agentleFS
NimbleBrainIncNimbleBrainInc/synapse-todo-board/skills/todo-board-usage/SKILL.md

todo-board-usage

Skill0 starsChanged 6 months agoMITView on GitHub

Choose the right Todo Board tool for each request, scoped to the board the person has open, for creating, finding, moving, reordering, summarizing and archiving tasks.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 0 are distinctive, and 6 are 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.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use create_board_task(board_id, title, ...) with flat arguments.

    line 16
  2. Very specific:

    Use find_board_task(board_id, query) when the user references a task by name on the current board.

    line 20
  3. Very specific:

    Use move_task(task_id, target_column) — never raw update_task for column changes.

    line 24
  4. Very specific:

    Use reorder_column(board_id, column_key, task_ids) with task IDs in the desired order.

    line 28
  5. Very specific:

    Use board_summary(board_id) for aggregate stats: per-column counts, WIP status, overdue and stalled tasks.

    line 32
  6. Very specific:

    Use batch_archive(board_id, older_than_days) to archive completed tasks older than N days (default 7).

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Todo Board — Tool Usage Guide

Board Context

The UI pushes visible state with the active board (selectedBoard.id, selectedBoard.name, selectedBoard.columns). Always use this context — never ask the user which board they mean when one is selected.

Tool Selection

Creating tasks

Use create_board_task(board_id, title, ...) with flat arguments. The board-specific tool links the task with a belongs_to relationship so it appears in the UI. create_task is hidden from the tool list; calling it directly leaves the task without a board, so it never shows in the UI.

Finding tasks

Use find_board_task(board_id, query) when the user references a task by name on the current board. Only fall back to search_tasks if find_board_task returns no matches.

Moving tasks between columns

Use move_task(task_id, target_column) — never raw update_task for column changes. move_task validates the column exists, checks WIP limits, and auto-sets completed_at when moving to done/complete/closed columns.

Reordering within a column

Use reorder_column(board_id, column_key, task_ids) with task IDs in the desired order. Each task gets position set to its array index.

Board overview

Use board_summary(board_id) for aggregate stats: per-column counts, WIP status, overdue and stalled tasks. Good for daily standups or when the user asks "how's the board looking?"

Bulk cleanup

Use batch_archive(board_id, older_than_days) to archive completed tasks older than N days (default 7). Keeps done columns clean.

Common Patterns

"Move X to done" → find_board_task to get the ID, then move_task to the done column.

"Add a task to do Y" → create_board_task with the selected board ID, column defaults to the board's default_column.

"What's overdue?" → board_summary shows overdue tasks with their due dates.

"Clean up the done column" → batch_archive with the board ID.

Column Keys

Column keys are lowercase with underscores (e.g., todo, in_progress, review, done). Use the keys from selectedBoard.columns in the visible state — never guess column names.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.