Install
$ agentstack add skill-krastanov-juliallmagentskills-julia-jet ✓ 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
JET.jl
Use this skill for all JET work. Keep the overview here and load the narrow reference that matches the task.
Warning
Use JET only on the latest stable Julia release. Nightly and pre-release Julia versions often break JET because it depends on compiler internals.
Environment Rule
- Prefer package-integrated JET runs via
Pkg.test(...; test_args=["jet"])or
the package's documented JET arguments.
- Keep JET as a test-only dependency in
test/Project.tomlwith root
[workspace] projects = ["test"]; avoid new [extras]/[targets] entries.
- Avoid direct
test/runtests.jlexecution unless you are debugging the test
router or worker behavior.
- Set
JULIA_PKG_SERVER_REGISTRY_PREFERENCE=eageror
ENV["JULIA_PKG_SERVER_REGISTRY_PREFERENCE"] = "eager" before Pkg operations in this workspace.
- Never read or edit
Manifest.tomldirectly. If a JET failure appears after
dependency churn, run Pkg.update() and Pkg.resolve() in the relevant package and JET environments first. If recurrent issues remain, delete the relevant Manifest.toml file and regenerate it with Pkg.instantiate() before blaming the analyzed code.
Choose a Mode
- Start with
@report_optto find runtime dispatch and captured variables. - Then use
@report_callorreport_packageto find type-level errors.
Quick Start
using JET
@report_opt sum(Any[1, 2, 3])
@report_call sum("julia")
using MyPackage
report_package(MyPackage; target_modules=[MyPackage])
report_file("my_script.jl")
Filtering
@report_opt target_modules=(MyPackage,) my_function(args...)
Read JET stack traces from the bottom up: the bottom frame is the actual problem site.
References
references/config.mdreferences/testing.mdreferences/error-kinds.mdreferences/fixing-dispatch.md
Related Skills
julia-perf- performance work after dispatch cleanupjulia-tests- test-suite integration patterns
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Krastanov
- Source: Krastanov/JuliaLLMAgentSkills
- License: Unlicense
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.