Skill for the core infrastructure module providing logging, configuration, exception handling, progress tracking, checkpoints, retry logic, pipeline execution, performance monitoring, security, file operations, and multi-project orchestration.
SkillScore100Maintained
Automatic
◆Doc Ops pack
Last verified 8/4/2026
What it changes
Passed 23 of 23 test cases with the skill, and 3 of 23 without it.
Without skill13%
With skill100%
Checks it passed that the model alone missed
Imports log_operation from infrastructure.core.
Uses log_stage to output structured stage progress.
Imports CheckpointManager from infrastructure.core.
and 29 more in the full report
20 fixed3 passed either way0 still failing0 broke
Pass-rate lift
+87 pp
Tokens
+10%
Agent turns
0%
Response time
-57%
Model gemini-3.6-flashMeasured 8/4/2026v1 · latest is v223 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
See it in action
One of 20 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 20
Prompt
I want to display a progress bar in the terminal during manuscript rendering. Instead of importing tqdm or printing percentage strings manually, what component from the infrastructure core should be used?
What was checked, without and with the skill
Checked
Without skill
With skill
Instantiates ProgressBar from infrastructure.core to track task progress.
Missed
Passed
case-13 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md188 linessingle file
Core Infrastructure Module
Foundation utilities used across the entire infrastructure layer and all project scripts.
Logging (logging/utils.py)
from infrastructure.core import get_logger, log_operation, log_stage, format_duration
from infrastructure.core.logging.setup import setup_logger
from infrastructure.core.logging.utils import log_timing, log_substep
logger = get_logger(__name__)
logger.info("Processing started")
# log_operation is a context manager (logs start, completion, failure)
with log_operation("Processing data"):
process()
# Decorator for automatic timing and logging
@log_timing
def expensive_operation():
pass
# Structured progress logging
log_stage(1, 10, "Running Tests")
log_substep("Unit tests passed")
# ETA calculation
from infrastructure.core.runtime import calculate_eta
Configuration (config/loader.py)
from infrastructure.core.config.loader import load_config, find_config_file, get_config_as_dict
# Load project config.yaml
config = load_config(project_path / "manuscript" / "config.yaml")
# Resolve a named project config; unqualified lookup is intentionally