arrow_backAI Skill ShieldpublicDefault-branch GitHub scan
Trust report
multica-ai/andrej-karpathy-skills
/skills/karpathy-guidelines
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
View scanned commit on GitHubopen_in_new0%Static score
89% score11% score gap
Highest finding: Medium severityLatest scan
medium severity
Static analysis score
Install decision
Safe to Review
No blocking install signals were found. Review the report, then proceed with normal caution.
Scan identity
- Scanned
- 2026-08-29
- Commit
- 2c606141936f
- License
- Not detected
- Repository
- Active
Repository scan summary
- policyFindings
- 5
- terminalInstall surface
- 0
- Repository reach
- 208,517
Validation findings detected
Execution paths reviewed
GitHub stars
Highest-priority findings
The latest default-branch scan, ordered by severity.
- mediumping to external hostskills/karpathy-guidelines/SKILL.md:9
- mediumNo agent compatibility detectedSKILL.md
- lowMissing version informationSKILL.md
- infoModerate readabilitySKILL.md
- infoFew code examplesSKILL.md
Share this trust result
The badge stays linked to the latest default-branch scan for this skill path.
Do you consider this skill safe to use?
Community signals help prioritize human review; they do not change the scan verdict.
AI Skill Shield is an automated pre-install review, not a guarantee of safety. Confirm sensitive permissions and execution paths before installation.