oxygen-sequencer-enroll
Skill2 starsChanged 2 months agoMITView on GitHub
Prepare a reviewed, verified cohort for a native OXYGEN Sequence and execute only the user's authorized enrollment and sending scope.
In this repository54 other files it gives its agents.
- AGENTS.mdAGENTS.md
- context/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- context/CLAUDE.mdCLAUDE.md
- brand-reviewSkill
- brand-systemSkill
- capture-contextSkill
- content-strategySkill
- crm-presync-checkSkill
- flowchartSkill
- graphics-designerSkill
- gtm-startSkill
- launch-videoSkill
- lead-magnet-creatorSkill
- lead-sourcingSkill
- linkedin-copywriterSkill
- long-formSkill
- manim-videoSkill
- newsletter-writerSkill
- outbound-copywriterSkill
- oxygen-dedupeSkill
- oxygen-deliverabilitySkill
- oxygen-diagnosticsSkill
- oxygen-email-infraSkill
- oxygen-gtmSkill
- oxygen-knowledgeSkill
- oxygen-linkedin-marketingSkill
- oxygen-quickstartSkill
- oxygen-recipesSkill
- oxygen-sequencerSkill
- oxygen-table-tidySkill
- oxygen-uniboxSkill
- oxygen-workflow-authoringSkill
- personalize-ai-columnSkill
- qmdSkill
- repurpose-contentSkill
- researcherSkill
- setup-workspaceSkill
- shorts-audioSkill
- shorts-cutSkill
- shorts-editSkill
- shorts-motionSkill
- shorts-qaSkill
- signals-sweepSkill
- spin-tagsSkill
- split-test-designerSkill
- video-useSkill
- voice-calibrationSkill
- week-postsSkill
- x-copywriterSkill
- youtube-descriptionSkill
- youtube-publisherSkill
- youtube-scriptSkill
- youtube-thumbnailSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Read composition, runtime contract and the prepare_sequence definition.
- Very specific: line 10
Use oxygen-sequencer for native definition, lifecycle and dispatch controls.
- Very specific: line 14
Every row needs independent company/persona gates, current valid email verification, an explicitly reviewed message, clear suppression …
- Distinctive: line 18
If the user authorized the exact send scope, proceed within it.
≈ “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
Hand off to a native Sequence
Read composition, runtime contract and the prepare_sequence definition. Discover the installed CLI's Sequence operations and schemas; older generic create/start examples are not authoritative.
Use oxygen-sequencer for native definition, lifecycle and dispatch controls. This skill is the kit-specific adapter from prepare_sequence into enrollment.
Inspect the exact Sequence, recipient cohort, sender identity, channel, steps, schedule/time zone, reply stops, suppression and current capacity. Use observed sender health and configured limits. Do not substitute a universal sends-per-day number.
Every row needs independent company/persona gates, current valid email verification, an explicitly reviewed message, clear suppression state and frozen experiment IDs. Run prepare_sequence for the selected rows; held rows keep their reasons.
Prepare native enrollment field mappings from real output columns. Render the actual subject/body against one real recipient and inspect unresolved variables and reply routing. Enrollment can itself trigger sending depending on Sequence state: verify that state before writing.
If the user authorized the exact send scope, proceed within it. If only a draft/setup was requested, finish the concrete preview and report the remaining authorization. Avoid duplicate enrollment after ambiguous results; query the recipient/Sequence state first.
Report enrolled/skipped/failed counts, actual Sequence state, limits and recipient scope. Preserve enrollment and experiment IDs for outcome normalization. Creating a Sequence, enrolling and starting delivery are distinct states; report only the one verified.
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.

