Skills for Real Engineers. Straight from my .agents directory.
develop-web-game
Agent skill fromfreestylefly/wesight
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.
How to install develop-web-game
npx skills add freestylefly/wesight# or add only this skill to Claude Code: copy the folder
SKILLs/develop-web-game/
# into
~/.claude/skills/develop-web-game/ (all projects)
.claude/skills/develop-web-game/ (one project)
1# Develop Web Game23Build games in small steps and validate every change. Treat each iteration as: implement → act → pause → observe → adjust.45## Skill paths (set once)67```bash8export SKILLS_ROOT="${WESIGHT_SKILLS_ROOT:-${SKILLS_ROOT:-$HOME/Library/Application Support/WeSight/SKILLs}}"9export WEB_GAME_CLIENT="$SKILLS_ROOT/develop-web-game/scripts/web_game_playwright_client.js"10export WEB_GAME_ACTIONS="$SKILLS_ROOT/develop-web-game/references/action_payloads.json"11```1213Installed skills resolve from `$WESIGHT_SKILLS_ROOT` / `$SKILLS_ROOT` (production default: app `userData/SKILLs`, macOS usually `~/Library/Application Support/WeSight/SKILLs`).1415## Workflow16171. **Pick a goal.** Define a single feature or behavior to implement.182. **Implement small.** Make the smallest change that moves the game forward.193. **Ensure integration points.** Provide a single canvas and `window.render_game_to_text` so the test loop can read state.204. **Add `window.advanceTime(ms)`.** Strongly prefer a deterministic step hook so the Playwright script can advance frames reliably; without it, automated tests can be flaky.215. **Initialize progress.md.** If `progress.md` exists, read it first and confirm the original user prompt is recorded at the top (prefix with `Original prompt:`). Also note any TODOs and suggestions left by the previous agent. If missing, create it and write `Original prompt: <prompt>` at the top before appending updates.22…
Excerpt shown under the repository's MIT license.
More skills in wesight
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
