CtrlK
BlogDocsLog inGet started
Tessl Logo

game-playtest

Run browser-game playtests and frontend QA. Use when the user asks for smoke tests, screenshot-based verification, browser automation, HUD or overlay review, or structured issue-finding in a browser game.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a well-structured, lean QA playbook with a clear workflow and concrete tool/check guidance. The main gap is that the referenced detail files are not present in the bundle to verify the progressive-disclosure split.

Suggestions

Add an explicit validation/verification checkpoint in the Preferred Workflow between capturing screenshots and reporting (e.g. re-run failing checks or confirm reproduction) to support a feedback loop.

Ensure the referenced files exist in the bundle or convert the inline 3D/Common checklists into the referenced playtest-checklist.md so the progressive-disclosure split is verifiable.

Tighten the 3D checks list by moving the long tail of edge-case bullets into the external checklist to reduce the body's token footprint.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — bullet lists of concrete checks with no padding or concept explanations — but the volume of check bullets (especially the 3D list) could be trimmed or deferred to the referenced checklist, so it sits just below the every-token-earns-its-place anchor 5.

4 / 5

Actionability

It names specific tools (Playwright, SpectorJS) and concrete checks ("screenshots are mandatory because DOM assertions alone miss visual regressions"), giving mostly actionable guidance; as an instruction-only QA skill it has no code, but the named tools and explicit checks keep it above the pseudocode/abstract anchor 3.

4 / 5

Workflow Clarity

The Preferred Workflow is a clear five-step sequence (Boot → Exercise verbs → Capture screenshots → Check UI layer independently → Report) with an explicit checkpoint ("confirm the first actionable screen"); a second validation checkpoint between capture and report would lift it to 5, so it is one step below.

4 / 5

Progressive Disclosure

Sections are well organized and the References block signals one-level-deep pointers clearly, matching the good-structure anchor; it stays at 4 rather than 5 because the referenced paths (e.g. ../../references/playtest-checklist.md, ../web-game-foundations/SKILL.md) do not resolve within the provided bundle, so the split cannot be verified.

4 / 5

Total

16

/

20

Passed

Description

87%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.

The description cleanly answers both what the skill does and when to use it, with natural trigger terms and a distinct browser-game niche. The only minor gap is that the 'what' is expressed as two high-level verbs rather than an enumerated action set.

DimensionReasoningScore

Specificity

"Run browser-game playtests and frontend QA" names the domain plus multiple concrete actions (playtests, frontend QA); coverage is strong but the 'what' clause is compressed into two verbs rather than an enumerated action list, so it falls just below the comprehensive anchor 5.

4 / 5

Completeness

It explicitly states both the what ("Run browser-game playtests and frontend QA") and the when ("Use when the user asks for smoke tests, screenshot-based verification..."), with concrete trigger phrases, matching the anchor that requires both clearly and explicitly.

5 / 5

Trigger Term Quality

Natural user-facing terms are well represented ("smoke tests", "screenshot-based verification", "browser automation", "HUD or overlay review", "structured issue-finding"), matching the good-coverage anchor; a few common synonyms (e.g. "playthrough", "regression test") are absent, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

"browser-game playtests" and "in a browser game" carve a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the minimal-conflict-risk anchor.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.