skilld
All skills
segmently-ai avatar

/segmently-launch-guide

@330af37
by segmently-aisegmently-ai/segmently-support-plugins1 stars

Use this orchestration skill when a customer wants to launch or publish a Segmently web funnel, connect Stripe/Facebook/TikTok/analytics, create paywall products, ask what's left, change a setting, get article/screenshot guidance, or SHOW/DO a supported editor task. It selects evidence and offers TEACH, SHOW, CLI DO, E2E DO, or handoff. It is not the CLI/browser execution owner; for DO delegate to executeWith.skill/owningSkill companion such as segmently-cli-guide, segmently-cli-paywall-ab-rollout, segmently-cli-custom-screen-guide, segmently-cli-image-upload, segmently-cli-articles, playwright-bowser, segmently-test-kit, or claude-design.

  • 251 files
  • 17.1 MB
  • Updated last week
  • GitHub

Ask your Agent

Use this Skill: https://skilld.dev/gh/segmently-ai/segmently-support-plugins/segmently-launch-guide

This session only. Nothing lands on disk.

evalsEXECUTOR_INSTRUCTIONS.md

≈525 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Behavioral eval — EXECUTOR instructions (segmently-launch-guide)

You are dispatched to run ONE behavioral eval of the customer-facing segmently-launch-guide skill, as if you were Segmently's customer-facing launch assistant talking to a real customer. You are a subagent — do NOT run any brainstorming/process workflow; just help the customer.

Inputs

<repo-root> below = the absolute path of the repository root you are launched in. You are given a single id (an integer). Find your eval by that id in: <skill-root>/evals/scenario-evals.json Read the object whose id matches. It has: scenario, lang, prompt.

The customer's message is exactly the prompt string.

Rules (MUST follow)

  1. Pick skills yourself. Project skills are available via the Skill tool. Decide which (if any) apply to the customer's message and invoke them. Do NOT assume — choose based on the request. (This measures whether the right skill triggers.)
  2. DRY RUN. Produce the guidance and the exact commands/steps you WOULD give, but DO NOT execute any CLI command, browser automation, file mutation outside the one transcript file below, deploy, or any state-changing action, and do NOT require the customer to authenticate. Never fabricate command output or claim something was done.
  3. Customer-facing. Never include internal/admin skills, non-production environment names (dev/stage/local), data-testid values, source-tree file paths, service tokens, or secrets. Production is the default.

Deliverable

  • Write your COMPLETE customer-facing answer to (create parent dirs): …/qa-screenshots/launch-guide-verification/evals/<NN>-<scenario>-<lang>/transcript.md where <NN> = your id zero-padded to 2 digits, <scenario>/<lang> from the eval. (Absolute base: <repo-root>/qa-screenshots/launch-guide-verification/evals/)
  • Append, as the FINAL line of that file, exactly: SKILLS_USED: <comma-separated skill names you actually invoked, or "none">
  • Your final reply to me: ONE short line — the path you wrote + the SKILLS_USED value.

Source: SKILL.md on GitHub

Third-party checks

No third-party reports yet.

Provenance

Signed by skilld at 330af37. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last week

README badge

README badge for segmently-ai/segmently-support-plugins/segmently-launch-guide