Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →docxology/infrastructure-autoresearch
Skill for deterministic AutoResearch readiness planning.
Passed 17 of 21 test cases with the skill, and 6 of 21 without it.
and 13 more in the full report
13 fixed5 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
In our custom reporting utility, we need to extract the physical or benchmark unit (e.g., ms, bytes) from a metric name string. Which helper function should we import from infrastructure.autoresearch?
| Checked | Without skill | With skill |
|---|---|---|
| Uses metric_unit_from_name to extract measurement units. | Missed | Passed |
| Imports helper utilities directly from the infrastructure.autoresearch package. | Passed | Passed |
The instructions your model reads when the skill loads.
Use this module for deterministic planning and readiness validation. It adapts reviewed AutoResearchClaw design ideas as file-backed template controls, not as an autonomous research agent.
AutoResearch CLI-style measurement ideas are treated the same way: adopt exact metric extraction, review-status vocabulary, baseline/noise/confidence disclosure, and append-only evidence discipline; do not add lifecycle hooks, git commit/revert ownership, or no-human autonomous loops by default.
uv run python -m infrastructure.autoresearch.cli validate --project templates/template_code_project --fail-on-issues
from infrastructure.autoresearch import (
AutoResearchConfig,
AutoResearchIssue,
AutoResearchPlan,
AutoResearchReport,
mad_confidence,
metric_unit_from_name,
build_autoresearch_plan,
load_autoresearch_config,
parse_metric_lines,
parse_string_sequence,
validate_autoresearch_plan,
write_autoresearch_report,
)
validate_autoresearch_plan(..., phase="intrinsic"|"extrinsic"|"all") splits
pre-write structure checks from post-write artifact checks.
test cases passed, vs 6 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.