Claude Skill

user-stories

Prioritized backlog of user stories with checkable acceptance criteria (docs/STORIES.md) for a macOS app, built from a brief, research, or screen index. Use after app-brief or clone, or when the user asks for user stories, a backlog, a feature list, or "what do we build first".

LLM Mart · 0 points · 3 views 0 listing impressions 0 install-command copies
Download daveebbelaar-bama-skills_plan_user-stories-15356bd.zip · 2 KB

Install

skills CLI npx skills add https://github.com/daveebbelaar/bama/tree/main/skills/plan/user-stories
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install daveebbelaar-bama@llmmart
Git git clone https://github.com/daveebbelaar/bama.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole daveebbelaar/bama collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

User stories

Screens show what an app looks like. Stories say what a person does with it. You build and test stories, not screens.

Read docs/BRIEF.md, docs/research/*.md, and docs/screens/INDEX.md where they exist. Write docs/STORIES.md.

Story format

### S-012 Complete a task with the keyboard
As the user, I select a task and press Command-Return to complete it.
Screens: 01-inbox.png, 02-today.png
Depends: S-004
Acceptance:
- [snap] The circle fills and the row fades out within half a second.
- [self] An "Undo" banner shows for five seconds; Command-Z also undoes it.
- [unit] A recurring task moves to its next date.
Status: todo
  • One action per story. "Rename a project from its context menu", not "Manage projects".
  • Every acceptance line starts with how it is checked: [snap] snapshot, [unit] unit test, [self] self-test, [manual] a person must try it. "Works well" is not checkable.
  • Screens: links reference screenshots, so improve-loop knows what to compare. Without a reference app, name the snapshot pages that will show the story. A panel, sheet, or menu needs its own snapshot page.
  • Depends: (optional) lists stories that must be done first.
  • Keep a control and the only surface that shows it in one story: a highlighting field that lives only in the quick-add panel ships with the panel.
  • Status: todo, doing, done, or dropped.

Milestones

Each milestone ends with an app the user can use for a day.

  1. M1 Core loop: the one thing the app is for, end to end. Data survives a restart.
  2. M2 Organize: the main structure, sidebar pages, moving items.
  3. M3 Time: dates, Today and Upcoming, recurrence, reminders.
  4. M4 Speed: quick-add panel, global shortcut, natural language input, keyboard navigation, search, menu commands.
  5. M5 System: menu bar, Share menu, Shortcuts, notifications, CLI.
  6. M6 Polish: drag and drop, context menus, empty states, icon, settings.

Rename milestones to fit the app. Inside a milestone, stories that others depend on come first.

Seed data

Every attribute the seed data sets (symbols, colors, notes) is something a story lets the user create in the app. Otherwise snapshots show features no one can use.

Leave things out

Drop what exists only for other people or for the vendor: accounts, sharing, teams, integrations, upgrade prompts, gamification. List them under ## Dropped, one line each, so the decision is visible.

UX notes

For each M1 story that adds a screen, an action, or words, call the Skill tool with ux-design. It adds a UX: block under the acceptance lines and starts docs/GLOSSARY.md, so every story uses the same names. Later milestones get their UX notes in improve-loop, just before they are built.

Size check

M1 has 5 to 10 stories. Over 60 stories in total means version one is too big: move stories to ## Later.

Done when every main job in the brief, every "Version one: yes" row in the research matrix, and every screen in the index maps to a story or a Dropped line, and every M1 story with UI has a UX: block.

Files (bama)
  • agents
    • openai.yaml 98 B
      Loading…
  • SKILL.md 3.4 KB
    ---
    name: user-stories
    description: Prioritized backlog of user stories with checkable acceptance criteria (docs/STORIES.md) for a macOS app, built from a brief, research, or screen index. Use after app-brief or clone, or when the user asks for user stories, a backlog, a feature list, or "what do we build first".
    ---
    
    # User stories
    
    Screens show what an app looks like. Stories say what a person does with
    it. You build and test stories, not screens.
    
    Read `docs/BRIEF.md`, `docs/research/*.md`, and `docs/screens/INDEX.md`
    where they exist. Write `docs/STORIES.md`.
    
    ## Story format
    
    ```markdown
    ### S-012 Complete a task with the keyboard
    As the user, I select a task and press Command-Return to complete it.
    Screens: 01-inbox.png, 02-today.png
    Depends: S-004
    Acceptance:
    - [snap] The circle fills and the row fades out within half a second.
    - [self] An "Undo" banner shows for five seconds; Command-Z also undoes it.
    - [unit] A recurring task moves to its next date.
    Status: todo
    ```
    
    - One action per story. "Rename a project from its context menu", not
      "Manage projects".
    - Every acceptance line starts with how it is checked: `[snap]` snapshot,
      `[unit]` unit test, `[self]` self-test, `[manual]` a person must try it.
      "Works well" is not checkable.
    - `Screens:` links reference screenshots, so `improve-loop` knows what to
      compare. Without a reference app, name the snapshot pages that will show
      the story. A panel, sheet, or menu needs its own snapshot page.
    - `Depends:` (optional) lists stories that must be done first.
    - Keep a control and the only surface that shows it in one story: a
      highlighting field that lives only in the quick-add panel ships with the
      panel.
    - Status: `todo`, `doing`, `done`, or `dropped`.
    
    ## Milestones
    
    Each milestone ends with an app the user can use for a day.
    
    1. **M1 Core loop**: the one thing the app is for, end to end. Data
       survives a restart.
    2. **M2 Organize**: the main structure, sidebar pages, moving items.
    3. **M3 Time**: dates, Today and Upcoming, recurrence, reminders.
    4. **M4 Speed**: quick-add panel, global shortcut, natural language input,
       keyboard navigation, search, menu commands.
    5. **M5 System**: menu bar, Share menu, Shortcuts, notifications, CLI.
    6. **M6 Polish**: drag and drop, context menus, empty states, icon, settings.
    
    Rename milestones to fit the app. Inside a milestone, stories that others
    depend on come first.
    
    ## Seed data
    
    Every attribute the seed data sets (symbols, colors, notes) is something a
    story lets the user create in the app. Otherwise snapshots show features
    no one can use.
    
    ## Leave things out
    
    Drop what exists only for other people or for the vendor: accounts,
    sharing, teams, integrations, upgrade prompts, gamification. List them
    under `## Dropped`, one line each, so the decision is visible.
    
    ## UX notes
    
    For each M1 story that adds a screen, an action, or words, call the Skill
    tool with `ux-design`. It adds a `UX:` block under the acceptance lines and
    starts `docs/GLOSSARY.md`, so every story uses the same names. Later
    milestones get their UX notes in `improve-loop`, just before they are built.
    
    ## Size check
    
    M1 has 5 to 10 stories. Over 60 stories in total means version one is too
    big: move stories to `## Later`.
    
    Done when every main job in the brief, every "Version one: yes" row in the
    research matrix, and every screen in the index maps to a story or a
    `Dropped` line, and every M1 story with UI has a `UX:` block.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.