Index of every page on this site: llms.txt
All skills
Run it yourself

Write, review, run, and repair Meadow E2E specifications. Use for scenario authoring, editorial and structural reviews, claim-to-evidence analysis, page-object abstraction, and E2E validation.

  • 3 files
  • 28.8 KB
  • Updated 3 weeks ago
  • GitHub
Use this Skill: https://skilld.dev/gh/sandharbor/meadow/e2e

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈49 tokens for metadata: the name and description. ≈806 when used: this file. ≈6.5k more on demand in 2 files.

Description uses 2.5% 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 ≈198 characters, or 2.5%.

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.

Meadow E2E Specifications

Use this skill for E2E authoring, review, and execution. Choose the work from the request; a review-only task does not require a suite run. The caller supplies test selection and batch size. An /e2e invocation without an authoring or review request uses run mode.

Write or change a scenario

Before implementing, read the live enforced-rule reference from the repository root:

NODE_OPTIONS="${NODE_OPTIONS:-} --preserve-symlinks" \
  app/acceptance/e2e/node_modules/.bin/tsx \
  app/acceptance/e2e/_module/scripts/rule-reference.ts

Use --list for rule IDs or pass IDs for focused lookup. The TypeScript rule definitions supply both this reference and lint failure guidance. Quickcheck runs their displayed valid and invalid examples through the real validators and checks that every lint is documented and registered at its stated enforcement level. This is a live view, with no generated document to refresh.

Read Specification quality, including the linked coding standards and canonical concept-authoring conventions. Design from the appropriate shared fixture, write intent-level sections using workflows and page objects, and make the title, description, sections, and checkpoints tell an accurate causal story. Keep storage paths, raw file access, and JSON/YAML parsing in reusable domain utilities or page classes; use the documented, reasoned e2e-allow-raw-data exception only when raw access is essential to the claim. Apply the same editorial rubric used in review.

Run the selected-spec concept-link audit, then required quickcheck. For new scenarios, scenario splits, or executable changes, follow Running and diagnosing for E2E validation. Preserve coverage when splitting and surface the affected scenarios' review artifacts.

Review or copy edit selected scenarios

Read Specification quality. Run the mechanical audit on the selected files, then review narrative, concept-link relevance, claim-to-evidence support, section granularity, and cohesion. Allow multiple claims with closer cohesion scrutiny. Give a structural verdict first. If keeping the structure, provide full replacement copy; if recommending a split or material regrouping, settle that proposal with the user before drafting copy. Honor any structure already agreed. Include a claim-to-evidence mapping and distinguish behavior-preserving edits from coverage or restructuring recommendations. In review-only mode, leave the tests unchanged.

When an external editor is requested, give it this skill, the quality reference, and raw selected tests and relevant canonical definitions. Verify its actual findings against assertions and helpers. Use concrete examples and user feedback to refine the shared rubric. Keep pilot selection outside the skill.

Run or repair the suite

Read Running and diagnosing and follow its runner, artifact, and failure-repair guidance. Apply the quality reference to test changes made during repairs. Use the caller's runner when one is already established. Follow the enclosing checkout's required validation instructions after changes.

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 62fef7a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 weeks ago.

Activeupdated 3 weeks ago

README badge

README badge for sandharbor/meadow/e2e