templates
Skill0 starsChanged 5 months agoMITView on GitHub
Use when authoring or editing Lettr-managed email templates — choosing transactional vs campaign purpose, writing HTML with merge tags, validating tags against a template version, and previewing or test-sending before shipping.
22 other projects use a version of this.
Adopted by
Most recently taken up by
- runa-tic/palimpsesttheir own version, first seen Nov 8, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
- razzant/ouroborostheir own version, first seen Oct 25, 2026
- sid-lakhani/agents-configtheir own version, first seen Oct 20, 2026
- The-Utopia-Studio/skillstheir own version, first seen Oct 13, 2026
- ibdmaibot-southafrica/claude-code-agent-startertheir own version, first seen Oct 9, 2026
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- razzant/ouroboros★ 1.6ksame name
- butterbase-ai/butterbase-plugin★ 535same name
- butterbase-ai/butterbase-skills★ 535same name
- xenitV1/Antigravity-Workflows★ 130same name
- VoDaiLocz/kilo-kit-mcp★ 28same name
- coder/skills★ 14same name
- The-Utopia-Studio/skills★ 6same name
- SKB3002/agenthub★ 4same name
- wachterjohannes/symfony-skills★ 4same name
- WESTsyre21/setup-backend-stack★ 4same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Every template is either transactional or campaign, and it defaults to transactional.
- Very specific: line 37
Write standard email-safe HTML.
- Very specific: line 41
New: create with name, html (or json for the visual-editor format), purpose (see step 3), and project_id if applicable.
- Very specific: line 43
Existing: update by slug. Each update creates a new version.
- Distinctive: line 62
Don't blast a test silently.
“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Author Lettr templates
Templates live in Lettr and are referenced by slug when sending. This skill is about writing the HTML and merge tags correctly and verifying the result before it goes to real recipients.
1. Load the references
- SDK calls: detect the stack via
../_shared/detect-stack.md, then read../_generated/sdk/<lang>/templates.mdfor create/update/get and merge-tag calls. - Wire contract:
../_generated/api/index.md— the Templates section (POST /templates,PUT /templates/{slug},GET /templates/{slug}/merge-tags,GET /templates/html). - Merge-tag syntax & conventions:
references/merge-tags.md.
2. Find the project
Templates are project-scoped. List projects (GET /projects) to get the right project_id. If the team has only one, use it.
3. Decide the purpose — before you create anything
Every template is either transactional or campaign, and it defaults to transactional.
| Purpose | What it is | Examples |
transactional (default) | Triggered by one person's action | Password reset, receipt, order confirmation, alert |
campaign | Marketing sent to an audience list | Newsletter, promotion, product announcement |
This cannot be changed after creation. A campaign can only send a template whose purpose is campaign, so a newsletter created with the default has to be rebuilt from scratch — and the failure does not surface until someone tries to attach it to a campaign in the dashboard, long after you have finished.
So: if the user's request is a newsletter, a promotion, an announcement, or anything else going to an audience rather than to one person, pass purpose: "campaign" on create. If you are not sure, ask — it is a cheap question and an expensive mistake.
Folders have a purpose too, and it is independent. Filing a template in a campaign folder does not make the template a campaign template; only purpose on the template does.
4. Author the HTML
Write standard email-safe HTML. Use {{variable}} for merge tags; see the merge-tags reference for conditionals and loops. Keep in mind email-client constraints (inline-friendly CSS, table layouts) — the sending options control CSS inlining at send time.
5. Create or update
- New: create with
name,html(orjsonfor the visual-editor format),purpose(see step 3), andproject_idif applicable. The response returns aslug— that's the send-time identifier, and echoes back thepurposeyou actually got. - Folder:
folder_idis optional; omitting it files the template in whichever folder the API picks. To choose deliberately, list folders (GET /folders) — that is the only call that returns a folder id. Nothing else does, so the alternative is hardcoding an integer read out of an app URL. - Existing: update by slug. Each update creates a new version; merge tags are re-extracted automatically. Older versions stay pinnable at send time (
template_version), which is how you keep production stable while drafting.purposeis fixed at creation and cannot be updated.
Imported templates are not instantly sendable
Template responses carry preparation_status: pending, ready or failed. An imported or JSON-authored template renders asynchronously, so it exists before its HTML does — typically for a few seconds.
- After a create:
pendingmeans there is no HTML yet. Sending now sends nothing useful. PollGET /templates/{slug}until it settles; seconds, not minutes. - After an update: the previous render keeps serving until the new one settles. A
pendingtemplate still sends — just not yet the new content. That is the trap: the send succeeds and quietly delivers the old version. failedmeans the render did not produce HTML. Do not send; re-import or fix the source.- Absent on older API responses — treat that as ready rather than blocking.
To check a whole batch at once, list with folder_id and per_page=100 rather than fetching each template individually; a per-template GET drags the full HTML payload against the same rate limit.
6. Confirm merge tags
Fetch the template's merge tags (GET /templates/{slug}/merge-tags, optionally per version). Cross-check the list against what the calling code passes as substitution_data — a missing variable renders as an empty string, which is rarely intended.
7. Offer a preview / test
Don't blast a test silently. Two levels, in order of cost:
- Render only: fetch the rendered HTML (
GET /templates/html) to show the user what default values produce — no email sent. - Live test (ask first): send a real email using the slug +
substitution_datato an address the user controls — the only way to know it renders in real clients. This is a send, so it's thesendingskill's job; hand off with the slug. Seereferences/testing.md.
What this skill does not do
- It doesn't author the send call — that's
sending. - It doesn't import templates from another provider; translate HTML with judgement if asked, but there's no conversion playbook.
- It doesn't sync templates to repo files unless the project already mirrors them (e.g. a Node
lettr-kitorphp artisan lettr:pullflow) — then edit the local file and let that tooling push.
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
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.

