develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

A well-structured, actionable skill body with a strong sequenced workflow and good progressive disclosure via verified bundle references. Its main weakness is verbosity from duplicated guidance and repeated screenshot-inspection prose.

Suggestions

Consolidate the progress.md guidance: keep the operational steps in the workflow and trim the redundant standalone Progress Tracking section to a brief pointer.

Tighten the Test Artifacts to Review section by merging the two screenshot-inspection passages and removing motivational filler like 'broken games are not acceptable' to reduce token cost.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable patterns and concrete commands, but padded in places — progress.md guidance is duplicated (workflow step 5 and a full Progress Tracking section) and the screenshot-inspection instruction is repeated verbosely with motivational filler like 'broken games are not acceptable'.	2 / 3
Actionability	Provides copy-paste-ready executable patterns (renderGameToText, advanceTime), a concrete example node command, real script/reference paths, and inline JSON action examples — fully actionable.	3 / 3
Workflow Clarity	A clearly sequenced multi-step workflow with explicit validation/feedback loops ('Repeat until correct', 'fix the first new error before continuing', rerun loops), matching the anchor for clear sequences with checkpoints.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing one level deep to verified bundle files ($WEB_GAME_CLIENT and $WEB_GAME_ACTIONS), with clearly signaled References/Scripts sections and well-organized headers — easy to navigate.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 strong, specific description with an explicit trigger clause and concrete capabilities. It clearly conveys both what the skill does and when to invoke it, with minimal fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (build/iterate web game via a Playwright test loop, inspect, review errors) and when via an explicit 'Use when Codex is building or iterating on a web game...' trigger clause.	3 / 3
Trigger Term Quality	Natural terms a user would say are present — 'web game (HTML/JS)', 'iterating on a web game', 'development + testing loop' — giving good coverage, though 'Codex' is slightly jargon-laden.	3 / 3
Distinctiveness Conflict Risk	The 'web game (HTML/JS)' niche combined with a Playwright-based testing loop is a clear, distinct trigger unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: netease-youdao/LobsterAI
Path: SKILLs/develop-web-game/SKILL.md
Commit: 2921c1e

Reviewed: about 11 hours ago

Table of Contents

Discovery Implementation Validation

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.