K-Dense-AI/scientific-agent-skills / skills/exploratory-data-analysis
exploratory-data-analysis
VerifiedPerforms bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.4 KB |
| assets/report_template.md | markdown | 7.7 KB |
| references/bioinformatics_genomics_formats.md | markdown | 8.8 KB |
| references/chemistry_molecular_formats.md | markdown | 8.5 KB |
| references/general_scientific_formats.md | markdown | 12.0 KB |
| references/microscopy_imaging_formats.md | markdown | 9.1 KB |
| references/proteomics_metabolomics_formats.md | markdown | 9.6 KB |
| references/spectroscopy_analytical_formats.md | markdown | 9.3 KB |
| scripts/__init__.py | script | 69 B |
| scripts/_capabilities.py | script | 20.2 KB |
| scripts/_common.py | script | 14.0 KB |
| scripts/_structured.py | script | 14.3 KB |
| scripts/_tabular.py | script | 32.0 KB |
| scripts/capability_manifest.py | script | 5.3 KB |
| scripts/distribution_sensitivity.py | script | 3.2 KB |
| scripts/eda_analyzer.py | script | 10.3 KB |
| scripts/image_inspector.py | script | 7.7 KB |
| scripts/missingness_leakage_audit.py | script | 3.8 KB |
| scripts/report_scaffold.py | script | 4.1 KB |
| scripts/sequence_inspector.py | script | 8.4 KB |
| scripts/tabular_profile.py | script | 3.0 KB |
scripts/distribution_sensitivity.py
View on GitHub#!/usr/bin/env python3
"""Bounded distribution, transformation, and outlier sensitivity CLI."""
from __future__ import annotations
import argparse
from _capabilities import capability_for_path
from _common import (
DEFAULT_MAX_FILE_BYTES,
DEFAULT_MAX_ROWS,
bounded_file_limit,
checked_input_file,
emit_json,
run_cli,
)
from _tabular import audit_distributions
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(
description=(
"Compare classical and robust summaries on bounded CSV/TSV data. "
"The command never deletes, winsorizes, transforms, or imputes source data."
)
)
parser.add_argument("input", help="Local .csv or .tsv path inside --root")
parser.add_argument(
"--root",
default=".",
help="Existing local directory that bounds all input/output paths",
)
parser.add_argument(
"--max-bytes",
type=int,
default=DEFAULT_MAX_FILE_BYTES,
help=f"Maximum input bytes (hard ceiling: {512 * 1024 * 1024})",
)
parser.add_argument(
"--max-rows",
type=int,
default=DEFAULT_MAX_ROWS,
help="Maximum rows to scan (hard ceiling: 1000000)",
)
parser.add_argument(
"--column",
action="append",
help=(
"Exact numeric column identifier; repeat as needed. Without this flag, "
"the first 64 columns are screened."
),
)
parser.add_argument(
"--missing-token",
action="append",
help="Explicit additional missing code; repeat as needed",
)
parser.add_argument(
"--reveal-identifiers",
action="store_true",
help="Emit sanitized column identifiers; values remain redacted",
)
parser.add_argument("--output", help="Optional local .json output path")
parser.add_argument(
"--force",
action="store_true",
help="Allow replacement of an existing regular output file",
)
return parser
def _main() -> None:
args = build_parser().parse_args()
max_bytes = bounded_file_limit(args.max_bytes)
path = checked_input_file(
args.input,
root=args.root,
suffixes={".csv", ".tsv"},
max_bytes=max_bytes,
)
report = {
"schema_version": "1.1",
"capability": capability_for_path(path),
"analysis": audit_distributions(
path,
columns=args.column,
max_rows=args.max_rows,
missing_tokens=args.missing_token,
reveal_identifiers=args.reveal_identifiers,
),
"security": {
"local_only": True,
"file_text_is_untrusted_data": True,
"embedded_instructions_followed": False,
"raw_values_and_paths_emitted": False,
},
"decisions": {
"automatic_outlier_deletion": False,
"automatic_transformation": False,
"automatic_imputation": False,
"hypothesis_tests_run": 0,
},
}
emit_json(
report,
output=args.output,
root=args.root,
force=args.force,
)
def main() -> int:
return run_cli(_main)
if __name__ == "__main__":
raise SystemExit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 463k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 463k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 463k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |