Use before claiming that the package can be installed or published. Verifies structure, adapters, schemas, executable scripts, and public-safety boundaries.
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Resolve ENGINE using /hep-build Step 0 and set PACKAGE_ROOT to the
generated agent repository. Run:
bash "$ENGINE/scripts/verify-generated-package.sh" "$PACKAGE_ROOT"
bash "$ENGINE/scripts/verify-team-package.sh" "$PACKAGE_ROOT"
(cd "$PACKAGE_ROOT" && bash "$ENGINE/scripts/public_safety_check.sh")Then inspect the generated package's selected adapters and install files:
AGENTS.md, CLAUDE.md, GEMINI.md;.agents/;.agentlas/;.claude/;codex/;scripts/install.sh.Do not claim completion if any required file is missing.
agentlas-ai/Agentlas-OS
e68fc35
Also appears in
since Aug 20, 2026
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.