Index of every page on this site: llms.txt
All skills
wix avatar

/rp-project-context

@e2bc48e official
by Wix.comwix/skills40 stars
42
Run it yourself

Resolve headless mode, scope, Wix project validity, and browser execution readiness.

  • 1 file
  • 3 KB
  • Updated 3 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/wix/skills/rp-project-context

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈26 tokens for metadata: the name and description. ≈723 when used: this file.

Description uses 1.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈105 characters, or 1.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Project context

Load this resource only when the run's mode, source/scope, output project, approval state, or browser environment is unresolved. It owns setup decisions, not extraction or UI work.

Read references/safety.md and the applicable mode/scope and preflight sections of references/workflow.md. Read references/output-contract.md only when validating the project or automation-state artifact.

Resolve mode and scope

  • Standalone uses the public source URL and requires home scope with no --urls.
  • Migration mode requires --handoff. Read its route families, public URL intent, Wix bindings, slug policy, websiteScope, automationMode, and frontendPhase.allowedNow. The handoff is authoritative.
  • If a handoff requests non-home or explicit-URL reconstruction, stop with the actionable requirement for the future multi-page workflow. One-click mode does not expand scope.
  • In plan phase, write/refresh plan-eligible context and evidence only; do not require a runnable frontend or attempt build/release. In build, validate the existing migration-owned project before proceeding.

Provision or validate the project

For standalone home cloning, provision or verify the exact final output directory before artifact generation or UI writes. It must be a real successful Wix CLI scaffold, not a manual fallback, and contain a valid Wix configuration plus package.json dev and build scripts. Create its empty yarn.lock project boundary up front. If the scaffold uses @wix/astro-wix-hosting-adapter, remove a direct standalone @astrojs/cloudflare dependency before install/build normalization.

For migration mode, reuse the handoff-owned project/site only. If project identity or its runnable contract fails, record the precise failure and recover it; never create a sibling scaffold.

Use clear-wix-starter.mjs after a valid template creates demo files, before clone UI work starts.

Browser preflight and recovery

Before browser extraction run:

node scripts/browser-extraction-preflight.mjs --project-root <project-root>

If needed, first attempt --fix. The host must have normal node_modules resolution, required browser/design dependencies, and Chromium; Yarn Plug'n'Play is not sufficient.

For this repository, run path-sensitive Wix/Yarn commands in interactive zsh with the repo-local NVM toolchain. In a one-click run, retry a shell/PATH mismatch once under that aligned shell. If browser launch or network access is sandbox-blocked, request the required escalation and retry. Only then record a blocker; a pending runtime approval is a real wait, not a reason to ask unrelated routine confirmations.

Write/update frontend-automation-state.json whenever the mode, phase, effective scope, scope checkpoint, or auto-progress policy changes. Return to the root supervisor once the context is durable.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at e2bc48e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 months ago

README badge

README badge for wix/skills/rp-project-context