oxygen-sequencer
Skill2 starsChanged 2 months agoMITView on GitHub
Operate native OXYGEN Sequences for new conversations and outreach cadence, including sender readiness, previews, enrollment, dispatch and recovery.
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-sequencer-enrollSkill
- 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
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 8
Read the runtime contract.
≈ “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
Operate the Sequence
Read the runtime contract. The kit-specific enrollment skill maps prepare_sequence outputs into the native surface; this skill owns Sequence setup and lifecycle.
New LinkedIn conversations belong to Sequences even for one recipient. Cadenced or multi-recipient outreach uses Sequences. Existing-thread replies and direct email without cadence use Messages.
Discover exact commands with oxygen capabilities search "preview outreach sequence" --json, then commands get for the selected operation.
Inspect these together:
- Sender profiles, exact accounts/mailboxes, health, channel limits and stable recipient-to-sender binding.
- Definition/version, ordered steps, delays, variants, send windows/time zone and any channel fallback.
- Recipient identity, mapped variables, exclusions, suppression, prior-contact rules and tags.
- Dispatch limits, lifetime budget, live-run cap, reply stops and bounce behavior.
Preview the actual recipient scope and render messages with their real variables. Report unresolved identities individually. A connected mailbox is not proof of readiness. Use email infrastructure for sender setup and deliverability for health issues.
Enrollment and dispatch are separate actions. Inspect the selected Sequence's current state: draft or paused enrollments may remain pending, while an active Sequence may deliver after enrollment. Execute only the user's authorized send scope and current platform gates; a cap is not authorization.
Record enrollment, variant and run IDs. For results, inspect campaign events/analytics and preserve actual mailbox/domain attribution; missing identity stays unattributed. Normalize events into analyse_results without claiming that the kit automatically wires telemetry.
For recovery, preview the narrow failed/deferred scope and reconcile provider outcomes before retrying. Pause/resume, retirement and capacity recovery have distinct semantics; discover them before acting. Return counts, held reasons, actual state, budget and deep-links.
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.

