agent-skills plugins

2,071 tagged agent-skills, measured the same way as everything else here.

Browse within: claude-code-plugin 261agentic-ai 108agents 102claude-code-marketplace 96skills 89claude-code-skills 78cli 77ai-tools 74antigravity 67ai-coding 66claude-code-plugins 65LLM 63agentskills 63claude-code-skill 56

powabase

577

powabase-ai/agent-skills

Plugin Claude Code

Bundles 1 skill · 210 tokens together

Build on Powabase — the AI Backend-as-a-Service (RAG, agents, orchestration, workflows) plus a Supabase-style BaaS layer. Bundles the powabase agent skill under skills/.

not rated 9 1mo ago A tokens not measured original Apache-2.0

unknowns

579

hiendinhngoc/unknowns

Plugin Claude Code

Bundles 6 skills · 342 tokens together

Skills for discovering and closing knowledge gaps across the dev lifecycle, from Thariq's 'Know Your Unknowns'.

not rated 9 1mo ago A tokens not measured original MIT

pickysteve

582

KernelLord/pickysteve

Plugin Claude Code

Bundles 1 MCP server

Skill router and context picker for coding agents — picks the right skill per prompt, scans both the request and every retrieved doc for prompt injection.

not rated 9 1mo ago A tokens not measured original MIT

fomo-kernel

583

atomchung/fomo-kernel

Plugin Claude Code

Bundles 2 skills, 1 hook, 1 MCP server · 81 tokens together

Help with investment decisions and explicit candidate searches — research, discover, compare, rank, and recommend with or without a recorded book, reading the user's own notes first when installed in their investing folder. Use for buy, add, reduce, trade-review, brokerage-statement, and position-review decisions. A…

not rated 9 changed 4d ago A tokens not measured original MIT

deepvista

584

DeepVista-AI/deepvista-cli

Plugin Claude Code

Bundles 1 skill, 2 commands, 5 hooks · 122 tokens together

Remote-managed skill catalog from DeepVista. Auto-syncs thin stubs into the plugin's skills dir on SessionStart; full bodies are lazy-loaded at invocation time.

not rated 9 1mo ago A tokens not measured original Apache-2.0

reaper

588

SebastianElvis/reaper

Plugin Claude Code

Bundles 10 skills · 484 tokens together

AI-native scientific research pipeline. Takes a research goal — optionally with a research paper — and autonomously conducts rigorous, multi-step academic research.

not rated 9 4mo ago A tokens not measured original Apache-2.0

coinlobster

591

CoinLobster/agent-skills

Plugin Claude Code

Bundles 6 skills, 1 MCP server · 809 tokens together

Live crypto whale trades across 15 exchanges plus Ethereum/Base/Arbitrum DEX swaps, Smart Money Radar, liquidations from the venues that publish them, and market snapshots. Six analysis skills plus the hosted MCP server, no API key required.

not rated 9 +1 26d ago A tokens not measured original MIT

robium

592

robium-ai/robium

Plugin Claude Code

Bundles 70 skills, 1 agent, 6 hooks · 7,932 tokens together

Self-improving robotics expertise for AI agents: skills for architecting, integrating, simulating, visualizing, testing, and training physical-AI applications (ROS 2, Nav2, Gazebo, LeRobot, Isaac, HuggingFace) — captured from real builds, mined from the ecosystem, evidence-verified.

not rated 9 yesterday A tokens not measured original MIT

multi

593

szarkans/multi

Plugin Claude Code

Bundles 6 skills, 5 agents · 734 tokens together

Several models on the same question at once — Claude sub-agents, OpenAI Codex and a cheap third via OpenCode. Review code (code-review), check whether the work is actually finished rather than finished-looking (check-if-done), brainstorm wide with a different model per cognitive frame (adhd), or just ask all of t.

not rated 9 +1 changed today A tokens not measured original MIT

devai

594

keli-wen/dev-skills

Plugin Claude Code

Bundles 9 skills · 953 tokens together

Dev skills I use day to day in agentic engineering, focused on multi-agent-driven work modes and long-horizon autonomous tasks. Includes long-horizon, fan-out, handoff, ctx-research, ctx-grill, to-ctx, just-ask, and the lowband and readout modes.

not rated 10 15d ago A tokens not measured

agent-skills

595

SteveVitali/agent-skills

Plugin Claude Code

Bundles 8 skills · 472 tokens together

Rigorous engineering process for AI coding agents: implement-spec, decompose-spec, orchestrate-build, self-review, review-pr, address-pr-comments, agent-docs, refresh-repo-docs.

not rated 12 7d ago A tokens not measured original MIT

RonMizrahi/sdlc-graph-engineering

Plugin Claude Code

Bundles 1 skill · 202 tokens together

Installs graph engineering into a project that has none: turns an existing process — skills, a runbook, a CI config, or a description — into a guarded graph with typed nodes, total exit guards, bounded retry loops, a run-state file, a skipped-step ledger, its own auditor, and an executable eval suite. Domain-agnostic.

not rated 9 +1 17d ago A tokens not measured original MIT

humanize-pro

597

msdanyg/humanize-pro

Plugin Claude Code

Bundles 1 skill · 168 tokens together

Make AI-drafted text read like a person wrote it, for the channel it ships in. De-AI pass, channel fit, voice profiles, and a two-gate audit before delivery.

not rated 10 +2 9d ago A tokens not measured original MIT

cannonball

598

harebeats/cannonball

Plugin Claude Code

Bundles 10 skills · 1,801 tokens together

Guarda as peças de site que você já fez e as encontra de volta antes de gerar qualquer coisa do zero. O acervo é seu e começa com três peças de exemplo: templates, design systems, componentes, animações, efeitos e prompts que você ingere. Busca, monta combinando peças, decide cor e tipografia com contraste e licença…

not rated 10 changed 3d ago A tokens not measured original MIT

example-skills

599

adryanmoldokkr32-pixel/anthropics-skills

Plugin Claude Code

Bundles 12 skills · 729 tokens together

Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling.

not rated 9 3mo ago A tokens not measured

coding-loop

600

duthaho/skillhub

Plugin Claude Code

Bundles 8 skills · 1,367 tokens together

The evidence-gated coding loop: orient (map), build (feature), fix (bugfix), improve (refactor), gate (done), and run it all on one yes (autopilot).

not rated 9 today A tokens not measured original MIT