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

Customer-safe runtime helper contract used by Segmently Launch Assistant browser SHOW and E2E DO plans. Also trigger when Segmently Launch Assistant returns executeWith.companionSkill=segmently-test-kit, a SHOW focus/screenshot plan, or an E2E browser verification contract.

  • 4 files
  • 6.6 KB
  • Updated 5 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/segmently-ai/segmently-support-plugins/segmently-test-kit

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈74 tokens for metadata: the name and description. ≈571 when used: this file. ≈1.1k more on demand in 3 files.

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 ≈295 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.

Segmently Test Kit

Use this skill only as the runtime companion named by Segmently Launch Assistant SHOW and E2E DO contracts. It is not a general testing framework for the customer to call directly.

When To Use

  • A segmently-launch-guide SHOW result names segmently-test-kit as the companion for browser navigation, focus, or screenshot evidence.
  • A segmently-launch-guide E2E DO result names segmently-test-kit as the companion for a generated browser driver.
  • The customer asks why browser setup, auth preflight, or verification is needed before a SHOW or E2E DO action can run.

Runtime Contract

Read references/runtime-contract.md before acting on a generated browser contract. The source of truth for the concrete action remains the JSON returned by segmently-launch-guide runners.

The helper contract is intentionally narrow:

  • Use the published segmently CLI from PATH for auth and verification reads.
  • Use playwright-bowser for observable browser control.
  • Keep SHOW read-only.
  • Run E2E DO only when the launch-guide action contract, required target ids, browser auth, and explicit execute approval are all present.
  • Never ask the customer for raw tokens, refresh tokens, service credentials, or direct database access.
  • Never require a Segmently source checkout, project build, maintainer command, hidden endpoint, or local-only helper.

Required Inputs

For SHOW, the generated contract normally needs a project, funnel, screen, and a browser base URL or editor URL. If session project context is present, do not ask for the project again; state which saved project is being used and ask only for the missing target inputs.

For E2E DO, require the action value plus every target id listed in the launch-guide contract. Do not infer a missing screen, funnel, or version from nearby prose when the runner says it is still missing.

Preflight

Follow references/browser-preflight.md before live browser work. Missing CLI auth or browser tooling is a recoverable preparation step, not a final failure.

Verification

Follow references/verification-contract.md. A mutation is complete only after the generated action executes and the named read-back verification succeeds. Dry-run output is a plan, not completion.

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 third-party reports yet.

Signed by skilld at f3f9f19. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 5 months ago

README badge

README badge for segmently-ai/segmently-support-plugins/segmently-test-kit