When Jev is defined in a Skill you can re-run something that worked before with a one-second response time.
It's a good use case when a non-deterministic task needs a lot of context and Opus can't handle it with a Python script.
Plus Opus don't waste time to define request, if it's already written as part of the Jinja Skill, it's just triggering it.
LLAJinja now supports Jev and decision models (including Ollama) in Jinja-templated Skills, without plugins or extensions, in any harness that supports Skill loading:
1
2
264
Jev + Jinja Skills turned out to be a great combination for tasks where you need simple, non-deterministic answers across many items.
You can run Jev in the middle of a Claude session and pass data without loading it into the context, saving tokens, time, and cost.
I ran some benchmarks with LLAJinja triggering Jev from Opus session 🧵:
Composing Skills:
With the power of Jinja templates, you can compose multiple Skills, or parts of Skills, together:
1
24
Jinja loops, IFs, and control flow:
You can define the Skill's execution logic as a control flow that depends on the inputs/outputs of each stage of the Skill:
1
38
Variables:
Specify the variables that need to be provided in the prompt/Skill, or the Harness will ask for any that are missing:
1
1
174
Working on a Skill that lets you run other Skills as Jinja templates. It works in any Harness/dev tool that supports Skill loading, with no extensions or plugins needed.
A few cool things you can do with it:
Example 3: applying the confusion-table inside GEPA, on KOR-Bench puzzles.
GEPA reflects on pass/fail. Prompt related contradictions are invisible to that signal, so it grows with every generation as the prompt grows.
At generation 4, I branched from the same parent and the same minibatch. GEPA's reflection pushed confusions up, while confusion-table held them flat and scored higher.
99
Example 2: @trailofbits `goal-prompt` skill, which turns a spec into a goal.
Here the confusion shows up in behavior: the model sometimes makes extra tool calls and wanders outside the working directory.
In total, 24.3 cases per run. After one rewrite iteration based on the confusion-table: 14.3, and the reasoning halved.
The model is much more reliable at focusing on writing the goal rather than handling contradictions in the skill.
1
125
Example 1: @mattpocockuk `to-spec` skill, that turns a conversation into a specification.
The skill is clear and simple, but the trace shows the model repeatedly stuck on rules like "don't interview the user" followed by "check with the user."
In total, 25.3 skill-related confusions per run. After repairing them based on the confusion-table: 13.0, and about 70% reduction in reasoning.
1
2
275







