ios-claude-skills
AGENTS.md1 starsChanged 14 days agoMITView on GitHub
This file configures AI agents working on the Sajidisrar/ios-claude-skills repository itself. Scope: This is not meant to be copied into other projects or into a global agent configuration. The reusable assets are the skills in skills/, not this file. A flat skills/ directory of 37 Claude Code-format skills for iOS/Swift development: 22 lifecycle-workflow skills (feature work, quality, review, shipping — presented in the README under "Build/Quality/Review/Ship" though the directory itself has no category subfolders) plus 15 Apple-framework skills (Swift concurrency…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository37 other files it gives its agents.
- ios-accessibility-auditSkill
- ios-api-contract-migrationSkill
- ios-api-endpointSkill
- ios-app-intents-siriSkill
- ios-bug-triageSkill
- ios-build-configurationSkill
- ios-cloudkit-syncSkill
- ios-combine-patternsSkill
- ios-commit-and-prSkill
- ios-commitSkill
- ios-concurrency-auditSkill
- ios-coreml-apple-intelligenceSkill
- ios-deep-linkingSkill
- ios-dependency-assessmentSkill
- ios-design-fixSkill
- ios-feature-moduleSkill
- ios-knowledge-baseSkill
- ios-latest-os-adoptionSkill
- ios-localizationSkill
- ios-offline-writeSkill
- ios-performance-tuningSkill
- ios-port-from-androidSkill
- ios-port-to-androidSkill
- ios-precommitSkill
- ios-privacy-complianceSkill
- ios-push-and-background-tasksSkill
- ios-refactorSkill
- ios-release-prepSkill
- ios-sdk-upgradeSkill
- ios-secure-reviewSkill
- ios-storekit-subscriptionsSkill
- ios-swift6-concurrency-migrationSkill
- ios-swiftdataSkill
- ios-swift-testing-migrationSkill
- ios-swiftui-screenSkill
- ios-unit-testsSkill
- ios-widgetkit-live-activitiesSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Follow
CONTRIBUTING.md's skill anatomy: when adding or editing a skill — frontmatter, verification checklist, no real … - Very specific: line 17
Version every release the same way: follow CONTRIBUTING.md's "Versioning and releases" — scripts/bump-version.sh for all manifests, a …
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md
This file configures AI agents working on the Sajidisrar/ios-claude-skills repository itself.
Scope: This is not meant to be copied into other projects or into a global agent configuration. The reusable assets are the skills in
skills/, not this file.
What this repo is
A flat skills/ directory of 37 Claude Code-format skills for iOS/Swift development: 22 lifecycle-workflow skills (feature work, quality, review, shipping — presented in the README under "Build/Quality/Review/Ship" though the directory itself has no category subfolders) plus 15 Apple-framework skills (Swift concurrency migration, SwiftData, StoreKit, and others — presented under "Frameworks & Platform").
Working on this repo
- Don't reintroduce nested category folders under
skills/. Every supported tool's native skill discovery (Claude Code, Codex, Cursor, Copilot, Gemini CLI) expectsskills/<name>/SKILL.mddirectly, one level deep. The Build/Quality/Review/Ship/Frameworks grouping is presentation-only — it belongs in README tables, never in the filesystem. - Follow
CONTRIBUTING.md's skill anatomy when adding or editing a skill — frontmatter, verification checklist, no real client/business/personal data, technical claims checked against Apple's actual documentation rather than written from memory. - Keep the per-tool docs (
docs/*.md),install.shand the SwiftPM plugin (Plugins/InstallIOSSkills/plugin.swift, same--tooltable) in sync with what's actually true of each tool's current skill-discovery mechanism — these are living integrations, not a one-time snapshot; a tool changing its skill directory convention should prompt an update here, not just in a comment. - The plugin manifests are directory-based, not list-based (
"skills": "./skills"), so adding or removing a skill folder doesn't require touching.claude-plugin/plugin.jsonor.codex-plugin/plugin.json. It does require updating the README's category tables. - Version every release the same way: follow CONTRIBUTING.md's "Versioning and releases" —
scripts/bump-version.shfor all manifests, a CHANGELOG.md entry, then avX.Y.Ztag. Never set a manifest version by hand, and never move or delete a published tag (SwiftPM users resolve against it).
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.