123,917 listed
Skills
Skills are folders with a SKILL.md file that an agent loads when a task needs it. These come from public GitHub repositories, with copy commands for Claude Code, Codex and other Agent Skills hosts.
Showing 97–120 of 18,866
- 0.844score
article-illustration-planner
yang0
深度分析文章脉络,精准规划插图点位与视觉意象。对知识类/教程类文章默认启动“认知降负与高保真图替繁文机制”,严禁删除公式与量化指标,强制协同 170 种排版图型(IG-*信息图/SC-*社媒卡)与 365 种视觉风格/36…
SkillAFreshness: A★ 6.2KClaude Code +9 - 0.844score
couple-photo-orchestrator
yang0
Orchestrates professional portrait, couple, wedding, family, cosplay, and themed photography planning from direction selection through Look, scene…
SkillAFreshness: A★ 6.2KClaude Code +9 - 0.844score
cpu-reduction
nubjs
Diagnose and clear CPU, memory, and disk contention on the maintainer's dev host.
SkillAFreshness: A★ 4.4KClaude Code +9 - 0.844score
disk-reduction
nubjs
Reclaim disk on the maintainer's Mac when the volume is full or filling — ENOSPC, "no space left on device", a failed build or agent harness, or a routine…
SkillAFreshness: A★ 4.4KClaude Code +9 - 0.843score
codex-first
steipete
Claude Code work routing: delegate hands-on work to Codex under the native-Claude model gate.
SkillAFreshness: A★ 7.4KClaude Code +9 - 0.843score
fleet-maintenance
steipete
Mac fleet inventory and upkeep with full/worker profiles: collect installed apps and packages, compare desired versus observed state, audit local-account…
SkillAFreshness: A★ 7.4KClaude Code +9 - 0.843score
visual-review
nubjs
Verify UI/layout/styling changes are correct by computing occlusion, clipping, and alignment from the browser's resolved paint order via the chrome-devtools…
SkillAFreshness: A★ 4.4KClaude Code +9 - 0.843score
agents-build
aws-agentcoreOfficial
Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource…
SkillAFreshness: A★ 3KClaude Code +9 - 0.842score
ambient-healthcare-agent-with-nemotron-voice-agent
Jin Li <jinl@nvidia.com>
Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows…
SkillAFreshness: A★ 3.7KClaude Code - 0.842score
holoscan-setup
Holoscan Team <holoscan-team@nvidia.com>
Assess a host and choose a Holoscan SDK 5.x installation method using release availability, CUDA 13 compatibility, and component needs.
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.842score
isaac-humanoid-cloud-control
yuzho <yuzho@nvidia.com>
Run streamed Unitree G1 cloud-navigation demos in Isaac Sim with guarded gantry release.
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.842score
eas-workflows
expo
Helps understand and write EAS workflow YAML files for Expo projects.
SkillAFreshness: A★ 3KClaude Code +9 - 0.842score
expo-ui
expo
Build native UI with the @expo/ui package: real SwiftUI on iOS and Jetpack Compose on Android.
SkillAFreshness: A★ 3KClaude Code +9 - 0.842score
browse
garrytan
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors.
SkillAFreshness: A★ 137.5KClaude Code +9 - 0.842score
setup-ts-deep-modules
vinvcn
在 TypeScript repo 中接入 dependency-cruiser,让每个 package 成为 deep module:implementation 隐藏在 subfolders 中,只能通过 entry-point files 访问。User-invoked。
SkillAFreshness: A★ 5.2KClaude Code +9 - 0.842score
wizard
vinvcn
生成一个交互式 bash wizard,逐步引导人完成只有他们能执行的手动流程。用于 provisioning 基础设施、设置 credentials 或 CI secrets、走查不熟悉的第三方 dashboard,或运行一次性 migration 或 cutover。对于 agent…
SkillAFreshness: A★ 5.2KClaude Code +9 - 0.841score
codonfm-finetune
NVIDIA BioNeMo <bionemofeedback@nvidia.com>
Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning.
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.841score
complexa-sweep
Ohad Mosafi <omosafi@nvidia.com>
Agent runbook for Proteina-Complexa parameter sweeps through the separately installed first-party CLI and config generator.
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.841score
isaac-mission-control-showcase
NVIDIA Isaac Team <info@nvidia.com>
Run and validate an end-to-end Mission Control showcase with a locally installed Isaac Sim launched in its GUI window, driven through the isaac-sim-remote…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.841score
aig-agent-redteam
Tencent Zhuque LabOfficial
当用户要求 AI/Agent 安全评估、蓝军演习、AI 安全审查、提示词注入测试、MCP/Skill/插件/代码包审计、Agent 工具链滥用测试,或需要生成类似渗透测试报告的 Markdown/HTML 时,必须使用本 skill。本 skill 让 Agent 以授权蓝军视角成为 AI 安全专家,面向 AI…
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.840score
project-structure
steipete
Generate a single-file compressed symbol map of a TypeScript or Swift repository — files, exported symbols, typed signatures, plugin boundaries — sized to fit…
SkillAFreshness: A★ 7.4KClaude Code +9 - 0.840score
cuopt-server-api-python
NVIDIA cuOpt Team
cuOpt REST server — start server, endpoints, Python/curl client examples.
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.840score
turnstile-spin
cloudflareOfficial
Set up, repair, or migrate to Cloudflare Turnstile bot verification in an existing frontend and backend, including server-side Siteverify.
SkillAFreshness: A★ 3.2KClaude Code +9 - 0.839score
handdraw-style-prompter
yang0
Turn a 001–366 hand-drawn and realistic style number and image theme into bilingual prompts, using model capability data to decide when core traits and a…
SkillAFreshness: A★ 6.2KClaude Code +9
Popular comparisons
- git-guardrails-claude-code vs ai-coding-agent-guardrails
- skill-creator vs skill-creator
- bmad-eval vs agent-evals
- playwright-validation vs playwright-cli
- e2e-cucumber-playwright vs playwright-cli
- obsidian-markdown vs lark-markdown
- protected-vercel-deployments vs vercel-optimize
- vercel-optimize vs vercel-sandbox