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

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills
sickn33 avatar

Senior Fullstack

sickn33/antigravity-awesome-skills

This is a scaffolding and analysis toolkit that bundles three Python scripts for spinning up fullstack projects, analyzing codebases, and running quality checks. It covers a wide tech stack (TypeScript, React, Next.js, Node.js, Python, Go, plus Docker and Kubernetes) with reference docs on architecture patterns and workflows. You'd reach for this when starting a new fullstack project or auditing an existing one for best practices. The scope is ambitious, maybe too ambitious, so expect to adapt the outputs rather than use them as-is. Marked critical risk because automated scaffolding and code changes need careful review before you commit them.

installs
1.8K
GitHub stars
43.1K
last updated
Jul 14, 2026
View on GitHubSave

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill senior-fullstack --agent claude-code

Installs into .claude/skills of the current project.

Files

Full-Stack Implementation Review

When to Use

Use when a feature spans the browser, backend service and database, or when reviewing an existing full-stack implementation for integration gaps.

Workflow

  1. Inspect the project's actual stack, build commands and conventions. Trace one user journey through interface state, API request, authorization, data access and response handling.
  2. Define the request/response contract, permission checks, input validation and failure states before changing code. Keep database migrations and external side effects explicit.
  3. Implement the smallest coherent slice using existing dependencies. Separate interface presentation, domain logic and persistence; use parameterized queries and server-side authorization.
  4. Run project-owned checks for the changed behavior: unit tests for rules, integration tests for permissions and persistence, and browser tests for the complete journey. Record which checks actually ran and any missing environments.
  5. Prepare a migration, rollback and release plan where needed. Dependency installation, destructive data changes, external notifications and deployments require authorization appropriate to that action.

Example

User: "Add a billing settings page."

Assistant: Inspect the existing billing integration and account permissions, define the settings API, implement loading/empty/error states, and test that one account cannot modify another account's settings. Prepare provider writes and deployment separately from local implementation; do not create a paid subscription merely to test the interface.

Bundled references

  • Stack inspection checklist
  • Boundary and contract review
  • Implementation and verification workflow

Helper status

The three retained Python helpers are unimplemented historical skeletons. They intentionally fail with a nonzero exit and do not scaffold, analyze quality or certify a project. Use the project's real tools; do not report an empty findings list as a clean audit. No executable installation or production deployment is supplied by this skill.

Limitations

  • Stack and provider compatibility must be checked in the actual project.
  • The references are review checklists, not complete application templates.
  • Passing a subset of tests does not prove security, performance or deployment readiness.
  • Do not infer permission to change accounts, billing or production resources from a request for a code review.
SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/sickn33/antigravity-awesome-skills

More from sickn33/antigravity-awesome-skills

All 708
  • Agent Memory Systems1.7K
  • Database Design1.7K
  • Scroll Experience1.6K
  • Shopify Development1.6K
  • Youtube Summarizer1.6K
  • App Store Optimization1.5K
  • Backend Dev Guidelines1.5K
  • Bash Linux1.5K
  • Bullmq Specialist1.5K
  • Cc Skill Security Review1.5K
  • Vercel Deployment1.5K
  • Bash Scripting1.4K
  • Browser Extension Builder1.4K
  • Documentation Templates1.4K
  • Prompt Engineer1.4K
  • Aws Serverless1.3K
  • Backend Architect1.3K
  • Conversation Memory1.3K
  • Copywriting1.3K
  • Discord Bot Architect1.3K
  • Firebase1.3K
  • Gcp Cloud Run1.3K
  • Github Workflow Automation1.3K
  • Last30days1.3K

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels594.9Kinstalls
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 s37.9Kinstalls
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes309.2Kinstalls
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 int4.1Minstalls