agentleFS
inttegrointtegro/labor/skills/message-delivery-integrity/SKILL.md

message-delivery-integrity

Skill1 starsChanged 4 days agoMITView on GitHub

Use for product work involving message templates, email, SMS, recipient resolution, composer or preview interfaces, message logs, provider delivery, or delivery evidence. Preserve semantic template metadata, channel-aware authoring, faithful previews, explicit send confirmation, and honest delivery state; do not use merely to rewrite ordinary prose.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Treat authored content, rendered content, transport state, and provider evidence as separate layers.

    line 8
  2. Distinctive:

    Read references/templates-and-authoring.md for template variables, contextual values, email editors, or SMS composition.

    line 17
  3. Distinctive:

    Keep the final send action in the preview or confirmation state.

    line 27
  4. Distinctive:

    Never send a real message, retry a provider delivery, or mutate suppression or provider state without explicit authorization.

    line 28
  5. Distinctive:

    Verify with representative complex email and long SMS content, not only one-line fixtures.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Message Delivery Integrity

Treat authored content, rendered content, transport state, and provider evidence as separate layers. A polished composer is not sufficient when variables, recipient resolution, preview fidelity, or delivery status are wrong.

Start with the contract

  1. Identify the source of truth for the template, recipient, channel, and delivery state.
  2. Trace the request through the authoring client, message service, queue or worker, and provider boundary as applicable.
  3. Determine whether the route is live or test mode and whether any action would contact a real recipient.
  4. Preserve existing service ownership instead of creating a second template or delivery model in the UI.

Read references/templates-and-authoring.md for template variables, contextual values, email editors, or SMS composition. Read references/preview-and-delivery.md for previews, sends, message logs, provider state, or test-mode behavior.

Non-negotiable decisions

  • Template variables need explicit user-facing metadata. Do not derive canonical labels, acronym casing, or field behavior solely from raw identifiers.
  • Auto-fill values only from recognized context and preserve their provenance. Missing required values remain visible fields and block final sending.
  • Email and SMS are different authoring modes. Reuse established channel-specific editors, validation, and segmentation logic.
  • A preview renders the actual output. Do not inject alignment, padding, foreground color, or body background that was not authored.
  • Show one primary rendition of the message. Do not render plain content and HTML as competing duplicate bodies.
  • The recipient should identify the customer or contact when known while retaining the actual address or formatted phone number required for delivery.
  • Keep the final send action in the preview or confirmation state. Do not send merely because the user advanced from the composer.
  • Never send a real message, retry a provider delivery, or mutate suppression or provider state without explicit authorization.

Completion standard

Verify with representative complex email and long SMS content, not only one-line fixtures. Report separately what was authored, previewed, persisted, queued, submitted, accepted by a provider, and confirmed delivered.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.