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

92%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.

A well-structured, highly actionable skill body with strong validation feedback loops and proper externalization of detail into bundle files. Minor redundancy in progress-tracking and screenshot sections keeps it just below perfect conciseness.

Suggestions

Consolidate progress.md guidance so it lives in one place rather than being restated across the workflow and the Progress Tracking section.

Dedupe screenshot-inspection instructions, which currently recur in steps 9-11 and the Test Artifacts section.

Dimension	Reasoning	Score
Conciseness	Largely efficient with concrete patterns and commands, but progress.md handling and screenshot-inspection guidance are repeated across the workflow and dedicated sections, adding redundant tokens that could be consolidated.	4 / 5
Actionability	Provides copy-paste-ready exports, a runnable example command with flags, an inline JSON action payload, and complete renderGameToText and advanceTime code patterns covering the common cases.	5 / 5
Workflow Clarity	A clear 14-step sequence with explicit validation/retry checkpoints ('Repeat until correct', 'fix the first new issue before continuing', 'rerun in a tight loop') and a test checklist with reset-between-scenarios guidance.	5 / 5
Progressive Disclosure	The body is an overview that points to two real, one-level-deep bundle files (scripts/web_game_playwright_client.js and references/action_payloads.json) via clearly signaled Scripts and References sections and inline env-var references.	5 / 5
	Total	19 / 20 Passed

Description

92%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 strong, specific description with concrete actions and an explicit trigger clause. The only gap is keyword synonym coverage for 'web game'.

Suggestions

Add natural synonyms such as 'browser game', 'HTML5 game', or 'JavaScript game' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the web-game domain and 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' — giving comprehensive coverage of the dev/test loop.	5 / 5
Completeness	Explicitly answers what (implement, run test script, inspect screenshots/text, review console errors) and when via a concrete 'Use when Codex is building or iterating on a web game' trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('building or iterating on a web game') but leans on tool jargon (Playwright, render_game_to_text) and misses common synonyms like 'browser game', 'HTML5 game', or 'JavaScript game'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — web game development with a specific Playwright-based testing loop — making it highly distinguishable and unlikely to trigger for unrelated skills.	5 / 5
	Total	19 / 20 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: 100d3f7

Reviewed: 2 days 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.