Ready to supercharge your AI agents?

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

Kdlbs/Qa | DecimalAI

testingby kdlbs

Kdlbs/Qa

kdlbs/qa

Source kdlbs/kandev ↗License AGPL-3.0

Verify a feature works after implementation. Actively try to break it — edge cases, error paths, integration wiring, and real usage flows.

NewMaintained

Automatic

QA & Test Engineering pack

Last verified 8/19/2026

What it changes

Passed 1 of 8 test cases with the skill, and 3 of 8 without it.

Without skill32%

With skill18%

Checks it passed that the model alone missed

Maps external integration points and data flows.
Identifies happy path user flow and system boundaries.

1 fixed3 passed either way14 still failing4 broke

Pass-rate lift: -14 pp
Tokens: +36%
Agent turns: 0%
Response time: -11%

Model gemini-3.6-flashMeasured 8/19/2026v14 of 22 cases passed with skill · 8 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/kdlbs-qa/SKILL.md https://app.decimal.ai/s/kdlbs-qa/SKILL.md

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

decimalai skills add kdlbs-qa

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

Run an adversarial QA pass on PR #310 which adds passwordless login via magic links. Start by establishing system expectations.

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies happy path user flow and system boundaries.	Missed	Passed
Maps external integration points and data flows.	Missed	Passed

case-13 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md140 linessingle file

QA

Planner Entry

Run /qa only when the user explicitly requests adversarial validation or an actionable PR/CI finding needs it. Do not add QA as a pre-PR quality gate: task-defined tests and the two PR AI reviewers are the default evidence.

Verify that a feature works as intended after implementation. Assume bugs exist and hunt for them.

Mindset: you are not confirming it works — you are discovering where it breaks.

Available skills

/tdd — Use when unit or integration coverage is missing.
/e2e — Use when a user-facing flow lacks browser coverage.

Before starting: create the pipeline

Create these tasks immediately (use your task/todo tracking tool if available):

Understand the intent — Read task/PR/commits to understand what was built
Trace the wiring — Verify the feature is actually connected end-to-end
Test the happy path — Run the feature as a user would
Try to break it — Boundary values, error paths, concurrency, auth
Verify test coverage — Check for missing tests and report gaps
Report — Summarize findings with verdict

Mark each task in_progress when you begin it and completed when you finish it.

Phase 1: Understand the intent

Mark task 1 as in_progress.

Read the task description, PR, or recent commits to understand what was built and what it should do. Identify:

The expected behavior (happy path)

Track record

Benchmark

1 / 8

test cases passed, vs 3 / 8 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

kdlbs / kandev

.agents/skills/qa/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.