RadarTopicsBuildersWeeklyReads
Open Source Radar
tech-leads-club/

agent-skills

GitHubWebsite

Agent Skills is a TypeScript CLI catalog to install, update, and manage vetted AI agent skills from a centralized registry. It supports interactive wizard setup, per-skill installation, and MCP server integration.

5.0kstars
450forks
7issues
2026since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
Reviewgenerated from repository data · Aug 5, 2026

What it is

Agent Skills is a CLI tool (TypeScript) that serves as a secure, validated skill registry for AI coding agents. It provides commands to install, update, remove, and list skills, and supports targeting specific agents (e.g., Cursor, Claude Code) and installation methods (copy or symlink).

How it works

The CLI fetches the skills catalog on-demand from a CDN, allows browsing and selecting skills, downloads and caches them locally, and installs them into the target agent configurations. Cached skills are stored in ~/.cache/agent-skills/ for offline use. It also includes an MCP server implementation (@tech-leads-club/agent-skills-mcp) to expose the catalog to AI agents.

Getting started

Install Skills in Your Project

npx @tech-leads-club/agent-skills

This launches an interactive wizard with steps: Choose Action, Browse & Select, Choose agents, Installation method, Scope. Other CLI usage:

# List available skills
agent-skills list
agent-skills ls        # Alias

# Install one skill
agent-skills install -s tlc-spec-driven

# Install multiple skills
agent-skills install -s aws-advisor coding-guidelines docs-writer

# Install to specific agents
agent-skills install -s my-skill -a cursor claude-code

Global Installation (Optional)

npm install -g @tech-leads-club/agent-skills
agent-skills  # Use 'agent-skills' instead of 'npx @tech-leads-club/agent-skills'

Recent releases

Latest: 0.17.2 (2026-08-04) — features tlc-spec-driven: close task status in the same atomic commit. Other recent: 1.4.10 (2026-07-31) - alignment release with no code changes; 0.17.1 (2026-07-31) with autonomous operator skill; 0.1.6 (2026-07-31) with MCP staging; 1.4.9 (2026-07-20) fixes.

Traction

Stars: 4983; Forks: 450; Open issues: 7; Language: TypeScript; License: none listed.

Behind the repo

URL to project site: https://tech-leads-club.github.io/agent-skills/

Caveats

License: Software Engine under MIT License; content licensing includes CC-BY-4.0 for skill files; age: created 2026-01-19; last push 2026-08-04.

Agent skills inside · 87
All skills →
tlc-spec-drivenFeature planning and implementation with 4 adaptive phases (Specify, Design, Tasks, Execute). Auto-sizes depth by complexity. Writes testable requirements in EARS notation, atomic tasks, atomic Conventional Commits, and requirement traceability. Ships deterministic Python validation scripts so structural gates are enforced by code, not memory. Features an independent Verifier (author != verifier, evidence-or-zero), a discrimination sensor, a decision log (STATE.md), a test-coverage matrix, and a self-improving lessons layer. Stack-agnostic and tool-agnostic. Use when (1) planning features, (2)Testing & QAscriptsexcalidraw-studioGenerate Excalidraw diagrams from natural language descriptions. Outputs .excalidraw JSON files openable in Excalidraw. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", "generate an Excalidraw file", "draw an ER diagram", "create a sequence diagram", or "make a class diagram". Supports flowcharts, relationship diagrams, mind maps, architecture, DFD, swimlane, class, sequence, and ER diagrams. Can use icon libraries (AWS, GCP, etc.) when set up. Do NOT use for code architecture analysis (use the architecture skilDevOps & Cloudscriptsmermaid-studioExpert Mermaid diagram creation, validation, and rendering with dual-engine output (SVG/PNG/ASCII). Supports all 20+ diagram types including C4 architecture, AWS architecture-beta with service icons, flowcharts, sequence, ERD, state, class, mindmap, timeline, git graph, sankey, and more. Features code-to-diagram analysis, batch rendering, 15+ themes, and syntax validation. Use when users ask to create diagrams, visualize architecture, render mermaid files, generate ASCII diagrams, document system flows, model databases, draw AWS infrastructure, analyze code structure, or anything involving "meDevOps & Cloudscriptsevolutionary-modular-architectureGuides design and implementation of evolutionary modular-monolith platforms with DDD (strategic + tactical), flat-by-aggregate organization, an Anti-Corruption Layer for vendor independence, a transactional outbox for events, smart resilience (backoff with jitter, circuit breakers, idempotency), and a polished architecture HTML document with elegant SVG diagrams. Use when designing a platform or backend, defining bounded contexts, organizing modules and folders, choosing monolith vs microservices, decoupling from an external service (ERP, storage, AI), making calls resilient, adding real-time Backend & APIscriptsaws-advisorExpert AWS Cloud Advisor for architecture design, security review, and implementation guidance. Leverages AWS MCP tools for accurate, documentation-backed answers. Use when user asks about AWS architecture, security, service selection, migrations, troubleshooting, or learning AWS. Triggers on AWS, Lambda, S3, EC2, ECS, EKS, DynamoDB, RDS, CloudFormation, CDK, Terraform, Serverless, SAM, IAM, VPC, API Gateway, or any AWS service. Do NOT use for non-AWS cloud providers or general infrastructure without AWS context.Securityscriptsnestjs-modular-monolithSpecialist in designing and implementing scalable modular monolith architectures using NestJS with DDD, Clean Architecture, and CQRS patterns. Use when building modular monolith backends, designing bounded contexts, creating domain modules, implementing event-driven module communication, or when user mentions "modular monolith", "bounded contexts", "module boundaries", "DDD", "CQRS", "clean architecture NestJS", or "monolith to microservices". Do NOT use for simple CRUD APIs, frontend work, general NestJS questions without architectural context, or stack-agnostic evolutionary modular monolith Frontendscripts
SharePost on XLinkedIn
All trending reposRevenue-verified startups →