Install
$ agentstack add skill-ejjcc-agent-skills-install-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Skill Installation Guide
When a user asks to install a skill (e.g., sends a link, mentions a skill name, or says "install xxx skill"), follow this process:
1. Identify the Package Name
Parse the user's input to extract the owner/repo or owner/repo@skill format:
| Input Format | Example | Extract As | |---|---|---| | skills.sh URL | https://skills.sh/s/owner/repo | owner/repo | | skills.sh skill URL | https://skills.sh/s/owner/repo/skill-name | owner/repo@skill-name | | GitHub URL | https://github.com/owner/repo | owner/repo | | GitHub tree URL | https://github.com/owner/repo/tree/main/skills/name | owner/repo@name | | Direct package | owner/repo | owner/repo | | Package with skill | owner/repo@skill | owner/repo@skill |
2. Install the Skill
SSOT Principle
~/.claude/skills/ is the single source of truth for all skills. Other agents (Codex, Cursor, etc.) use symlinks pointing to it. Always ensure skills are installed to ~/.claude/skills/.
Call the install_skill MCP tool with the extracted package name:
install_skill({ "package": "owner/repo" })
Or with a specific skill from the repo:
install_skill({ "package": "owner/repo@skill-name" })
Post-install: Symlink to other agents
After installation, create symlinks for other agents that share skills:
ln -s ~/.claude/skills/ ~/.codex/skills/
3. Handle Results
On success:
- Tell the user which skill(s) were installed (use the
installedarray from the response) - Briefly describe what the skill does (if you know from context)
- Mention they can manage it in the Skills page
- Offer to symlink to other agents (e.g., Codex) if applicable
On failure:
- Check if the package name format is correct
- Suggest the user verify the URL or package name
- Common issues:
- Package not found: double-check the owner/repo spelling
- Network error: ask user to retry
- Invalid format: must be
owner/repoorowner/repo@skill
4. Uninstalling
If the user wants to uninstall a skill, use the uninstall_skill MCP tool:
uninstall_skill({ "skill_id": "skill-name" })
The skill_id is the directory name of the installed skill.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ejjcc
- Source: ejjcc/agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.