Use when a Hermes agent needs to evaluate agent behavior, run Autocontext scenarios, inspect Hermes curator state, export reusable knowledge, or prepare local MLX/CUDA training data through the autoctx CLI.
SkillScore73Maintained
Automatic
◆AI Engineer pack
Last verified 8/17/2026
What it changes
Passed 14 of 19 test cases with the skill, and 5 of 19 without it.
Without skill27%
With skill73%
Checks it passed that the model alone missed
Executes autoctx simulate with --runs 3.
Executes autoctx solve with --iterations 5.
Sets max_rounds to 4 in autocontext_improve.
and 9 more in the full report
10 fixed6 passed either way6 still failing0 broke
Pass-rate lift
+45 pp
Tokens
-5%
Agent turns
0%
Response time
-51%
Model gemini-3.6-flashMeasured 8/17/2026v416 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
I am working on an algorithm problem from the command line using the autoctx CLI tool. I want it to run a strategy search loop for 5 iterations on the problem 'optimize matrix multiplication'. What CLI command should I execute?
What was checked, without and with the skill
Checked
Without skill
With skill
Executes autoctx solve with --iterations 5.
Missed
Passed
case-16 · gemini-3.6-flash · 8/17/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md98 linessingle file
autocontext
autocontext is an iterative strategy generation and evaluation system that uses
LLM-based judging to score and improve agent outputs.
Available Tools
autocontext_judge — Evaluate agent output against a rubric. Returns a 0–1
score with reasoning and per-dimension breakdowns.
autocontext_improve — Run a multi-round improvement loop. The agent output
is judged, revised based on feedback, and re-evaluated until the quality
threshold is met or max rounds are exhausted.
autocontext_queue — Enqueue a task for background evaluation by the task
runner daemon.
autocontext_status — Check the status of runs and queued tasks.
autocontext_scenarios — List available evaluation scenarios and their
families.
autocontext_runtime_snapshot — Inspect run artifacts, package provenance,
branchable session lineage, and recent event-stream entries.
Quick Start
1. Evaluate output quality
Use autocontext_judge with a task prompt, the agent's output, and a rubric:
autocontext_judge(
task_prompt="Write a Python function to parse CSV files",
agent_output="def parse_csv(path): ...",
rubric="Correctness, error handling, edge cases, documentation"
)
2. Improve output iteratively
Use autocontext_improve to automatically revise output through
judge-guided feedback loops: