Ready to supercharge your AI agents?

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

Get Started Free →

Verify Changes · pubkey | DecimalAI

testingby pubkey

Verify Changes

pubkey/verify

Source pubkey/rxdb ↗License Apache-2.0

Verifies code changes by running tests and generation scripts

SkillScore88Maintained

Automatic

QA & Test Engineering pack

Last verified 9/27/2026

What it changes

Passed 20 of 23 test cases with the skill, and 6 of 23 without it.

Without skill25%

With skill88%

Checks it passed that the model alone missed

Identifies npm run lint as optional
Notes that npm run lint is optional
Mentions npm run lint as an optional step

and 12 more in the full report

15 fixed6 passed either way3 still failing0 broke

Pass-rate lift: +63 pp
Tokens: -68%
Agent turns: 0%
Response time: -64%

Model gemini-3.6-flashMeasured 9/27/2026v121 of 24 cases passed with skill · 23 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/pubkey-verify/SKILL.md https://app.decimal.ai/s/pubkey-verify/SKILL.md

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

decimalai skills add pubkey-verify

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

curl -fsSL --create-dirs -o .claude/skills/pubkey-verify/SKILL.md https://app.decimal.ai/s/pubkey-verify/SKILL.md

Raw file: /s/pubkey-verify/SKILL.md ↗ · machine-readable summary at /s/pubkey-verify.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 15

Prompt

I updated the utility module in our JavaScript codebase. Should I execute standard npm test or is there a dedicated fast memory test script for verifying core functionality?

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends running npm run test:fast:memory	Missed	Passed

case-06 · 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.md17 lines2 filesincludes scripts

Verify Changes

This skill verifies that recent code changes are correct and do not break existing functionality.

Steps

Run the fast memory tests to ensure core functionality is working.
```
npm run test:fast:memory
```
(Optional) Run linting to check for style issues.
```
npm run lint
```

Track record

Benchmark

20 / 23

test cases passed, vs 6 / 23 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

pubkey / rxdb

.agent/skills/verify/SKILL.md

View on GitHub ↗

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

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

Verify Changes

Steps

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills