AIDevTools

Manages ClaudeChain automated PR chains. Use when working with claude-chain projects, listing open chain PRs, rebasing chain branches, triggering chain workflow runs, checking chain capacity, fetching workflow logs, creating new chains, or updating/editing an open chain PR locally.

Debugging guide for AIDevTools (evals, plan runner, Mac app, PRRadar). Shows how to discover configured repositories, eval cases, artifact paths, plan storage, log files, and CLI commands for troubleshooting. Use this skill when: the user reports a bug, asks to check eval data, shares a screenshot of eval results or the Mac app, mentions a failing case, wants to inspect provider output, needs to debug plan generation or execution, or is debugging PRRadar behavior (pipeline output, rule evaluation, Mac app issues). Screenshots of the Mac app are a strong signal to invoke this skill — they mean the user wants you to reproduce or investigate using the CLI.

Reference for where Claude and Codex provider data is stored on disk — session logs, raw output, thinking/reasoning availability, and format differences between the two providers. Use whenever investigating provider output, debugging missing thinking blocks, reading session history, or asking "where does X get stored for Claude vs Codex?"

Running, writing, and extracting screenshots from UI tests and interactive tests for the AIDevTools Mac app. Use this skill when: running XCUITests, capturing app screenshots, adding new screenshot tests, extracting images from .xcresult bundles, or using the interactive test runner (XCUITestControl) to programmatically drive the app UI.

Guidance for this project's composition root pattern — how SharedCompositionRoot centralises shared service wiring, how the Mac app and CLI targets each have their own root that wraps it, and how platform-specific additions (models, git client, credentials) are layered on top. Use this when adding new shared services, creating a new CLI command that needs services, modifying how providers or credentials are wired, reviewing code that constructs services outside a composition root, or any time someone asks how dependency wiring works in this project.

Guide for adding, modifying, or reviewing configuration in this Swift app. Use when adding credentials or API keys, creating a new config file, adding a ServicePath case, setting up a service that reads settings, wiring configuration through the Apps layer, reviewing whether config is injected correctly (resolved values vs raw services), asking 'where should this config go?', or adding per-repo feature settings. Also use when working with SecureSettingsService, CredentialResolver, SettingsService, DataPathsService, or RepositoryConfiguration anywhere in the codebase.

Debugging context for PRRadar. This content has moved — use the ai-dev-tools-debug skill instead, which now covers PRRadar debugging inline.

Checks and fixes code quality issues in Swift: fallback values that hide failures, backwards-compatibility shims for unreleased code, raw String/[String:Any] types where typed models should exist, optional properties that should be non-optional, AI-changelog comments that describe what changed rather than why, duplicated logic across call sites, inline string formatting for derived identifiers (branch names, keys, paths), raw string literals used as shared identifiers, and force unwraps. Use when reviewing Swift code for quality, before committing, when asked to clean up or harden code, or when ai-dev-tools-enforce is running.

Orchestrates enforcement of this project's coding standards against recently changed Swift code. Runs in two modes: Fix mode makes direct code changes (default); Analyze mode produces a violation report with severity, explanation, and fix suggestions without touching code. Trigger Fix mode when asked to "enforce architecture", "apply reviews", "refactor to spec", "fix violations", or "clean up recent changes". Trigger Analyze mode when asked to "analyze", "review for violations", "what would you change", or "show me what's wrong".

Checks and fixes Swift code for architecture violations in this project's 4-layer system (Apps → Features → Services → SDKs). Covers layer placement, upward dependencies, @Observable outside the Apps layer, multi-step orchestration in models, feature-to-feature imports, SDK coupling to app-specific types, SDK mutable state, use case struct convention, type naming, CLI parity, and error swallowing across layers. Use this whenever reviewing or refactoring Swift code for architecture compliance, when code is being added to any layer, when someone asks if code follows the layered architecture, or when ai-dev-tools-enforce is running.

Checks and fixes build quality issues in Swift code: compiler warnings in new or modified files, TODO/FIXME comments left in production code, commented-out code blocks, and debug artifacts (print statements, hardcoded test values, fatalError("not implemented"), temporary return statements). Use this whenever reviewing changed Swift files before committing, when asked to clean up code, or when ai-dev-tools-enforce is running.

Checks and fixes Swift file and type organization: splits files containing multiple unrelated top-level types into one file per type, moves supporting enums and nested types below the primary type they support, and renames files whose name doesn't match their primary type. Use when reviewing Swift file structure, when a file feels hard to navigate, or when ai-dev-tools-enforce is running.

Logging infrastructure for this project — reading logs, filtering output, debugging via logs, and adding logging to new features. Use this skill whenever reading logs, investigating errors via logs, adding log statements for debugging CLI or Mac app behavior, or ensuring new features are properly covered by logs. Trigger on any mention of logs, log files, Logger calls, log levels, or "what happened during the last run", and when implementing new functionality.

Create a new PRRadar review rule. Use when the user wants to add a code review rule, create a violation check, or set up a new pattern to detect in PRs. Handles choosing the project config, rule directory, evaluation mode (AI/script/regex), file targeting, and grep filtering.

Add an item to the project TODO list with t-shirt size categorization (Small, Medium, Large)

Four techniques for capturing iOS/macOS screenshots. Method 1 (XCUITests for macOS) captures real app screenshots — the preferred approach. Method 2 (ImageRenderer) works anywhere with no dependencies. Methods 3-4 require Aqua launchctl bootstrap from background processes. Use when you need screenshots from daemons, CI, SSH, or OpenClaw.

Checks and fixes Swift test files for conformance to Swift Testing conventions: replaces XCTest assertions with #expect/#require, adds @Test with descriptive sentence-form names, converts XCTestExpectation-based async tests to async throws, enforces Arrange-Act-Assert structure with blank-line separation, and splits tests covering multiple behaviors into separate @Test functions. Use when writing or reviewing Swift test files, when adding new tests to this project, or when ai-dev-tools-enforce is running.

Returns the current time. Use when the user asks what time it is or wants to know the current time.

Tells AI dev tools themed jokes. THIS SKILL MUST be used any time the user asks for a joke about AI, dev tools, coding tools, evals, or AI development. Always invoke this skill before answering joke requests related to AI development tooling.