Agent skill
oxygen-table-tidy
Inspect and improve OXYGEN Table structure, visibility and formatting while preserving raw data, dependencies and record identity.
From timscheuerai/gtm-architecture-template · 51 skill entries · 13 · pushed 2026-09-17
What it does when it runs
Inspect and improve OXYGEN Table structure, visibility and formatting while preserving raw data, dependencies and record identity.
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-table-tidy" mkdir -p ~/.claude/skills/oxygen-table-tidy cp -R "/tmp/gtm-architecture-template/.agents/skills/oxygen-table-tidy/." ~/.claude/skills/oxygen-table-tidy/
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-table-tidy/SKILL.md, which is licensed MIT (repository). 209 words, 1 heading.
Make the Table usable
Read the runtime contract. Use oxygen-dedupe for identity matching; this skill handles columns and presentation.
Discover oxygen commands get "tables tidy-suggest" --json and run the suggestion pass read-only on the named Table. Inspect its actual schema, dependencies and a bounded sample.
Group findings by overlapping columns, order, types, formatting, visibility and suspicious values. Similar names do not prove identical semantics. Record the consumers of a proposed change before applying it.
Separate workspace hiddenByDefault curation from the user's empty-column collapse. Hidden columns still exist and may feed downstream formulas or AI inputs; hidden is not archived. Prefer a visibility change when the goal is a cleaner view, and keep raw evidence when adding a cleaned/derived value.
A completely blank enrichment column may never have run for older rows. Inspect run/provenance and current backfill preview instead of immediately forcing every row to rerun. Paid backfill requires the selected row scope and current cap.
Apply requested reversible formatting/order/visibility fixes within scope. Present data-changing retypes, archival or paid cleanup concretely before any additional authorization needed. Do not merge records or overwrite raw values as a cosmetic tidy operation.
Re-describe the Table and inspect representative rows after changes. Return what changed, affected dependencies, held suggestions and the Table link.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- table-creation by extruct-ai · 109
- table-setup by Frontal-so · 6
Need help setting it up?
This page tells you what oxygen-table-tidy 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.