Ready to supercharge your AI agents?

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

Quality Verify Skill · aiskillstore | DecimalAI

testingby aiskillstore

Quality Verify Skill

aiskillstore/quality-verify

Source aiskillstore/marketplace ↗License Not recorded

Verify the final deliverable meets all quality criteria before delivery. Use as the final validation step to ensure the output meets the user's quality standards across all 6 dimensions.

SkillScore77Maintained

Automatic

QA & Test Engineering pack

Last verified 8/22/2026

What it changes

Passed 17 of 22 test cases with the skill, and 5 of 22 without it.

Without skill23%

With skill77%

Checks it passed that the model alone missed

The readyToDeliver flag is false
The final qualityScore calculates to 80
The final calculated qualityScore is 75

and 26 more in the full report

15 fixed2 passed either way2 still failing3 broke

Pass-rate lift: +55 pp
Tokens: +48%
Agent turns: 0%
Response time: -37%

Model gemini-3.6-flashMeasured 8/22/2026v117 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/aiskillstore-quality-verify/SKILL.md https://app.decimal.ai/s/aiskillstore-quality-verify/SKILL.md

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

decimalai skills add aiskillstore-quality-verify

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

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

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

A microservice deployment script has a dimension base average of 85 and contains 2 major issues (missing error logging section and inconsistent environment variable naming). What is the calculated final score?

What was checked, without and with the skill
Checked	Without skill	With skill
Each major issue incurs a deduction of 5 points	Missed	Passed
The final calculated qualityScore is 75	Missed	Passed

case-08 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md194 linessingle file

Quality Verify Skill

Purpose

Final validation that the formatted deliverable meets ALL quality standards before delivery. This is the last gate - if it passes here, it's ready to go.

Quality Dimensions

The system checks against 6 quality dimensions. Evaluate each:

1. Completeness

Does the deliverable have all required parts?
Nothing missing or obviously incomplete?
All requirements from the user met?

2. Correctness

Is the code syntactically correct? (No errors)
Are facts/information accurate?
Does it do what was asked?
No logical errors?

3. Consistency

Formatting consistent throughout?
Naming conventions consistent?
Style consistent?
Patterns applied consistently?

4. Performance (when applicable)

Is it efficient? (Code shouldn't be obviously slow)
Does it scale? (For large inputs/data)
Any obvious performance issues?

5. Security (when applicable)

No obvious vulnerabilities?
Inputs validated/sanitized?
No hardcoded secrets?
Following security best practices?

6. Maintainability

Is it readable?

Track record

Benchmark

17 / 22

test cases passed, vs 5 / 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 v4 — 8/3/2026

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

aiskillstore / marketplace

skills/abejitsu/quality-verify/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

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

Quality Verify Skill

Purpose

Quality Dimensions

1. Completeness

2. Correctness

3. Consistency

4. Performance (when applicable)

5. Security (when applicable)

6. Maintainability

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills