Kanban AI

Manage a Markdown-based Kanban board using card files in a kanban/ directory (including kanban/archived/ for completed cards). Use when the user asks to create, move, view, list, or manage tasks or cards on a kanban board, or when tracking work items across statuses like backlog, todo, doing, done, or archive.

26 stars 3 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add mattjoyce/kanban-skill --skill kanban-ai
Manual install
git clone --depth 1 https://github.com/mattjoyce/kanban-skill.git /tmp/kanban-skill
mkdir -p ~/.claude/skills
cp -r /tmp/kanban-skill/skills/kanban-ai ~/.claude/skills/kanban-ai

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Kanban AI Skill

Manage a Kanban board as Markdown files in the `kanban/` directory. Each file is a card. The board state is derived by reading all card files and grouping by `status`.

## Narrative Record (Required)

Treat cards as durable source material for future review. Do not rewrite or delete prior narrative content unless explicitly asked. When updating a card, append a brief narrative note to a `## Narrative` section at the end of the file. Focus on reasons, discoveries, insights, and decisions. Avoid transactional status-change logs unless they matter to the story. Use ISO dates.

Narrative entry format:

```markdown
## Narrative
- 2026-02-05: Discovered the auth flow must support device-based MFA; shifted approach to use WebAuthn. (by @assistant)
```

If the card has no `## Narrative` section, add it. If a change is minor (e.g., typo), skip the narrative note unless it carries meaningful insight.

When a card is moved to `done`, add enough narrative detail that a future reader can understand the card’s story and outcome. Keep it coherent and complete without being verbose.

## Card Fields

Each card's frontmatter supports the following fields:

- `id` — Unique numeric identifier. Scan existing cards in `kanban/` (including `kanban/archived/`), take max + 1. Start at `1` if empty. Reference cards by this number.
- `status` — Column: `backlog`, `todo`, `doing`, `done`, or `archive`.
- `priority` — `High` or `Normal`. Defaults to `Normal` if omitted.
Read the full skill on GitHub

Details

Skill name
kanban-ai
Path
skills/kanban-ai/SKILL.md
License
Apache-2.0
Repo updated
5 June 2026

FAQ

What does the Kanban AI skill do?

Manage a Markdown-based Kanban board using card files in a kanban/ directory (including kanban/archived/ for completed cards). Use when the user asks to create, move, view, list, or manage tasks or cards on a kanban board, or when tracking work items across statuses like backlog, todo, doing, done, or archive.

How do I install the Kanban AI skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mattjoyce/kanban-skill --skill kanban-ai. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Kanban AI popular?

It lives in mattjoyce/kanban-skill, which has 26 GitHub stars and 3 forks, and is included in 1 curated skill list.

Related skills

Mcwander

43

Sirius0o0/McWander

Plan a local Citywalk with McDonald's rest stops using the McWander project, Amap walking routes and McDonald's MCP menu and price queries. Use for city strolls with time, walking-distance and dining-budget limits.

AI, LLMs & Agents

Install Dsh Origin

49

Fantasality/dsh-origin-plugin

帮用户把 dsh-origin-plugin(AI 驱动 OriginLab Origin 画图的 MCP 插件)装好并验证可用。当用户说"帮我装 Origin 插件""配置 MCP""让 AI 能画 Origin 图"或遇到装到旧版本/连不上 Origin 时使用。

AI, LLMs & Agents

Origin Scripting

49

Fantasality/dsh-origin-plugin

Origin 零安装脚本模式(v1.0.0)——教 AI 生成可直接粘贴进 Origin Script Window / Python Console 的 Python(originpro) 或 LabTalk 脚本,零依赖、零安装、不需要 MCP。用户拿去手动跑。

AI, LLMs & Agents

Fat Agent

40

spruikco/fat-agent-skill

FAT Agent with Superpowers (Fix, Audit, Test) — a post-launch quality assurance agent that systematically audits deployed websites and web applications using modular, auto-detected check categories. Triggers whenever a user mentions "FAT agent", "post-launch audit", "site audit", "audit my site", "check my deployment", "post-deploy check", "QA my site", "launch checklist", or any request to review a live or recently deployed website for issues. Also triggers after a successful deploy (on any platform — Netlify, Vercel, Cloudflare Pages, AWS, shared hosting, whatever) when the user asks "what s

AI, LLMs & Agents

Review Suno Song

43

nwp/suno-song-creator-plugin

This skill should be used when the user asks to "review my Suno song", "check Suno prompt quality", "evaluate song lyrics", "review this prompt", "check for AI-slop", "validate my Suno prompt", or wants independent quality assessment of Suno prompts and lyrics. Launches the quality-reviewer sub-agent to evaluate material against professional production standards including AI-slop detection, cliché detection, poor quality lines, rhyme assessment, style-lyric consistency, gender-pronoun consistency, and general taste.

AI, LLMs & Agents

Cleanddd Modeling

49

zhouda1fu/Ncp.Admin

基于 cleanddd-requirements-analysis 结果,输出符合 CleanDDD 的聚合、命令、事件、查询、API 端点(Endpoints)、定时任务模型;用于从已拆解的需求快速得到建模蓝图

AI, LLMs & Agents12

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.