Install
$ agentstack add skill-lingbol088-spec-auto-skill-installer-auto-skill-installer ✓ 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
Auto Skill Installer
Use this skill when the current task exposes a capability gap and another skill is likely the right fix.
Workflow
- Summarize the missing capability in one short phrase.
- Search local and remote sources with
scripts/auto_install.py search --need "". - Prefer an already-installed or system skill when it is a strong match.
- Install the best remote match with
scripts/auto_install.py ensure --need "". - Validate the installed skill, then continue the user task and mention what was installed.
Search Strategy
- Start with concrete task language, not generic words. Prefer
github review commentsovergithub. - If the first search is noisy, run a second search with two or three sharper keywords.
- Prefer skills whose
descriptionexplicitly matches the task and trigger context. - If several candidates are close, read the strongest candidates'
SKILL.mdfiles before choosing.
Read [references/source-format.md](references/source-format.md) when you need to add or debug a registry source.
Commands
python scripts/auto_install.py search --need "github pull request review comments"
python scripts/auto_install.py ensure --need "figma design generation"
python scripts/auto_install.py add-source --repo your-org/skills --path skills --name your-org
python scripts/auto_install.py list-sources
Decision Rules
- Install automatically when one candidate is clearly better than the rest.
- Pause and tell the user when multiple candidates have different tradeoffs and no clear winner.
- Do not overwrite an existing destination skill directory.
- Treat user-configured sources as higher priority than broad fallback registries.
- After installation, tell the user that restarting or reloading the target agent may be required for automatic discovery.
Safety
- Use
$CODEX_HOME/skillsas the default Codex destination; use--destwhen another agent runtime needs a different skills directory. - Only install directories that contain
SKILL.md. - Reject archive paths that escape the temporary extraction root.
- If a network source fails, explain the failure briefly and continue with remaining sources.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: lingbol088-spec
- Source: lingbol088-spec/auto-skill-installer
- 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.