Learn — Find & Install Skills
ListedDiscover, install, and manage AI agent skills from agentskill.sh. Search for capabilities mid-session, install extensions, and scan for security issues.
Install on your platform
Showing OpenClaw.
- 1
Run this in your terminal
terminal$ openclaw skills install learn
What we know about this skill
Publisher
agentskill-sh
Taken from the source listing. We haven't verified who controls this account.
Install target
Pinned to 3d9ae7be
Installs fetch a stored snapshot of that commit, so the code can't change after the fact.
Automated safety checks
This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.
No pipe-to-shell installers: failed
Runs code fetched at install time in 1 place.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
What it found
- skills/learn/SKILL.md:341tells the user to run: npm install straight from a URL(in the instructions, not code)
| CLI not available / npx fails | "Installing ags..." and retry once. If still fails: "Could not run ags. Try `npm install -g @agentskill.sh/cli` or browse htt…
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
Pinned to a commit: passed
Scanned agentskill-sh/learn at ede92fd8fc.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- ede92fd8fc
- Manifest
- skills/learn/SKILL.md
- Scanned
- 2 files, 945 lines
About this skill
What it does
The learn skill allows an AI agent to discover and install relevant skills from a registry of over 100,000 skills. It analyzes the current project context and suggests appropriate skills for integration. This process helps agents expand their capabilities without manual searching or risk of malicious code through vetted skill installations.
When to use it
- When you want your AI agent to automatically identify useful tools and functionalities for a specific project.
- To quickly broaden an agent's skillset beyond its initial configuration.
- After setting up the
agentskill.shCLI, to populate your agent with relevant skills. - To ensure that newly added skills have been vetted for security vulnerabilities before installation.
Key capabilities
- Skill discovery from a large registry (100,000+ skills).
- Project context analysis for skill recommendations.
- Security scoring of skills based on static analysis (0-100).
- Client-side confirmation required for low-scoring skills.
Example prompts
/learn- Initiates the skill discovery process./learn suggest– Requests a list of suggested skills for the current project./learn install <skill_slug>- Installs a specific skill by its slug (e.g.,/learn install python).
Tips & gotchas
- Requires installation of the
@agentskill.sh/clitool vianpmor through a plugin marketplace (Claude Code). - Skills scoring below 30 require explicit confirmation before installation due to potential security risks.