testdino-audit — Claude Code skill: TestDino audit for Playwright
Runs a TestDino audit over Playwright test code through the TestDino MCP server and saves the findings as a markdown report. Only fires on an explicit request.
MIT ★ 4,931 updated 2026-10-24
/plugin marketplace add anthropics/claude-plugins-community
/plugin install testdino@claude-communityWhat testdino-audit does
The skill activates when someone explicitly asks for a TestDino audit. It then calls whatever tools the TestDino MCP server exposes: get_audit_report and submit_audit_report on current setups, or the older test_audit with an action argument. A tool that isn't in the available list won't be invented.
The flow: call health when projectId is unknown, pull the audit context read-only, review the local Playwright code, write findings into a markdown file such as TEST-AUDIT.md, submit the score and the report, then browse earlier audits with action: "list" or action: "get".
Scope is automated Playwright tests. Ask for a TestDino audit on some other code and the skill says so and offers a plain review in chat. Nothing runs without the TestDino MCP server connected, because the audit tools come from it.
What it helps with
- run a TestDino audit over Playwright specs and get a score
- write findings to a markdown report before submitting
- fetch audit context from TestDino when
projectIdis unknown - browse reports submitted earlier for a project
- keep a generic code review separate from a TestDino audit
Example prompts for the agent
- Run a TestDino audit on the Playwright specs in
tests/e2eand save the findings toTEST-AUDIT.md - Fetch the audit context, then submit the report with a score
- List the TestDino audits already submitted for this project
How to install testdino-audit
1Plugin marketplace
/plugin marketplace add anthropics/claude-plugins-community/plugin install testdino@claude-communityThis installs the whole testdino plugin with all its skills
2Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-community --skill testdino-audit -a claude-code3Manually: put the files in place
~/.claude/skills/testdino-audit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/testdino-audit/
1Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-community --skill testdino-audit -a codex2Manually: put the files in place
.agents/skills/testdino-audit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-community --skill testdino-audit -a cursor2Manually: put the files in place
.cursor/skills/testdino-audit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install anthropics/claude-plugins-community testdino/skills/testdino-audit2Manually: put the files in place
.github/skills/testdino-audit/SKILL.md1Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-community --skill testdino-audit -a gemini-cli2Platform CLI
gemini skills install https://github.com/anthropics/claude-plugins-community --path testdino/skills/testdino-auditManually: put the files in place
.devin/skills/testdino-audit/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about testdino-audit
How to install testdino-audit in Claude Code?
Use the marketplace: first /plugin marketplace add anthropics/claude-plugins-community, then /plugin install testdino@claude-community.
What does testdino-audit do?
It routes an explicit TestDino audit request to the MCP server tools, reviews the local Playwright tests, and submits a score with a markdown report.
What does the skill need to work?
A connected TestDino MCP server with the audit tools. If projectId is unknown, the skill calls health first.
Source text
SKILL.md · MIT
--- name: testdino-audit description: 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. --- # 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: 1. Call `health` if `projectId` is not known. 2. 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`. 3. Review the local Playwright target using the returned context and write findings to a local markdown file (e.g. `TEST-AUDIT.md`). 4. Submit the completed report (score + markdown report). - New tools: `submit_audit_report`. - Legacy: `test_audit` with `action: "analyze"` plus `score` and `markdownReport`. 5. 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
© TestDino · MIT · anthropics/claude-plugins-community