Personally reviewed agent skills

Install better workflows into Claude, Codex, and every agent.

Find a vetted SKILL.md, inspect the source, watch the demo when one exists, then install the exact workflow your next session needs.

Browse skills Submit a skill

install shortcut

reviewed

curl --create-dirs -fsSL skillmake.xyz/i/<name> -o ~/.claude/skills/<name>/SKILL.md

 ____  _    _ _ _                 _
/ ___|| | _(_) | |_ __ ___   __ _| | _____
\___ \| |/ / | | | '_ \` _ \ / _\` | |/ / _ \
 ___) |   <| | | | | | | | | (_| |   <  __/
|____/|_|\_\_|_|_|_| |_| |_|\__,_|_|\_\___|

Prompt Packs

Copy-paste prompt grammar for Nano Banana and other generative models.

MCPs

Agent-callable tools for browsers, APIs, SaaS, and custom workflows.

Budget

Spend less, keep context cleaner, and keep agent sessions pointed.

Submit

Send a skill through review so builders can inspect and install it.

security

Before installing any skill, scan it with SkillSpector— NVIDIA's open-source security scanner for agent skills. A skill gets file, network, and environment access on install, so run it through a security check first. Learn more →

all creators engineers devops design marketing security PMs job search trending budget mcps productivity packs loopscreative·soon

4 security

⌕

#namesourceproof

skill-auditorengineerssecurity

Use when reviewing a SKILL.md before installation or publication — audit triggering, structure, safety, evidence, freshness, context cost, and testability, then propose bounded fixes.

github.com

anthropics/skills

install★ 161k

skillspectorengineerssecurityOfficial

Use when vetting an AI agent skill before installing it, to scan the SKILL.md and its code for prompt injection, data exfiltration, and other malicious or vulnerable patterns.

github.com

NVIDIA/SkillSpector

install★ 7.5k

one-passwordengineerssecurity

Use when working with 1Password/op: service-account first, targeted secret read/store/inject, tmux from steipete/agent-scripts.

github.com

steipete/agent-scripts

install★ 5.0k

openclaw-secure-linux-cloudengineerssecurity

Use when an agent needs to run shell commands on a remote Linux host or ephemeral cloud sandbox with least-privilege defaults, audit logging, and an explicit destructive-action gate.

github.com

xixu-me/skills

install★ 65

Think SKILL.md for the rest of the agent stack — by hand, not by scrape.