Ready to supercharge your AI agents?

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

Python Scratchpad · openbmb | DecimalAI

codingby openbmb

Python Scratchpad

openbmb/python-scratchpad

Source openbmb/chatdev ↗License Apache-2.0

Use the existing Python execution tools as a scratchpad for calculations, data transformation, and quick script-based validation.

NewMaintained

Automatic

Coding pack

Last verified 9/27/2026

What it changes

Passed 2 of 11 test cases with the skill, and 9 of 11 without it.

Without skill86%

With skill14%

Checks it passed that the model alone missed

Identifies references/examples.md as the reference file path.

1 fixed3 passed either way2 still failing18 broke

Pass-rate lift: -71 pp
Tokens: -1%
Agent turns: 0%
Response time: +1%

Model gemini-3.6-flashMeasured 9/27/2026v14 of 24 cases passed with skill · 11 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/openbmb-python-scratchpad/SKILL.md https://app.decimal.ai/s/openbmb-python-scratchpad/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add openbmb-python-scratchpad, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/openbmb-python-scratchpad/ and pins it in .decimal/skills.lock

decimalai skills add openbmb-python-scratchpad

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/openbmb-python-scratchpad/SKILL.md https://app.decimal.ai/s/openbmb-python-scratchpad/SKILL.md

Raw file: /s/openbmb-python-scratchpad/SKILL.md ↗ · machine-readable summary at /s/openbmb-python-scratchpad.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

Where in the reference documentation for the scratchpad workflow should an agent look if it needs concrete usage examples for constructing short Python scripts? Name the exact file path referenced in the workflow.

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies references/examples.md as the reference file path.	Missed	Passed

case-15 · gemini-3.6-flash · 9/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md31 lines2 files

Python Scratchpad

Use this skill when the task benefits from a short Python script instead of pure reasoning.

This skill is especially useful for:

arithmetic and unit conversions
validating regexes or parsing logic
transforming JSON, CSV, or small text payloads
checking assumptions with a small reproducible script

Requirements:

The agent should have access to execute_code.

Workflow:

If the task needs computation or a repeatable transformation, activate this skill.
If you need examples, call read_skill_file for references/examples.md.
Write a short Python script for the exact task.
Prefer execute_code.
Use the script output in the final answer.
Keep scripts small and task-specific.

Rules:

Prefer standard library Python.
Print only the values you need.
Do not invent outputs without running the script.
If execute_code is not available, say exactly: No Python execution tool is configured for this agent.
Do not claim there is a generic execution-environment problem unless a tool call actually returned such an error.

Expected behavior:

Explain the result briefly after using the script.
Include the computed value or transformed output in the final answer.

Track record

Benchmark

2 / 11

test cases passed, vs 9 / 11 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/31/2026

View 15 scanner checks

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

openbmb / chatdev

.agents/skills/python-scratchpad/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/31/2026Version v1Bundled 1 file

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Python Scratchpad

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills