sending-email-campaigns
Skill0 starsChanged 9 days agoMITView on GitHub
Picks an audience, drafts a Sendly email campaign, sends a test, and sends the campaign only after the user confirms the recipient count. Use when the user asks to 'draft a September newsletter for premium members', 'write an email announcement', 'prepare a campaign', 'who is in this segment', 'send me a test email', 'send the campaign', or run an email marketing send or email blast.
In this repository66 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adding-uptime-monitorsSkill
- analyzing-page-performanceSkill
- booking-meetingsSkill
- building-onboarding-workflowsSkill
- building-study-guidesSkill
- capturing-tasksSkill
- capturing-web-pagesSkill
- chasing-unpaid-invoicesSkill
- checking-domain-connectionsSkill
- checking-email-deliverabilitySkill
- checking-notification-deliverySkill
- checking-uptime-statusSkill
- cleaning-up-bookkeepingSkill
- connecting-customer-domainsSkill
- discussing-buildsSkill
- drafting-invoicesSkill
- drafting-social-postsSkill
- editing-demosSkill
- editing-page-draftsSkill
- extracting-document-textSkill
- finding-meeting-timesSkill
- handling-flaky-changesSkill
- investigating-tasksSkill
- making-demo-videosSkill
- managing-bookingsSkill
- managing-content-calendarSkill
- managing-demosSkill
- managing-voice-librarySkill
- planning-revisionSkill
- preflighting-domainsSkill
- publishing-pagesSkill
- reading-financial-reportsSkill
- reading-text-aloudSkill
- reading-web-pagesSkill
- reporting-snapvisor-usageSkill
- researching-course-materialSkill
- researching-summary-librarySkill
- responding-to-incidentsSkill
- reviewing-email-performanceSkill
- reviewing-notification-workflowsSkill
- reviewing-social-performanceSkill
- reviewing-visual-buildsSkill
- reviewing-workloadSkill
- searching-getitdone-api-docsSkill
- sending-notificationsSkill
- setup-bioflowSkill
- setup-calySkill
- setup-demofySkill
- setup-dodomainSkill
- setup-getitdoneSkill
- setup-notiflySkill
- setup-postifySkill
- setup-sendlySkill
- setup-shortySkill
- setup-snapvisorSkill
- setup-superbooksSkill
- setup-unotesSkill
- setup-upapiSkill
- setup-uptimelySkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 4 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Every tool in this skill comes from the sendly MCP server, the Sendly connector, and is written here as sendly:<tool>.
- Very specific: line 15
Tools listed by name: call them directly, for example sendly:list_contacts.
- Very specific: line 33
If the user wants to start from a template, call sendly:list_templates and sendly:get_template.
- Distinctive: line 34
Write the subject and body in the user's voice.
- Very specific: line 35
Call sendly:check_domain and make sure the from address is on a verified domain.
- Very specific: line 36
Call sendly:create_campaign with name, subject, body, from, and audience.
- Very specific: line 38
When the user asks to send, call sendly:send_campaign without confirm.
- Very specific: line 39
Ask: "Send this to N contacts now?" Only after an explicit yes in this turn, call sendly:send_campaign again with confirm: true.
- Very specific: line 43
Never call sendly:send_campaign with confirm: true, sendly:send_email, or sendly:send_mailbox_email without an explicit yes to a stated …
- Distinctive: line 44
Never send to addresses that are not already contacts in the project.
- Very specific: line 45
If sendly:send_test_email refuses a recipient, explain that tests go only to the owner's own verified address.
- Distinctive: line 46
If the sending tools are missing, the user did not grant the sending scope.
- Distinctive: line 47
Do not fabricate links, prices, or claims in the copy.
≈ “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.
Files
<!-- Generated from plugins/sendly/skills/sending-email-campaigns/SKILL.md by scripts/sync-skills.mjs. Edit the plugin copy, then run the script. -->Draft and send a Sendly campaign
Go from an idea to a campaign in DRAFT, then to a test, then to a send. Sending reaches real inboxes, so it happens only after the user explicitly confirms the audience size.
Connecting and calling the tools
Every tool in this skill comes from the sendly MCP server, the Sendly connector, and is written here as sendly:<tool>.
- Tools listed by name: call them directly, for example
sendly:list_contacts. - Only
sendly:search_toolsandsendly:execute_typescriptlisted (Code Mode, the default): callsendly:search_toolsfirst, then call each tool insidesendly:execute_typescriptasexternal_<tool>(for exampleexternal_list_contacts); the program mustreturnits result. Scopes, confirmations and gates are identical on both surfaces. - "Tool not found": switch to the Code Mode route instead of retrying the direct call. If
sendly:search_toolsdoes not return the tool either, its OAuth scope was not granted; the user reconnects Sendly and approves that scope. - No
sendlytools at all: Sendly is not connected yet. Follow thesetup-sendlyskill.
Tools you will use
sendly:list_segments,sendly:list_segment_contacts,sendly:list_lists,sendly:list_contacts: find and size the audience.sendly:list_templates,sendly:get_template: reuse the copy and layout of an existing template.sendly:create_campaign: save a campaign in DRAFT. Needsname,subject,body, andfrom, even though the schema marks only the first two as required.sendly:update_campaign: change a draft campaign.sendly:send_test_email: send a test to the project owner's own verified address. Refuses any other recipient.sendly:send_campaign: two-step. Withoutconfirm: trueit returns the audience size and sends nothing. Withconfirm: trueit sends to every contact in the audience.sendly:check_domain: confirm thefromaddress is on a verified domain.
Workflow
- Settle the audience. Call
sendly:list_segmentsorsendly:list_lists, thensendly:list_segment_contactsorsendly:list_contactsto show who is in it and how many. - If the user wants to start from a template, call
sendly:list_templatesandsendly:get_template. - Write the subject and body in the user's voice. Show them and ask for changes once.
- Call
sendly:check_domainand make sure thefromaddress is on a verified domain. If not, stop and offer thechecking-email-deliverabilityskill. - Call
sendly:create_campaignwith name, subject, body, from, and audience. Report the campaign id and that it is a DRAFT. Nothing is sent. - Offer a test. Call
sendly:send_test_emailonly after the user says yes; it goes to their own verified address. - When the user asks to send, call
sendly:send_campaignwithoutconfirm. Report the audience size it returned, the subject, and the from address. - Ask: "Send this to N contacts now?" Only after an explicit yes in this turn, call
sendly:send_campaignagain withconfirm: true. Report the result.
Rules
- Never call
sendly:send_campaignwithconfirm: true,sendly:send_email, orsendly:send_mailbox_emailwithout an explicit yes to a stated recipient count. An earlier "send it" before the count was shown is not confirmation. - Never send to addresses that are not already contacts in the project. There is no bulk import or arbitrary-recipient send here, and a purchased list is not consent.
- If
sendly:send_test_emailrefuses a recipient, explain that tests go only to the owner's own verified address. - If the sending tools are missing, the user did not grant the sending scope. Say so; do not look for another way to send.
- Do not fabricate links, prices, or claims in the copy. Ask for them.
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.

