ios-feature-implementation
Structured procedure for implementing a new feature or change in an existing iOS codebase — inspect and explain before touching files, then implement, then…
Skill by apexbymanish
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/apexbymanish-ios-feature-implementation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ios-feature-implementation
What's inside
- Skill name
ios-feature-implementation- Description
- Structured procedure for implementing a new feature or change in an existing iOS codebase — inspect and explain before touching files, then implement, then verify against a concrete checklist including memory/performance. Use when asked to "implement this feature", "add this screen/flow", or when given a feature request with context/requirements/constraints.
- License
- MIT
- Instructions
- 282 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# iOS Feature Implementation A disciplined inspect → explain → implement → verify loop for feature work in an existing codebase. Do not skip straight to editing files. ## 0. Expected request shape A well-formed feature request names, at minimum: - **What to build** — the feature/behavior in plain language. - **Existing context** — the specific screen(s), ViewModel(s), API(s), and model(s) already involved, by name. - **Requirements** — the specific behaviors the finished feature must have. - **Constraints** — minimum iOS version, dependency policy, "follow existing architecture", "reuse existing components", "don't touch unrelated files". If a request is missing this (e.g. "add a favorites feature" with nothing else), ask for the specific existing files involved before inspecting — guessing which ViewModel or API is "the" relevant one wastes the inspection step below. ## 1. Inspect before touching anything Read, in this order, before writing a single line: 1. **The existing feature/screen this touches.** Read the actual current implementation, not a description of it — a stale comment or README is not the source of truth (if the codebase is undocumented or you can't tell what's current, use `ios-legacy-auditor` first). 2. **The existing business logic it must integrate with or not break.** Trace what the current ViewModel/service actually does with the data today — validation rules, edge cases already handled, state machines, pricing/eligibility logic, anything with branching. New code that duplicates or silently diverges from existing business rules is a correctness bug even when it compiles and looks clean. 3. **The API/model layer** it will call into or extend — actual current signatures and types, not remembered ones. 4. **Nearby reusable components** — check for an existing view, view modifier, or helper before writing a new one; constraints usually say "reuse existing components" for a reason. 5. **Existing API/networking behavior on this path** — the actual current auth-header handling, retry/timeout policy, offline/error handling, and response caching for the endpoint(s) involved. New code that silently drops an existing retry or error-mapping behavior is a regression even if the happy path works. 6. **Existing security posture for this data path** — how any credential, token, or sensitive field involved is stored and transmitted today (Keychain vs. `UserDefaults`, TLS/ATS settings, whether it's ever logged elsewhere). Carry the existing posture forward; don't introduce a weaker one for convenience (e.g. caching a token in `UserDefaults` because it's easier than reusing the existing Keychain wrapper). Do not modify files during this step. ## 2. Explain before implementing Present, in this order, before writing implementation code: 1. **Existing architecture** — the pattern actually in use in the touched area (may not match what the rest of the app does — say so if not). 2. **Files that need modification** — exact paths, and for each, what changes and why. 3. **Proposed implementation** — concrete enough to review: new types/methods with real signatures, not just prose. 4. **Potential risks** — what could break, what's ambiguous in the requirements, anything the constraints make harder (e.g. "no new dependencies" ruling out the obvious library for this). If the codebase's current architecture is unclear or looks like it may not match assumptions, use `ios-architect` for the structural judgment call before proposing an approach. ## 3. Implement - Match the existing architecture and style in the touched files — this is not the place to introduce a different pattern, even a better one, unless the request explicitly asks for a refactor. - Respect every stated constraint literally: if minimum iOS is 14, don't use an iOS 15+ API without an availability check; if "no new dependencies", don't add one even for a one-line convenience. - Touch only the files identified in step 2. If implementation reveals that another file must change too, say so explicitly rather than silently expanding scope. - Follow `ios-testing-strategy` for any new tests this feature needs. ## 4. Verify Run and report on each of the following — don't skip one because it seems obviously fine: 1. **Build** — the project actually compiles. If the `ios-simulator` MCP server is configured (see this repo's `.mcp.json` and README), `build_project` gives a structured result instead of parsing raw `xcodebuild` output; otherwise run `xcodebuild` directly. 2. **Tests** — run the relevant test target(s), report pass/fail counts (`run_tests` via `ios-simulator-mcp`, or `xcodebuild test` directly). 3. **API availability** — every API used is available at the stated minimum iOS version, or is properly `#available`-guarded. If the `ios-agent` MCP server is configured, `mcp__ios-agent__check_availability_guards` also catches the less obvious mistake: a guard set to a *higher* iOS version than the API actually requires, which silently drops support for every device between the true minimum and the guard's version. 4. **Retain cycles** — see the Memory & Performance Review below. 5. **Concurrency** — new `async`/actor-isolated code doesn't introduce a data race or an accidental main-thread block; existing concurrency model in the touched files is preserved, not mixed with a new one. 6. **Memory implications** — see the Memory & Performance Review below. 7. **Performance implications** — no new unbounded main-thread work (image decode, JSON parsing, file I/O) introduced on a hot path. 8. **Security** — see the Security Review below. 9. **Review the diff** — read your own changes once, end to end, before reporting done; look for anything outside the files named in step 2. ## Memory & Performance Review For any feature involving images, networking, WebViews, large collections, caching, Core Data, PDF, or media, check all of the
From apexbymanish/claude-ai-agents-ios, MIT.
