Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Document Environment Snapshot — measured AI agent skill | DecimalAI

brycewang-stanford/env-snapshot

SkillScore77Maintained

Captures tool versions, packages, and kernel info as a reproducibility record in notes/. Use when documenting the environment.

by brycewang-stanford

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

decimalai skills pull brycewang-stanford-env-snapshot

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/brycewang-stanford-env-snapshot/SKILL.md

Raw file: /s/brycewang-stanford-env-snapshot/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-env-snapshot.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6h ago

—+2% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	-9%	0%
case-04	✗→✓	▲ Improved	103%	0%
case-07	✗→✓	▲ Improved	-2%	0%
case-08	✗→✓	▲ Improved	200%	0%
case-12	✗→✓	▲ Improved	-60%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / Auto-Empirical-Research-Skills

skills/29-quarcs-lab-project20XXy/dot-claude/skills/env-snapshot/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1

Skill contents

SKILL.md

Document Environment Snapshot

Capture the full environment state and save it as a reproducibility record.

Steps

Gather system and tool versions:

bash uname -a # OS info quarto --version # Quarto uv --version # uv python3 --version # Python

Capture Python package versions:

bash uv pip list # all installed packages with versions

Capture Jupyter kernel list:

bash uv run jupyter kernelspec list

If R is available, capture R session info:

bash R -e "sessionInfo()"

If Stata is available, note the version:

bash which stata # or check nbstata.conf for edition info Read ~/.config/nbstata/nbstata.conf for stata_dir and edition.

If TeX Live is available:

bash pdflatex --version | head -1

Generate a timestamped Markdown file with all collected information:

markdown # Environment Snapshot — YYYY-MM-DD

## System

OS: ...
Platform: ...

## Tools | Tool | Version | | ---- | ------- | | Quarto | x.x.x | | uv | x.x.x | | Python | 3.12.x | | R | x.x.x (or N/A) | | Stata | SE x.x (or N/A) | | TeX Live | xxxx (or N/A) |

## Jupyter Kernels

python3: /path/to/kernel
ir: /path/to/kernel (or N/A)
nbstata: /path/to/kernel (or N/A)

## Python Packages | Package | Version | | ------- | ------- | | numpy | x.x.x | | pandas | x.x.x | | ... | ... |

## R Session Info (full sessionInfo() output, or "R not available")

## Stata Packages (ado dir output, or "Stata not available")

Save to notes/environment-YYYYMMDD.md (using today's date).

Report the file path.

Want to see if brycewang-stanford/env-snapshot would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.