Menu
Fetch a campaign from the Supabase DB and save as local JSON. Use when the user asks to load, download, or fetch a campaign from the database.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Take a set of local feature branches/worktrees all the way to merged PRs — discover unmerged work, fix commit-time hygiene, push, raise PRs, watch CI, auto-fix mechanical failures, merge on green, and cascade-rebase the rest. Use when the user says "shepherd PRs" or wants several branches driven to merge autonomously.
Read BEFORE invoking `playwright test` in any form, for any reason — running e2e, visual regression, room snapshots, or verifying a change 'via e2e'. Covers required project scoping (chromium-desktop, matching CI), the sandbox browser-build bridge, and the pnpm webServer failure. Also load on these failure signatures: every test failing at browserType.launch, 'Executable doesn't exist at /opt/pw-browsers/...', or 'Process from config.webServer was not able to start'.
Run the true-site-size GitHub Action locally via `act` inside the Claude Code web sandbox, to measure the game/editor cold-load journey byte cost without a CI round-trip. Use when asked to measure or verify build/wire size, or to check a byte-saving change, in the sandbox.
Drive the Head over Heels remake's UI via the chrome-devtools MCP. Use this skill when the user asks for browser automation, capturing localStorage, dispatching game actions, or anything that involves driving the running game on localhost.
Run Docker — and tools that need it, like `act` (local GitHub Actions) — inside the Claude Code web sandbox, where image pulls and in-container networking collide with the egress proxy. Use when `docker pull` returns 403 on image layers, when a container can't reach the network, or when running `act`/CI-in-docker locally (e.g. the `act-true-site-size.sh` script).
Edit the BlockStack spritesheet — its IFF source of truth, image layout and cell grid, palette and two-tone colour rules, the iff→webp conversion pipeline, and how to hand-edit in DPaint/pyDPainter or bake webp-only art back into the IFF. Use when adding or changing sprites, fixing sprite art, or reconciling the IFF and webp.
| name | fetch-campaign |
| description | Fetch a campaign from the Supabase DB and save as local JSON. Use when the user asks to load, download, or fetch a campaign from the database. |
eval "$(fnm env)" && fnm use && pnpm --silent exec tsx scripts/fetchCampaign.ts <campaignName> [userId]
The default user ID is 2924c962-99f1-4dd2-9b9c-fef832dc991b (Jim's account). Pass a different user ID as the second argument if needed.
Output is pure JSON on stdout — redirect to a file or pipe to jq. The --silent is required: without it, pnpm's cold-start reporter prints a banner to stdout that corrupts the JSON. It must come before exec (pnpm exec --silent is parsed as a command and fails).
Sequel campaigns are named sequel_XX where XX is the release number. To know the number, read src/gameInfo.ts or see where it is loaded from in the
select which game menu to start a new game on the sequel campaign.
# fetch Jim's campaign to a file (replace XX with the next release)
pnpm --silent exec tsx scripts/fetchCampaign.ts sequel_XX > /tmp/sequel_XX.json
# fetch another user's campaign
pnpm --silent exec tsx scripts/fetchCampaign.ts my_campaign abc123-def456 > /tmp/my_campaign.json
# pipe to jq to inspect a specific room (replace XX with the next release)
pnpm --silent exec tsx scripts/fetchCampaign.ts sequel_XX | jq '.rooms["head_homers_jump"].meta.subRooms'
The script calls the get_latest_campaign Supabase RPC, which returns a gzip+base64 encoded blob. It decodes with js-base64 and node:zlib gunzip, then prints the parsed JSON to stdout.