Ready to supercharge your AI agents?

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

TestDino Audit · anthropics | DecimalAI

code reviewby anthropics

TestDino Audit

anthropics/testdino-audit

Source anthropics/claude-plugins-community ↗License Apache-2.0

Use only when the user explicitly asks for a TestDino audit of Playwright automated test code. Routes through the audit tools the TestDino MCP server exposes (get_audit_report + submit_audit_report, or the legacy test_audit). For generic code review or non-Playwright targets, do a normal review instead.

SkillScore39Maintained

Automatic

QA & Test Engineering pack

Last verified 9/28/2026

What it changes

Passed 5 of 13 test cases with the skill, and 3 of 13 without it.

Without skill22%

With skill39%

Checks it passed that the model alone missed

The assistant offers a standard chat review as an alternative.
The assistant includes a score parameter in the submission call.
The assistant offers a normal review in chat for the Cypress tests.

and 5 more in the full report

5 fixed4 passed either way13 still failing1 broke

Pass-rate lift: +17 pp
Tokens: +5%
Agent turns: 0%
Response time: -52%

Model gemini-3.6-flashMeasured 9/28/2026v19 of 23 cases passed with skill · 13 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/anthropics-testdino-audit/SKILL.md https://app.decimal.ai/s/anthropics-testdino-audit/SKILL.md

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

decimalai skills add anthropics-testdino-audit

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

curl -fsSL --create-dirs -o .claude/skills/anthropics-testdino-audit/SKILL.md https://app.decimal.ai/s/anthropics-testdino-audit/SKILL.md

Raw file: /s/anthropics-testdino-audit/SKILL.md ↗ · machine-readable summary at /s/anthropics-testdino-audit.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

Execute a TestDino audit against our Robot Framework acceptance test suite in `atest/` and submit the audit score.

What was checked, without and with the skill
Checked	Without skill	With skill
The assistant indicates that TestDino audit procedures require Playwright test targets.	Missed	Passed
The assistant offers to review the Robot Framework scripts directly in chat.	Passed	Passed

case-06 · gemini-3.6-flash · 9/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md35 linessingle file

TestDino Audit

Use the TestDino audit flow only when the user explicitly asks for a TestDino audit.

Rules:

If the user asks for a generic review or audit, do a normal review in chat.
If the user explicitly asks for a TestDino audit and the target is Playwright code, use the audit tools below.
If the user names TestDino but the target is not Playwright code, explain that the TestDino audit flow is for Playwright automated tests and offer a normal review instead.

Tool selection — use whichever audit tools the TestDino MCP server exposes:

If get_audit_report and submit_audit_report are available, prefer those (the current split tools).
If only the legacy test_audit tool is available, use it instead (it takes an action parameter).
Do not invent a tool that is not in the available tool list.

Preferred flow:

Call health if projectId is not known.
Fetch the audit context (read-only). Do not write findings, score, or headings before this returns.
- New tools: get_audit_report with action: "context".
- Legacy: test_audit with action: "analyze" and no score.
Review the local Playwright target using the returned context and write findings to a local markdown file (e.g. TEST-AUDIT.md).
Submit the completed report (score + markdown report).
- New tools: submit_audit_report.
- Legacy: test_audit with action: "analyze" plus score and markdownReport.
Browse or retrieve previously submitted audits.
- New tools: get_audit_report with action: "list" or action: "get".
- Legacy: test_audit with action: "list" or action: "get".

Important:

keep generic reviews as normal chat reviews
use the TestDino audit flow only for explicit TestDino audit requests
keep this flow centered on Playwright automated test code

Track record

Benchmark

5 / 13

test cases passed, vs 3 / 13 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

anthropics / claude-plugins-community

testdino/skills/testdino-audit/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/31/2026Version 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

TestDino Audit

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills