CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qa-scout

Browser QA of a PR against a running Twenty app, post-merge on main or pre-merge via the qa-scout label. Derives user-visible scenarios from the PR diff, executes them with the Playwright MCP browser, attests database effects over SQL, watches server and worker logs for swallowed errors, and writes a structured verdict plus a report. Invoked by ci-e2e-main.yaml after the deterministic e2e suite; also runnable locally against a dev stack.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary single-file skill body: dense, executable, and sequenced with validation checkpoints and fail-fast rules throughout. Every section earns its tokens, and the verdict contract removes ambiguity about outputs and stopping conditions.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: an inputs table, exact commands, and a verdict lifecycle with no explanations of concepts Claude already knows. The opening searchVector anecdote is project-specific motivation that defines the failure class, not padding.

5 / 5

Actionability

Guidance is copy-paste ready throughout: 'psql -h localhost -U postgres -d default', 'tail -n +<offset+1>', the exact login click-path ('Continue with Email' to the Apple workspace), a full verdict.json template, and a screenshot naming pattern ('03-note-timeline-missing.png').

5 / 5

Workflow Clarity

Six clearly numbered steps with explicit validation checkpoints (mark log offsets before touching the app, fail fast if the app does not boot, confirm Timeline after every write, re-read the log window after each scenario) and a feedback loop (rewrite both output files after each scenario; in-progress to final lifecycle with fail-fast rules for early stops).

5 / 5

Progressive Disclosure

No bundle files exist and nothing inlined belongs in a separate file — the verdict template, login flow, and hard rules are all runtime-critical. Clear single-level sections (Inputs, Procedure, Verdict contract, Hard rules, Running locally) make navigation easy.

5 / 5

Total

20

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, third-person description that comprehensively names concrete capabilities and pins down a distinct niche. Its only weakness is that the when-guidance is expressed as CI invocation mechanics rather than natural user-language trigger phrases, and a few common synonyms (test, regression) are missing.

Suggestions

Add a 'Use when...' clause in user language (e.g., 'Use when asked to QA or regression-test a PR against a running Twenty stack') alongside the CI invocation details.

Include natural trigger synonyms such as 'test the PR', 'smoke test', or 'regression check' so the description matches how a user would phrase the request.

DimensionReasoningScore

Specificity

Lists five distinct concrete actions in third person ('Derives user-visible scenarios from the PR diff, executes them with the Playwright MCP browser, attests database effects over SQL, watches server and worker logs for swallowed errors, and writes a structured verdict plus a report'), covering the full scope-execute-attest-observe-report loop comprehensively.

5 / 5

Completeness

The 'what' is explicit and the 'when' is concretely stated ('post-merge on main or pre-merge via the qa-scout label', 'Invoked by ci-e2e-main.yaml after the deterministic e2e suite; also runnable locally'), but the trigger guidance is CI-mechanism language rather than a natural 'Use when...' user-language trigger phrase.

4 / 5

Trigger Term Quality

Good natural keyword coverage for the domain ('Browser QA', 'PR', 'e2e', 'server and worker logs', 'post-merge', 'pre-merge', 'dev stack'), but common user phrasings like 'test the PR', 'regression', or 'smoke test' are absent.

4 / 5

Distinctiveness Conflict Risk

A clear niche ('running Twenty app', 'Playwright MCP browser', 'qa-scout label', 'ci-e2e-main.yaml') with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

twentyhq/twenty

Path

.claude/skills/qa-scout/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.