apple-platform-planner
Skill2 starsChanged 2 months agoMITView on GitHub
Use when planning a new iOS, macOS, or shared Apple-platform feature. Do not use for implementation-only requests or non-Apple planning.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- apple-accessibility-reviewSkill
- apple-app-marketing-siteSkill
- apple-design-systemSkill
- apple-development-foundationSkill
- apple-error-statesSkill
- apple-security-privacy-reviewSkill
- codex-bootstrapSkill
- codex-skill-maintainerSkill
- ios-macos-platform-adaptationSkill
- maestro-apple-app-testingSkill
- reusable-code-extractorSkill
- swift-concurrency-reviewSkill
- swift-package-module-authorSkill
- swift-testing-verificationSkill
- swiftui-component-authorSkill
- swiftui-tab-navigationSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 12
Inspect context: Read consumer AGENTS.md (root through relevant scopes), deployment targets, package products, existing modules, and …
- Distinctive: line 19
Risks and stops: Call out unknowns, dependency needs that require authorization, and decisions that need the user.
≈ “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.
Files
Apple platform planner
Produce a bounded implementation plan for an Apple-platform feature in the consumer workspace. Do not write product code when the request is planning-only.
Workflow
- Inspect context. Read consumer
AGENTS.md(root through relevant scopes), deployment targets, package products, existing modules, and navigation/state patterns before proposing architecture. - Clarify the slice. Restate the user goal, platforms in scope, and out-of-scope items. Stop and ask if platforms, consumer path, or success criteria are materially ambiguous.
- Separate shared vs platform-specific. Identify logic that can stay shared versus presentation, navigation, or lifecycle differences that need
ios-macos-platform-adaptationlater. - Name ownership. For each major state or dependency, say who owns it (view, environment, observable model, actor, package) and how it is injected. Flag any proposed view model with an ownership or testability reason.
- Surface constraints early. Note accessibility, privacy/permissions, entitlements, offline/network, and concurrency risks that affect design — not only polish. When relevant, plan against Apple’s 2026 HIG design principles (Purpose, Agency, Responsibility, Familiarity, Flexibility, Simplicity, Craft, Delight) — see Design principles. Use them as named audit language only; do not expand into an essay.
- Plan verification. List the smallest build/test/UI checks (XcodeBuildMCP / unit / Maestro) that will prove the feature. Prefer one exact simulator/device strategy when iOS is in scope.
- Sequence work. Ordered implementation slices small enough to land independently. Recommend skill chain for the build phase (for example design system → component author → platform adaptation → reviews → testing).
- Risks and stops. Call out unknowns, dependency needs that require authorization, and decisions that need the user.
Plan shape (required sections)
- Goal and non-goals
- Platforms and deployment assumptions
- Shared core vs platform deltas
- State / dependency ownership
- Accessibility and privacy notes
- Implementation sequence
- Verification plan
- Risks and open questions
- Suggested skill chain for implementation
Stop conditions
- Implementation-only request with clear scope → do not over-plan; hand off to authoring skills and implement.
- Non-Apple or pure backend/web planning → out of scope for this skill.
- Planning-only → no code, no dependency changes, no project file edits.
- Missing consumer workspace → stop; do not plan against this foundation repo’s
archive/unless explicitly asked.
Inputs: requested feature and existing project context. Output: a bounded implementation plan with risks and verification. Planning-only requests produce no code or repository changes.
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
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.

