Install
$ agentstack add skill-stark-ai-de-agent-skills-skill-installation-support ✓ 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.
About
Skill Installation Support
Goal
Help users install, list, update, remove, and troubleshoot Agent Skills with clear commands and safe distinctions between local, global, and agent-specific installation.
When to use
- The user asks how to install a skills repo or one skill.
npx skills@latest addfails or does not discover expected skills.- The user asks about Codex, Claude Code, Cursor, or all-agent installation targets.
When not to use
- The user wants to create or review a skill; use
skill-authoring-review. - The user wants to maintain this repository's catalog or release state; use
skill-repo-curator. - The source skill has unclear provenance or license and should not be installed yet.
Inputs
- Repository path or GitHub owner/repo.
- Desired skill name, target agent, and global or project install preference.
- Error output from
npx skills@latest. - Local
skills/tree andSKILL.mdfrontmatter when troubleshooting discovery.
Inputs to inspect
- Inspect the source path or repository, requested skill name, target agent, global/project scope, and CLI error output.
- Check
SKILL.mdnames and descriptions when discovery fails.
Process
- Identify source: local folder, GitHub repo, full Git URL, or specific skill.
- List skills before installing when the source is unfamiliar.
- Choose global or project install based on the user's scope.
- Choose target agent flag based on the user's runtime.
- Troubleshoot discovery by checking folder structure,
SKILL.md, name matching, and CLI output. - Avoid global installation or overwrites without user approval.
Workflow
Follow the process above, then return a copy-pasteable command plus a verification command before suggesting any global install.
Decision points
- Use
--listbefore installation for unfamiliar repos. - Use
--skillwhen installing one skill from a multi-skill repo. - Use
--allonly when the user wants all supported agents. - Prefer local folder install for testing unpublished repos.
Safety rules
- Tell users to review public skills before installing them.
- Do not install globally unless the user requested or approved it.
- Do not run commands that overwrite existing local skills without approval.
References
Read references/vercel-skills-cli.md when the user needs command examples or troubleshooting steps.
Scripts
No bundled scripts.
Output format
Return:
- Recommended command
- What it installs
- Scope and target agent
- Verification command
- Troubleshooting notes
Failure modes
- If the CLI is unavailable, give the install prerequisite and a no-op discovery check.
- If the skill name is not found, list available skills from the source.
- If global installation is risky, recommend project-local installation first.
Completion criteria
- The user has an exact command for their source and target agent.
- Safety and scope are explicit.
- Discovery or installation failure has a concrete next diagnostic step.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: stark-ai-de
- Source: stark-ai-de/agent-skills
- License: Apache-2.0
- Homepage: https://stark-ai-de.github.io/agent-skills/
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.