the only tool your agent needsSponsoredone prompt install

What it does

The skill checks the host-scoped registry first, can register new hosts with different sync modes (junction, copy-skills, plugin-managed), and won't clobber local changes without permission. It updates one host by default or all registered hosts if you pass `--all`, then verifies with aegis-doctor before reporting the commit delta and reload hint. The registry awareness is solid: if multiple hosts share the same method-pack root, it updates the pack once and refreshes each host's exposure separately. Useful if you're running Aegis across different AI coding environments and want predictable, evidence-first updates instead of background auto-update chaos.

Files

Select a file.

Details

Repository
github.com/ganyuanran/aegis
License
MIT
First seen
Jun 11, 2026

More from ganyuanran/aegis

All 22
  • Using Aegis
  • Using Git Worktrees
  • Verification Before Completion
  • Writing Plans
  • Writing Skills
  • Anti Entropy Governance
  • Brainstorming
  • Communicating Concisely
  • Dispatching Parallel Agents
  • Establishing Project Context
  • Executing Plans
  • Finishing A Development Branch
  • First Principles Review
  • Goal Framing
  • Long Task Continuation
  • Receiving Code Review
  • Recording Architecture Decisions
  • Requesting Code Review
  • Subagent Driven Development
  • Systematic Debugging
  • Test Driven Development

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels587.7Kinstalls
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.4Minstalls
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s36.9Kinstalls
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes304.2Kinstalls
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kinstalls
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4Minstalls