Skills / Category
Agent building
177 skills
Showing 25–48 of 177
- 0.699score
google-cloud-solution-multi-agent-security
googleOfficial
Designs, deploys, and secures Google Cloud Agent Gateway solutions.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.695score
local-ai-app-integration
amd
Integrates local AI capabilities into applications using Embeddable Lemonade.
SkillAFreshness: A★ 465Claude Code +9 - 0.691score
citation-crosscheck
wanshuiyin
Conditionally double-blind bibliographic cross-check (double-blind only when the host can isolate the web agent; a flag-only heuristic when isolation can't be…
SkillAFreshness: A★ 18KClaude Code - 0.691score
citation-crosscheck
wanshuiyin
Double-blind bibliographic cross-check: one agent extracts each cited entry verbatim from the local .bib, a second independently re-fetches the same paper's…
SkillAFreshness: A★ 18KClaude Code - 0.678score
taskmarket-delegate
aeonfun
Delegate work to the TaskMarket agent-worker market - browse open tasks, create tasks with explicit authorization, and track/submit work, so an agent can…
SkillBFreshness: B★ 782Claude Code +9 - 0.674score
deobfuscating-javascript-malware
adriannoes
Deobfuscates malicious JavaScript code used in web-based attacks, phishing pages, and dropper scripts by reversing encoding layers, eval chains, string…
SkillAFreshness: A★ 72Claude Code +9 - 0.674score
skill-security-auditor
adriannoes
Security audit and vulnerability scanner for AI agent skills before installation.
SkillAFreshness: A★ 72Claude Code +9 - 0.669score
skillguard
profbernardoj
Security scanner for AgentSkill packages.
SkillCFreshness: C★ 110Claude Code +9 - 0.668score
auditing-mcp-servers-for-tool-poisoning
adriannoes
Scan Model Context Protocol servers and tool metadata for poisoning, SSRF, and unauthenticated exposure.
SkillAFreshness: A★ 72Claude Code +9 - 0.659score
dspy-ruby
gvkhosla
Build type-safe LLM applications with DSPy.rb — Ruby's programmatic prompt framework with signatures, modules, agents, and optimization.
SkillAFreshness: A★ 51Claude Code +9 - 0.657score
kiln
elithril
Makes and fixes 3D assets in Blender, for games, the web and AR.
SkillAFreshness: A★ 57Claude Code - 0.655score
helius-dflow
Helius Labs
Build Solana trading applications combining DFlow trading APIs with Helius infrastructure.
SkillAFreshness: A★ 29Claude Code +9 - 0.654score
agent-platform-inference
googleOfficial
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama…
SkillBFreshness: B★ 21.5KClaude Code +9 - 0.652score
grok-imagine
remorses
Generate images on grok.com/imagine with the signed-in Grok session.
SkillAFreshness: A★ 44Claude Code +9 - 0.647score
create-canvas-app
jongio
Build a GitHub Copilot App canvas extension the right way, fast.
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
b3os-team-inbox
b3rys
the team lead AI Team 6 agent 가 message bus 와 대화하는 도구.
SkillAFreshness: A★ 14Claude Code +9 - 0.640score
deepseek-codex-subagent
Zedong-Liu
Delegate bounded side tasks to a DeepSeek-backed Codex CLI subagent through the official DeepSeek API, persistent sessions, and an interactive Terminal monitor.
SkillAFreshness: A★ 25Claude Code +9 - 0.638score
chengfeng-videocut-skills:剪口播
Pluviobyte
口播基础素材包生成。转录口播、识别口误、生成审核页;用户确认后剪出新视频,Agent 再基于剪后视频重新转写、AI 校对字幕,输出后续口播成片可用的 source_cut.mp4 和 subtitles.srt。触发词:剪口播、处理口播素材、准备口播素材、识别口误、基础素材包
SkillBFreshness: B★ 1.7KClaude Code +9 - 0.636score
m0
coco-research
Use when the user says 'm0', 'm0 status', 'start m0', 'cross-tool memory', 'operational thread', or 'where is my memory stored', or when the M0 daemon or MCP…
SkillAFreshness: A★ 784Claude Code +9 - 0.636score
openai-agents
coco-research
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming.
SkillAFreshness: A★ 784Claude Code +9 - 0.634score
nano-banana-pro-openrouter
mouadja02
Generate or edit images via OpenRouter with the Gemini 3 Pro Image model.
SkillAFreshness: A★ 11Claude Code +9 - 0.633score
checkup
agentvitals
Give your AI agent a professional health checkup (AgentVitals).
SkillBFreshness: B★ 95Claude Code +9 - 0.632score
suede-agent-teams
JasonColapietro
Suede AI agent-team orchestrator, the method behind multi-agent automation: split complex work into coordinated lanes with explicit file ownership, WIP…
SkillAFreshness: A★ 125Claude Code +9 - 0.631score
browser-trace
vanducng
Capture a full DevTools-protocol trace of a locally driven browser automation - CDP firehose, screenshots, and DOM dumps - then bisect the stream into…
SkillAFreshness: A★ 8Claude Code +9