latestaiagents

Developer plugin: the 19 developer skills + 2 commands. MCP servers: GitHub, Sentry, Linear, Atlassian (each needs your own account).

19 skills · 2 commands · 4 MCP servers

Security plugin: all 16 security skills (OWASP-category and common practices) + 2 commands. MCP server: GitHub. For the same skills without commands or MCP, install the security entry.

16 skills · 2 commands · 1 MCP server

DevOps/SRE plugin: incident response, runbooks, on-call, Kubernetes troubleshooting, observability, SLOs. 8 skills + 6 commands. MCP servers: Datadog, PagerDuty, GitHub (each needs your own account).

8 skills · 6 commands · 3 MCP servers

Multi-agent plugin: the 13 agent-architect skills + 2 commands (design-agent, debug-agent). No MCP servers.

13 skills · 2 commands

Multi-agent system design: supervisor and mesh patterns, handoffs, memory, tool routing, error recovery, cost budgets, testing, LangGraph, durable state, human-in-the-loop, checkpointing, A2A. 13 skills. Same skills as agent-plugin, without its commands.

13 skills

QA/Testing plugin: test strategy, test writing, Playwright automation, API and performance testing. 6 skills + 3 commands. MCP servers: BrowserStack, Atlassian, GitHub (each needs your own account).

6 skills · 3 commands · 3 MCP servers

RAG plugin: the 7 rag-architect skills (chunking, hybrid retrieval, GraphRAG, agentic and corrective RAG, evaluation, production checklist) + 3 commands. MCP server: Pinecone (needs your API key).

7 skills · 3 commands · 1 MCP server

Every skill pack in this repository (109 skills) plus 10 slash commands: safety, Git, debugging, code intelligence, multi-agent architecture, LLMOps, RAG, security, MCP, Claude API features, Agent SDK, skills authoring, evals, design, SEO, and video. Does not include the plugins/ bundles.

10 commands

Skills for OWASP Top 10 risk areas (organized by the 2017 list, each mapped to its 2025 category): injection, authentication, access control, XSS, misconfiguration, and more. 10 skills.

10 skills

HR/People Ops plugin: job descriptions, interview question banks, performance reviews, compensation analysis, onboarding checklists, policy documents. 6 skills + 2 commands. No MCP servers.

6 skills · 2 commands

AI-assisted coding workflows: context building, reviewing AI-generated code, refactoring, test generation, debugging, doc sync, code explanation. 7 skills.

7 skills

Production LLM operations: token cost analysis, caching patterns, model routing, rate limiting, audit logging, prompt-injection defenses, fallback chains. 7 skills.

7 skills

Model Context Protocol: server authoring, client integration, tool design, resources and prompts, authorization, transports, security. 7 skills.

7 skills

Use Claude API platform features correctly: thinking and effort, prompt caching, long context and context management, memory tool, code execution, web search and fetch, and computer use. Version-neutral guidance with links to the official docs. 7 skills.

7 skills

Retrieval-augmented generation: hybrid retrieval, chunking, GraphRAG, agentic and corrective RAG, evaluation, production checklist. 7 skills. Same skills as the rag-plugin plugin, without its commands and MCP server.

7 skills

Common security practices: API security, secrets detection, secure code review, CSRF, security headers, JWT. 6 skills.

6 skills

Debugging workflows: error patterns, log forensics, stack traces, minimal reproductions, performance profiling, dependency conflicts. 6 skills.

6 skills

Git workflows: merge conflicts, undoing mistakes, safe rebases, commit messages, branching strategy, history search. 6 skills.

6 skills

Build agents with the Claude Agent SDK and Managed Agents: quickstart, streaming, Managed Agents API, session lifecycle, subagents. 5 skills. Formerly claude-agent-sdk.

5 skills

Mandatory confirmations for destructive operations, migration and database safety, file and Git safety. 5 skills (same as the safety entry).

5 skills

Avoid generic, template-looking UI. Audit pages for template defaults, set a visual direction from the product's subject, build typography and color systems, write specific copy, and keep a WCAG 2.2 AA baseline. Complements Anthropic's frontend-design skill. 5 skills.

5 skills

Measure LLM quality: LLM-as-judge, eval dataset design, regression evals, golden sets, cost/quality tradeoffs. 5 skills.

5 skills

Plan, design, finish, and caption videos with agents: a production pipeline with a Remotion / HyperFrames / FFmpeg-only decision guide, motion design principles, tested FFmpeg post-production recipes, captions and transcription, and product demo videos. Works alongside the official Remotion and HyperFrames skills. 5 skills.

5 skills

Technical SEO and AI search visibility without guesswork: technical SEO audit, AI crawler access by purpose (training, search, user fetch), an honest llms.txt assessment, programmatic SEO guardrails against Google spam policies, and a Product Hunt / Show HN launch checklist. 4 skills.

4 skills

Author agent skills that activate reliably: frontmatter, activation patterns, progressive disclosure, testing. 4 skills.

4 skills

Developer skill packs in one install: Git mastery, code intelligence, and debug detective. 19 skills. Same skills as the developer-toolkit plugin, without its commands and MCP servers.

Agent architecture and LLMOps skills in one install: multi-agent patterns, LangGraph, cost, caching, rate limiting, audit logging, prompt-injection defenses, fallbacks. 20 skills.

Essential safety skills: confirmation protocols for destructive operations, database, migration, file, and Git safety. 5 skills.

Security skill packs in one install: OWASP-category skills and common security practices. 16 skills. Same skills as the security-guardian plugin, without its commands and MCP server.