Ready to supercharge your AI agents?

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

Get Started Free →

gstack-qa-only — measured AI agent skill | DecimalAI

ling71671/gstack-qa-only

NewSkillScoreMaintained

Read-only QA report for an OPC desktop flow, CLI command, local URL, staging URL, or documented user journey. Does not modify code.

Testingby ling71671

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

Automatic

QA & Test Engineering pack

decimalai skills pull ling71671-gstack-qa-only

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/ling71671-gstack-qa-only/SKILL.md

Raw file: /s/ling71671-gstack-qa-only/SKILL.md ↗ · machine-readable summary at /s/ling71671-gstack-qa-only.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

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

No measurable change-47% tokens0% turns78% of whole cases pass with skill (18/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	-34%	0%
case-02	✗→✓	▲ Improved	-39%	0%
case-05	✗→✓	▲ Improved	-85%	0%
case-13	✗→✓	▲ Improved	-66%	0%
case-14	✗→✓	▲ Improved	-66%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

ling71671 / open-claudecode

plugins/gstack-workflows/skills/gstack-qa-only/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

Skill contents

SKILL.md

gstack-qa-only

Use this skill to test behavior and report bugs without changing files.

Workflow

Define the target flow, environment, and success criteria.
Run the app, command, or URL using the existing project workflow.
Exercise the primary path and at least two edge paths.
Capture objective evidence: command output, logs, screenshots if available, request/response details, or UI text.
Separate product bugs from setup failures.

OPC Checks

When testing OPC desktop, prefer:

npm --prefix desktop test
./script/build_and_run.sh --verify
provider bridge health and /models behavior when relevant
installed app behavior when the issue concerns /Applications/OPC.app

Output

Return a QA report:

Environment
Tested flow
Pass/fail summary
Bugs with reproduction steps
Evidence
Suggested regression coverage

Do not edit code in this workflow.

Want to see if ling71671/gstack-qa-only 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.