Agent skill
oxygen-recipes
Find and inspect a versioned OXYGEN business play, preflight its resources and adapt it to the reader's GTM goal.
From timscheuerai/gtm-architecture-template · 51 skill entries · 13 · pushed 2026-09-17
What it does when it runs
Find and inspect a versioned OXYGEN business play, preflight its resources and adapt it to the reader's GTM goal.
Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/timscheuerai/gtm-architecture-template.git /tmp/gtm-architecture-template git -C /tmp/gtm-architecture-template sparse-checkout set ".agents/skills/oxygen-recipes" mkdir -p ~/.claude/skills/oxygen-recipes cp -R "/tmp/gtm-architecture-template/.agents/skills/oxygen-recipes/." ~/.claude/skills/oxygen-recipes/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from timscheuerai/gtm-architecture-template/blob/2c312c9398064ad3730c786647293458cb89632c/.agents/skills/oxygen-recipes/SKILL.md, which is licensed MIT (repository). 219 words, 1 heading.
Choose a useful play
Read the user's goal and first-batch guide. A Recipe is an advisory playbook whose steps use native Tables, Workflows, Sequences and other primitives.
oxygen capabilities search "proven play for warm LinkedIn engagement" --json
oxygen commands get "recipes list" --json
oxygen commands get "recipes show" --json
List a bounded set by goal or lifecycle stage, read one selected Recipe and explain its prerequisites, input, output and limits. Use the reader's actual context; do not make a network motion the default for someone who has no relevant network or chose a different channel.
For a first LinkedIn motion, inspect the current linkedin-network-first-motion recipe if available. Distinguish captured events from coverage of the existing network, and make any standing auto-enrollment grant explicit.
If the Recipe includes a staged kit or Blueprint, inspect the current apply/preflight command. Preview the resources and cumulative forecast before installation. Reuse existing matching stages and record installed versions. Read the resulting resource states; installation does not authorize enabling, enrollment, sending or paid steps.
Use the selected play's actual dependency order and current command schemas. For this repo's functions, prefer the existing installer over creating duplicate equivalents.
Return the chosen play, rationale, prerequisites, installed objects if requested, and the next useful action. A recommended or installed Recipe is not a completed motion.
Need help setting it up?
This page tells you what oxygen-recipes does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.