This is the one page written for the technical detail rather than for you. Installing the skills takes a single command. Everything below that is what your agents are taught, published openly so you can check it.
Before you install
The skills do nothing on their own. Everything they describe is a call to a Tatara MCP tool, so your agent needs a connected Tatara MCP server first. See Connect an agent.
Installing
Install every skill into every agent tool detected on your machine:-a, which you can repeat:
As a Claude Code plugin
On claude.ai
Download the repository, zip a folder underskills/, and upload it in claude.ai under Settings → Capabilities → Skills.
The twelve skills
One core skill, six skills for the document formats, and five for the other kinds of document.How the skills combine
The coretatara skill is always in play. It owns the workflow (search first, resolve the folder, tag from the taxonomy, then write) and the recovery loop when a write is rejected. The other skills load on top of it, one for each kind of document, and each governs only what goes inside that document.
So a plain prose document needs only the core skill. A board needs the core skill and tatara-kanban: the core skill decides where the document is filed and how it is tagged, and tatara-kanban decides what the body looks like. A slide deck takes three: the core skill, tatara-html for the HTML itself, and tatara-slides for the slides.
Choosing between skills
See Document formats for what each format requires.Board or task checklist
Both use- [ ] checkbox items, so look past the checkbox to where the meaning lives.
- Choose kanban when the column a card sits in is the state. The work of the document is moving cards between columns.
- Choose tracker when the metadata on each task is the point: per-task tags, a priority glyph, a
📅 YYYY-MM-DDdue date, a✅ YYYY-MM-DDcompletion date. Tasks can be grouped under## Sectionheadings, but the grouping is optional and is not a state machine.
Table or base
Both render as a grid, which is where the confusion starts. The difference is what owns the rows.- A table holds its own data. The rows live in the document body as one pipe table, with a declared type per column.
- A base holds no data of its own. It is a saved view whose rows are other documents in your workspace, selected by filters. The body contains only the query.
Table or workbook
Both hold rows with typed columns and formulas. The difference is whether the formulas stay live.- A table works out its formula columns and writes the results into the table as values.
- A workbook keeps its formulas live, and holds several tables and named cells. Choose it for anything calculated: a budget, a model, a tracker with totals.
Mind map or whiteboard
- A mind map is a plain tree: every topic has one parent.
- A whiteboard joins ideas with named relations, so it suits causes and effects, a process, or dependencies.
Dashboard or data page
- A dashboard counts and lists the workspace’s own documents.
- A data page lays out figures from one workbook for people to read: KPIs, a scorecard, a monthly report. The figures live in the workbook, and the page reads them.
Repository
tatara-app/tatara-skills
The skills are open source under the MIT licence. Read them to see exactly what your agent is told about each kind of document.