Index of every page on this site: llms.txt
All skills
n8n-io avatar

/experiments

@273d130 official
by n8n - Workflow Automationn8n-io/n8n211k stars
61,599
Run it yourself

Guides work on `packages/frontend/editor-ui` experiments. Use when creating, extending, wiring, testing, reviewing, or retiring editor-ui experiments, PostHog feature flags, experiment key indexes, variants, stores/composables, persisted experiment state, or experiment telemetry.

Use this Skill: https://skilld.dev/gh/n8n-io/n8n/experiments

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈73 tokens for metadata: the name and description. ≈185 when used: this file. ≈2.4k more on demand in 1 file.

Description uses 3.7% 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 ≈298 characters, or 3.7%.

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.

Experiments

Use this skill for frontend experiment code lifecycle work in packages/frontend/editor-ui.

Start with the relevant mode in reference.md:

  • Create for a new experiment folder, constant, store/composable, and tests.
  • Extend for new variants, behavior, display logic, or telemetry on an existing experiment.
  • Wire for host-surface integration through routes, modals, views, or components.
  • Test for store, composable, persistence, telemetry, and UI behavior coverage.
  • Review for auditing experiment changes.
  • Retire for cleaning up completed or abandoned experiments.

When experiment work touches Vue components or user-facing copy, also follow n8n:ui-design and n8n:content-design.

Source: SKILL.md on GitHub

No rule matched.

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 alerts6mo3 checks · Risk SAFE
  • Gen Agent Trust Hub6mo

    This skill provides instructions for managing frontend experiments and PostHog feature flags within the n8n-io project. It follows standard development practices and does not exhibit malicious behavior or security risks.

  • Socket6mo

    No alerts

  • Snyk6mo

    Risk: LOW · No issues

Signed by skilld at 273d130. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
  • Frontend
  • Vue
  • n8n
  • experiments
  • feature-flags
  • posthog
  • editor-ui
  • telemetry
  • ab-testing

README badge

README badge for n8n-io/n8n/experiments

Manages the lifecycle of A/B experiments in n8n's editor-ui frontend, including experiment setup, variant wiring, state persistence, PostHog integration, and telemetry. Use this skill when creating, extending, testing, or retiring experiments in the `packages/frontend/editor-ui` codebase.

Generated from the current SKILL.md.

What part of n8n does this skill cover?
This skill guides work on frontend experiments in the `packages/frontend/editor-ui` directory, including experiment setup, PostHog feature flags, variants, stores, composables, persistence, and telemetry.
Does this skill cover experiment retirement and cleanup?
Yes. The skill includes a `Retire` mode for cleaning up completed or abandoned experiments from the codebase.
What other skills should I load alongside this one?
If your experiment work touches Vue components or user-facing copy, also load `n8n:design-system` and `n8n:content-design`.
What are the main workflow modes this skill provides?
The skill covers six modes: Create (new experiments), Extend (variants and behavior), Wire (host-surface integration), Test (coverage), Review (audit changes), and Retire (cleanup).

Generated from the current SKILL.md. These answers refresh after source changes.