Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 389,706 indexed, measured the same four ways as everything else here.
69mannying/itsreallyvivek-research-agent-skill
Skill Claude CodeCodex
ML research agent persona and operating protocols. Use when designing experiments, choosing problems, reading literature, analyzing training runs, writing research notes, debugging models, or when the user invokes research mode. Embodies outcome-first reasoning, fast iteration loops, taste-building, and honest logging…
Skill Claude CodeCodex
Orchestrate the full atelier workflow in one task window using pi teams runtime teams plus predefined agents, spawning right-side worker panes only when a phase is active and routing review loops until acceptance while preserving planner/implementer live context. Use when running…
Plugin Claude Code
Bundles 1 skill · 59 tokens together
Portable LSP analysis skills for AI agents — build definition trees, find references, and decode semantic tokens from any codebase without VS Code.
Skill Claude CodeCodex
Use when refactoring TypeScript code whose tests require monkey-patching modules, swapping globals, or stubbing imports (vi.mock, jest.mock, sinon) because collaborators (database, HTTP client, clock, RNG, env, logger) are hardcoded inside the unit. Trigger on requests like "I can't test this without mocking the…
Skill Claude CodeCodex
Create YouTube-ready podcast videos from audio and images with AI-driven semantic image timing, fade transitions, and soft subtitles using local Whisper and FFmpeg.
Plugin Claude Code
Bundles 8 skills · 586 tokens together
Agent definitions and skill prompts for Claude Code covering requirement-doc planning, technical-spec planning, architecture drafting, execution planning, and end-to-end initiative planning orchestration.
selectdb/selectdb-cloud-skills
Skill Claude CodeCodex
SelectDB Cloud control-plane operations using the sdbcli CLI. Use for SelectDB Cloud setup, sdbcli auth, API host selection, warehouse/cluster context management, cluster pause/resume/reboot/create/delete/resize, billing queries, audit log inspection, public access policy, PrivateLink configuration, BYOC/SOCKS5…
Skill Claude CodeCodex
Control the Grabbit CLI to record browser interactions (HAR) and generate API workflows. Use this skill when the user wants to: (1) Automate browser actions, (2) Capture web traffic for API analysis, (3) Create deterministic workflows from browsing sessions, or (4) Learn how to use the Grabbit CLI commands.
ualberta-rcg/drac-agent-skills
Skill Claude Code
Submit, monitor, and troubleshoot Slurm jobs on Alliance (DRAC) HPC clusters. Covers Lua auto-routing, GPU/GRES discovery, MIG and soft-MIG, prolog-injected environment, proxy, cache redirection, and storage rules. Use alliance-cvmfs for software and modules, alliance-docs for cluster policies.
kieutrongthien/skills-fullstack
Skill Claude CodeCodex
Build, maintain, and debug Go backends (Gin and Echo).
Plugin Claude Code
Bundles 26 skills, 9 agents, 4 hooks · 1,343 tokens together
SeleneDB-first development lifecycle toolkit. 25 graph-native skills, 9 agents. Every skill reads from and writes to the property graph. Includes multi-agent context bridge for coordination.
halay08/fullstack-agent-skills
Skill Claude CodeCodex
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities.
Skill Claude CodeCodex
Call the argo REST API (https://argo.jkrumm.com/api) for TickTick tasks, Gmail, Calendar, Docker (homelab + VPS), UptimeKuma, weather, Garmin Health, Strength tracking, WalkingPad treadmill stats, AI usage/cost, user profile, and read-only SQL — use curl with Bearer $HOMELABAPIKEY.
Plugin Claude Code
Bundles 1 skill, 2 hooks, 1 MCP server · 89 tokens together
Maguyva code-intelligence MCP server with a usage skill and session-start guidance for indexed-repo exploration.
Skill Claude CodeCodex
Stake LYX tokens on Stakingverse (LUKSO liquid staking). Use when the user wants to stake LYX, unstake LYX, claim rewards, or check sLYX balance on Stakingverse. Supports deposit, withdrawal requests, and oracle-claim pattern.
Skill Claude CodeCodex
Detect when the user is asking about their attempted solution (Y) instead of their actual problem (X). Use when the user presents a specific approach, asks how to implement a particular technique, or seems stuck on a path that feels forced or indirect.
Skill Claude CodeCodex
Advanced desktop automation with mouse, keyboard, and screen control.
commerce-agentic/agentic-commerce-skills
Plugin Claude Code
Bundles 8 skills · 321 tokens together
AI agent skills for Shopify catalog optimization against shopping agents (ChatGPT, Gemini, Claude, Mistral, DeepSeek). Audit, fix, capture, measure causal uplift.
hwchany0ung/claude-agent-playbook
Skill Claude CodeCodex
Guide for running multiple Claude Code agents concurrently. Identifies parallelizable tasks, manages dependencies, and integrates results. Based on real multi-agent workflows.
Skill Claude CodeCodex
Runtime helper for autonomous-research-loop ledgers plus headless drive, host-owned multi-agent panel phases (--panel on, auto, or off), and the default cross-platform force-loop kit (bootstrap/start/drain with enforce/hard/notify defaults). Use to initialize, append, validate, inspect, smoke-test, drive, or…
Skill Claude CodeCodex
Publish skills and tools to the public agent-toolkit repo. Use when user says "publish skill", "push to marketplace", or wants to share skills publicly.
MichalSteczko/rhoai-agentic-skills
Skill Claude CodeCodex
Debug and fix OpenShift AI Models-as-a-Service (MaaS) issues — stuck tenants, DSC conditions, bootstrap loops, missing DBs, CrashLoopBackOff pods, HTTPRoute gateway failures, leader election crashes.
TriangulosTecnologia/devanity-skills
Skill Claude Code
Guard and improve a repository's AI-readiness. Run /guardian plan, review, audit, improve, or docs to keep it in basis-form (a basis of decisions, not a list of cases) — compressible, contractual, verifiable, safe — and to migrate rules from prose into deterministic enforcement.
Skill Claude CodeCodex
Generates a standard Domain-Driven Design (DDD) feature-first directory structure inside the lib folder.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: