Ready to supercharge your AI agents?

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

Get Started Free →

Safe refactor · juliusbrussee | DecimalAI

codingby juliusbrussee

Safe refactor

juliusbrussee/safe-refactor

Source juliusbrussee/caveman ↗License NOASSERTION

Restructure code while preserving behavior.

SkillScore100Maintained

Automatic

Coding pack

Last verified 9/4/2026

What it changes

Passed 22 of 22 test cases with the skill, and 19 of 22 without it.

Without skill86%

With skill100%

Checks it passed that the model alone missed

Recommends preserving existing exception handling during refactoring.
Recommends running the same verification tests after structural edits are completed.
Recommends against introducing unnecessary new configuration parameters during a pure refactor.

3 fixed19 passed either way0 still failing0 broke

Pass-rate lift: +14 pp
Tokens: -28%
Agent turns: 0%
Response time: -20%

Model gemini-3.6-flashMeasured 9/4/2026v122 of 22 cases passed with skill

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/juliusbrussee-safe-refactor/SKILL.md https://app.decimal.ai/s/juliusbrussee-safe-refactor/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add juliusbrussee-safe-refactor, 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/juliusbrussee-safe-refactor/ and pins it in .decimal/skills.lock

decimalai skills add juliusbrussee-safe-refactor

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

curl -fsSL --create-dirs -o .claude/skills/juliusbrussee-safe-refactor/SKILL.md https://app.decimal.ai/s/juliusbrussee-safe-refactor/SKILL.md

Raw file: /s/juliusbrussee-safe-refactor/SKILL.md ↗ · machine-readable summary at /s/juliusbrussee-safe-refactor.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

An engineer working on C++ `EngineMath` library wants to begin structural edits immediately and only write or run unit tests after all code modifications are complete. Provide advice on when verification should be established and run.

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends running verification tests prior to making structural edits.	Passed	Passed
Recommends running the same verification tests after structural edits are completed.	Missed	Passed

case-06 · gemini-3.6-flash · 9/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md11 linessingle file

Safe refactor

Define behavior-preservation boundary and establish verification before structural edits.

Keep feature changes outside refactor.
Move one ownership boundary at a time.
Preserve public interfaces, failure behavior, ordering, and compatibility unless explicitly scoped.
Keep intermediate states buildable and testable.
Avoid dependency or configuration growth without correctness need.

Run same proof after change. Stop when behavior matches and requested structure is achieved.

Track record

Benchmark

22 / 22

test cases passed, vs 19 / 22 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 — 8/15/2026

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

juliusbrussee / caveman

skills/safe-refactor/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/15/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

Safe refactor

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills