Ready to supercharge your AI agents?

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

Auto Tester — measured AI agent skill | DecimalAI

stijnman/auto-tester

SkillScore73Maintained

Runs validation tests on code, skills, or outputs after changes. Use after i mplementations or when user says run tests, auto test, validate changes. Tri ggers: run tests, auto test, validate changes. Use when the user needs this capability.

by stijnman

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

Automatic

QA & Test Engineering pack

decimalai skills pull stijnman-auto-tester

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-auto-tester/SKILL.md

Raw file: /s/stijnman-auto-tester/SKILL.md ↗ · machine-readable summary at /s/stijnman-auto-tester.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 7d ago

—-37% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-11	✗→✓	▲ Improved	-46%	0%
case-05	✗→✓	▲ Improved	305%	0%
case-09	✗→✓	▲ Improved	-65%	0%
case-10	✗→✓	▲ Improved	-30%	0%
case-13	✗→✓	▲ Improved	-64%	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 — 8/1/2026

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

stijnman / grok-custom-skills

.grok/skills/auto-tester/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Auto Tester

When to Use

User says run tests or task matches this capability
User says auto test or task matches this capability
User says validate changes or task matches this capability
User says check tests or task matches this capability

Workflow

Detect project type (Python, Node, skill-only).
Run appropriate test command (pytest, npm test, or skill checklist).
Parse results; classify pass/fail/flaky.
On fail: invoke self-healing-error-recovery or report with fix hints.

Integrations

goal-verifier
self-healing-error-recovery
hyper-skill-tester

Error Handling

| Failure | Response | |---------|----------| | No test suite | Run smoke checks: import, lint, dry-run. |

Gotchas

Never skip tests before marking goal-verifier complete.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/auto-tester 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.