More from apexbymanish/claude-ai-agents-ios
- 0.524score
swiftui-engineering
apexbymanish
Procedure for reviewing SwiftUI code for state-ownership, view-identity, lifecycle, and rendering correctness — distinct from ios-ux-reviewer's visual/HIG…
SkillBFreshness: BClaude Code +9 - 0.524score
ios-accessibility
apexbymanish
Procedure for reviewing and verifying iOS accessibility — VoiceOver, Dynamic Type, contrast, hit targets, Switch Control, Reduce Motion — with an explicit…
SkillBFreshness: BClaude Code +9 - 0.524score
ios-api-availability
apexbymanish
Procedure for determining whether code actually works at a project's stated minimum iOS version — deployment target vs.
SkillBFreshness: BClaude Code +9 - 0.524score
ios-app-store-readiness
apexbymanish
App Store submission readiness checklist covering privacy manifests, export compliance, permission usage descriptions, App Tracking Transparency, Sign in with…
SkillBFreshness: BClaude Code +9 - 0.524score
ios-testing-strategy
apexbymanish
Step-by-step procedure for adding tests to existing Swift/iOS code, whether untested legacy code or new TDD work.
SkillBFreshness: BClaude Code +9 - 0.524score
ios-legacy-mapping
apexbymanish
Step-by-step procedure for mapping an undocumented, unfamiliar, or large legacy iOS codebase (Objective-C, UIKit, SwiftUI, or a mix) before making changes.
SkillBFreshness: BClaude Code +9 - 0.524score
ios-performance-measurement
apexbymanish
Procedure for confirming a performance fix actually worked, with a real number, instead of asserting improvement from reading code.
SkillBFreshness: BClaude Code +9 - 0.524score
ios-security-review
apexbymanish
Comprehensive security audit procedure for iOS/Swift code covering data storage, transport security, authentication, input validation, deep links, third-party…
SkillBFreshness: BClaude Code +9 - 0.524score
swift-concurrency
apexbymanish
Procedure for reviewing real Swift code for concurrency correctness — async/await, actors, Sendable, cancellation, task lifetime — not a Swift Concurrency…
SkillBFreshness: BClaude Code +9 - 0.521score
ios-evidence-reporting
apexbymanish
Standard for reporting task outcomes with verifiable evidence instead of confident prose.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 28, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from apexbymanish
- 0.524score
swiftui-engineering
apexbymanish
Procedure for reviewing SwiftUI code for state-ownership, view-identity, lifecycle, and rendering correctness — distinct from ios-ux-reviewer's visual/HIG…
SkillBFreshness: BClaude Code +9 - 0.524score
ios-accessibility
apexbymanish
Procedure for reviewing and verifying iOS accessibility — VoiceOver, Dynamic Type, contrast, hit targets, Switch Control, Reduce Motion — with an explicit…
SkillBFreshness: BClaude Code +9 - 0.524score
ios-api-availability
apexbymanish
Procedure for determining whether code actually works at a project's stated minimum iOS version — deployment target vs.
SkillBFreshness: BClaude Code +9 - 0.524score
ios-app-store-readiness
apexbymanish
App Store submission readiness checklist covering privacy manifests, export compliance, permission usage descriptions, App Tracking Transparency, Sign in with…
SkillBFreshness: BClaude Code +9 - 0.524score
ios-testing-strategy
apexbymanish
Step-by-step procedure for adding tests to existing Swift/iOS code, whether untested legacy code or new TDD work.
SkillBFreshness: BClaude Code +9 - 0.524score
ios-legacy-mapping
apexbymanish
Step-by-step procedure for mapping an undocumented, unfamiliar, or large legacy iOS codebase (Objective-C, UIKit, SwiftUI, or a mix) before making changes.
SkillBFreshness: BClaude Code +9
Cite this page
ios-feature-implementation skill. Agent Mart. https://agentmart.dev/skills/apexbymanish-ios-feature-implementation (last updated 2026-10-24)