campaigns
Skill0 starsChanged 5 months agoMITView on GitHub
Use when sending or scheduling Lettr campaigns from code and reading their engagement events. Campaigns are authored in the Lettr dashboard; the API lists, sends, schedules, unschedules, and reports on them.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- spotify/ads-agentic-toolstheir own version, first seen May 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- spotify/ads-agentic-tools★ 20same name
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
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
If the user wants to *create* or *change content/audience* of a campaign, that's a dashboard task — tell them, don't look for an API that …
- Very specific: line 39
Sending is irreversible and goes to real people: Always confirm the target campaign's name, audience size, and content with the user before …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Send & schedule Lettr campaigns
A campaign is a one-to-many marketing send to an audience list/segment. Campaigns are created and designed in the Lettr dashboard — the API does not create, edit, or delete them. From code you can list them, trigger or schedule a send, cancel a schedule, and pull engagement events.
1. Load the references
- SDK calls: detect the stack via
../_shared/detect-stack.md, then read../_generated/sdk/<lang>/campaigns.md. - Wire contract:
../_generated/api/index.md, Campaigns section.
2. The only operations that exist
| Goal | Call |
| Find a campaign / its id and status | GET /campaigns, GET /campaigns/{id} |
| Send now | POST /campaigns/{id}/send |
| Send later | POST /campaigns/{id}/schedule with scheduled_at |
| Cancel a scheduled send | POST /campaigns/{id}/unschedule |
| Read opens/clicks/etc. | GET /campaigns/{id}/events |
If the user wants to create or change content/audience of a campaign, that's a dashboard task — tell them, don't look for an API that isn't there.
3. The template must be a campaign template
A campaign can only send a template whose purpose is campaign. This is the most common way a campaign gets stuck, and it fails late: the template is created, the content is right, and the dashboard simply will not offer it when binding the campaign.
purpose cannot be changed after creation — a transactional template has to be rebuilt as a campaign one, content and all.
So when a user asks for a newsletter or promotion and you create the template for them, set purpose: "campaign" at creation time. See the templates skill, step 3. To check what already exists, list templates filtered by purpose=campaign — that returns exactly the set a campaign is able to use.
A folder's purpose is separate: filing a template in a campaign folder does not make the template a campaign template.
4. Gotchas
- Sending is irreversible and goes to real people. Always confirm the target campaign's name, audience size, and content with the user before calling
send. Preferschedule(which can be cancelled) oversendwhen there's any doubt. - The audience must be ready first. A campaign sends to whatever list/segment it's bound to. If that audience needs building or cleaning, do it in the
audienceskill before sending. scheduled_atis a timestamp — confirm the timezone interpretation with the user; an off-by-timezone schedule sends at the wrong hour.- Idempotency: don't retry a
sendblindly on a network error — re-fetch the campaign status first to see whether it already started. The idempotency keys described in thesendingskill cover transactional sends (POST /emails), not campaign sends; there is no key to pass here, so status is the only check.
5. After sending
Report the campaign id and scheduled/sent status. For results, poll GET /campaigns/{id}/events (opens, clicks, bounces). Delivery problems on individual recipients are the diagnose skill.
What this skill does not do
- It doesn't build or clean the audience — that's
audience. - It doesn't author campaign content — that's the dashboard.
- It doesn't send transactional email — that's
sending.
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.