agentleFS
Sign inStart free
WhatscheapWhatscheap/igly-canvas-plugin/skills/kanban-retro/SKILL.md

kanban-retro

Skill0 starsChanged 14 days agoMITView on GitHub

Build a kanban board, retrospective wall, affinity map, SWOT, pros and cons or any sticky-note board on an editable Igly canvas. Use when the user wants items sorted into columns or categories, or a team board to move notes around.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Put the user's exact wording on notes.

    line 23

≈ “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

Kanban, retro and sticky-note boards

1. Pick the frame

  • Kanban: To do / Doing / Done (add Blocked or Review if asked).
  • Retro: Went well / To improve / Actions (or Start / Stop / Continue, or Mad / Sad / Glad).
  • SWOT: 2 x 2 grid (Strengths, Weaknesses, Opportunities, Threats).
  • Affinity map: cluster the user's notes into 3 to 6 themes you name.

2. Create

create_canvas with a title (e.g. "Sprint 14 retro"). Keep canvas_id.

3. Layout (one add_elements call)

  • Title: type: "text" at (0, -150), font_size: 48, bold.
  • Column i: a background lane type: "shape", rectangle 360 wide, tall enough for its notes (90 + rows * 200), at x = i * 400, y = 0, fill: "#F4F4F5", stroke: null, corner_radius: 24, with name set to the column title.
  • Column header: type: "text" at x = i * 400 + 24, y = 20, bold, font_size: 30.
  • Notes: type: "sticky", 312 x 170, x = i * 400 + 24, y = 90 + row * 200. One sticky color per column, e.g. #FDE68A, #BFDBFE, #BBF7D0, #FBCFE8.
  • For a 2 x 2 grid use two rows of lanes (y = 0 and y = rows * 200 + 140).
  • Put the user's exact wording on notes; keep each to about 12 words.

4. After drawing

  • Moving a note between columns: update_elements with dx: 400 (or -400) and a new sticky fill if columns are colored.
  • Re-pack a column: arrange with distribute_vertical and gap: 30.
  • Summaries: read the board with get_canvas_summary before summarising or proposing actions.
  • The board is editable in the chat; the user can drag notes too. Offer export_png or the open_url.

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.

Check your setup, free