oxygen-gtm
Skill2 starsChanged 2 months agoMITView on GitHub
Route a GTM outcome to the correct OXYGEN primitive and select the narrower bundled skill for hosted execution.
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-knowledgeSkill
- oxygen-linkedin-marketingSkill
- oxygen-quickstartSkill
- oxygen-recipesSkill
- oxygen-sequencer-enrollSkill
- 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
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read the runtime contract.
- Very specific: line 15
Search by the actual goal, then hydrate the returned command.
- Very specific: line 32
Prefer the kit's existing callables for research/scoring/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
Route the next GTM job
Read the runtime contract. Use this fallback when no narrower OXYGEN skill already fits.
oxygen capabilities search "research and qualify target accounts" --json
oxygen commands get "tables create" --jsonSearch by the actual goal, then hydrate the returned command. Provider operations have a separate catalog: bounded tools search, then tools get for the selected operation's inputs, readiness, effects and current estimate.
| Job | Native owner / bundled guide |
| Company, ICP, offer, rubric, durable learning | Knowledge |
| Choose a repeatable business play | Recipes |
| Working account lists, AI/tool/waterfall columns | Tables; kit composition |
| Canonical company/person/deal truth | Records; inspect promotion and field ownership |
| Existing-thread replies and direct email | Unibox / Messages |
| Content, engagement and scheduled posts | LinkedIn marketing; Posts, Signals and Publishing |
| Outreach cadence, enrollment and reply stops | Sequences |
| Deterministic triggers, branches and retries | Workflows |
| Adaptive goals and tool choice | Agents; discover the native goal/thread/checkpoint surface |
| Run failures, provenance and spend | Diagnostics |
In Tables, use a formula for deterministic transforms, AI for reasoning, a tool column for one provider operation and a native waterfall for ordered fallback. Cross-table links remain Tables relations; they do not automatically create CRM objects. Shared Tags label native objects, and Dashboards summarize their data.
Prefer the kit's existing callables for research/scoring/copy. Inspect one mapped row and its estimate before live work. Long-running production work belongs in durable OXYGEN runs. Return object links, completed scope, cost evidence and held work.
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.

