App Planner

What it does

When your agent uses it

• The user describes an app idea
• Workflow and needs a structured plan before building
• What features does X need
• Feature breakdown

Example prompts

• “plan this app”
• “what features does X need”
• “design plan”
• “/app-planner”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Purpose / Big Picture (what the redesign achieves)
2. 2User & Moments (personas + frequency-ranked interactions)
3. 3Progress (living checkboxes, updated each session)
4. 4Design Milestones (one per screen, pattern-mapped)
5. 5Deliberate Omissions (what's NOT in scope)
6. 6Decision Log (updated during execution)
7. 7Surprises & Discoveries (updated during execution)

What it can do on your machine

Read from SKILL.md and the folder at commit cf93c57. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

App Planner loads about 1.6k tokens when it runs. Until then it costs about 170 tokens; SKILL.md has 488 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~170

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pproenca/dot-skills at commit cf93c57, republished under its MIT licence (© pproenca). 488 words, ~1,583 tokens.

name

app-planner

description

Produces a design-plan (living document like an exec-plan) that maps an app domain to feature groups using Apple Design DNA patterns. Each feature group becomes a milestone buildable in one ios-taste session. Use when the user describes an app idea, domain, or workflow and needs a structured plan before building. Triggers on "plan this app", "what features does X need", "design plan", "feature breakdown", "what screens do I need", or any pre-build planning question. Also trigger when the user provides workflow notes or user interview results. CRITICAL: This skill produces a DESIGN-PLAN document only. It does NOT generate SwiftUI code, layouts, or visual design.

# [App Name] Design Plan — [Focus]

This DesignPlan is a living document. Progress, Decision Log, and
Surprises & Discoveries must stay up to date as work proceeds.

## Purpose / Big Picture

[1-3 sentences: what the user can do AFTER this plan is executed.
Outcome-focused, not feature-list.]

## User & Moments

- **[Persona 1]**: [who, when, device context]
- **[Persona 2]**: [who, when, device context]

| Frequency | Moment | What they do |
|-----------|--------|-------------|
| 50x/day | [moment name] | [one line] |
| 10x/day | [moment name] | [one line] |
| 5x/day | [moment name] | [one line] |
| 1x/day | [moment name] | [one line] |
| 1x/week | [moment name] | [one line] |

## Progress

- [ ] Milestone 1: [screen name]
- [ ] Milestone 2: [screen name]
- [ ] Milestone 3: [screen name]
...

## Design Milestones

### Milestone 1: [Screen Name]

**User goal**: "[What the user is trying to do — in their words]"
**Pattern**: [Apple Design DNA pattern name] (from [source app])
**Priority**: Must-have
**Frequency**: [how often this screen is used]
**Existing TCA domain**: [which reducer/feature this touches]

**Features**:
- [Feature] — [why the user needs it]
- [Feature] — [why the user needs it]
- [Feature] — [why the user needs it]

**Acceptance criteria**:
1. [Observable proof — what the screen shows/does]
2. [User test — "show to [persona], they say X"]
3. [Technical — builds, tests pass, no raw design tokens]

**ios-taste prompt** (use this to start the build session):
> "[Exact prompt to give ios-taste to build this screen, including
> user context, emotional intent, and which pattern to reference]"

---

### Milestone 2: [Screen Name]
...

## Deliberate Omissions

- [Feature] — [why it's excluded]
- [Feature] — [why it's excluded]

## Decision Log

_Updated during execution._

## Surprises & Discoveries

_Updated during execution._

© pproenca, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/.experimental/app-planner of pproenca/dot-skills.

• SKILL.md
• metadata.json

Open the folder on GitHubat commit cf93c57