Skills directory · page 66

Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.

Swift 6.2 Approachable Concurrency: single-threaded by default, @concurrent for explicit background offloading, and isolated conformances for main-actor types.

Swift 6.2のアクセシブルな並行処理——デフォルトはシングルスレッド、@concurrentは明示的なバックグラウンドオフロードに使用し、分離の一貫性はMainActor型に使用する。

Swift 6.2 Approachable Concurrency — single-threaded by default, @concurrent for explicit background offloading, isolated conformances for main actor types. Use when adopting Swift 6.2 concurrency — offloading with @concurrent or resolving main-actor isolation.

Review and fix Swift concurrency issues such as actor isolation and Sendable violations.

Protocol-based dependency injection for testable Swift code—using focused protocols and Swift Testing to mock the file system, network, and external APIs.

Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.

Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing. Use when Swift code needs testing and file system, network, or external APIs must be mocked.

テスト可能なSwiftコードのためのプロトコルベースの依存性注入——焦点を絞ったプロトコルとSwift Testingを使用してファイルシステム、ネットワーク、外部APIをモックする。

@Observableを使用した状態管理、ビュー合成、ナビゲーション、パフォーマンス最適化、モダンなiOS/macOS UIのベストプラクティスを備えたSwiftUIアーキテクチャパターン。

SwiftUI architecture patterns using @Observable for state management, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices.

SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices. Use when building or reviewing SwiftUI views, @Observable state, navigation, or render performance.

Perform a detailed SWOT analysis — strengths, weaknesses, opportunities, and threats with actionable recommendations. Use when doing strategic assessment, competitive analysis, or evaluating a product or business position.

Use when the user shares a course syllabus or outline and wants supplementary readings. Groups topics with topic_grouper.py, finds recent peer-reviewed papers and writes a .docx with summaries and discussion questions.

Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters.

コードベースの現状に合わせてドキュメントを同期・更新する。 README、コンセプト、構文仕様、要求など実装とともに変遷したドキュメントを見直し、 差分があれば更新 PR を作成する。 Trigger when the user says: "ドキュメント同期", "docs sync", "sync docs", "ドキュメントを更新", "仕様を反映", "ドキュメントが古い", "stale docs", or similar phrases requesting documentation synchronization.

他の PR を main にマージした後、進行中の各 worktree に main を取り込む (merge) ワークフロー。並行している worktree が main から遅れるのを一括で 解消する。Trigger when the user says: "worktreeにmainを取り込む", "worktreeを最新化", "worktree同期", "mainを取り込む", "sync worktrees", "merge main into worktrees", "update worktrees with main", or similar phrases requesting to bring the default branch into in-flight worktrees.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

You MUST use this whenever something is broken, before proposing or making any fix, including quick fixes and when the user is in a hurry: a bug, a failing or red test, a build or CI failure, a crash, a performance problem, unexpected behavior. Finds the root cause in four phases (investigate, compare, test one hypothesis, fix with a failing test first) instead of guessing, and stops after three failed fixes to question the design. Not for writing new features.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Find a bug's root cause before changing code: build a tight red-capable feedback loop, gather evidence at component boundaries, rank falsifiable hypotheses, then fix once and prove it with a regression test. Use for any test failure, production bug, unexpected behavior, performance regression or build failure — especially under time pressure or after a fix that did not work. Not for exploratory "make it nicer" refactors, and not for a known mechanical change with an already-proven cause.

Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css.

Build production-ready design systems with Tailwind CSS, including design tokens, component variants, responsive patterns, and accessibility.

Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.

Builds backend services, integrations, scripts, and business logic within an assigned scope. Activate when the user invokes Tanis by name or assigns this persona; the specialty alone does not trigger it.

Expert in TanStack Query (React Query) — asynchronous state management. Covers data fetching, stale time configuration, mutations, optimistic updates, and Next.js App Router (SSR) integration.

Run one subtask end to end: clarify the approach, write the code, test it, then deliver it behind a completion gate. Use it at the start of every subtask you implement.

Decide whether a subtask needs a brainstorm and a locked spec before any code is written. Run it at the start of every subtask, and transparently skip the brainstorm when the subtask is routine.

Write the code for a locked subtask, then record the progress so the session can resume later. Run it after the spec is settled and before the subtask is tested.

Close out a subtask behind a completion gate and mark it complete in progress.md. Run it after the tests pass, before you start the next subtask.

Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-design-assistant output, (2) resuming interrupted work, (3) batch executing tasks. Triggers on 'start implementation', 'run tasks', 'resume'.

Create one decision-complete task handoff in its repository or on the Desktop for cross-repository work, return a command for a fresh interactive Codex session, and recommend Codex subagent delegation for complex tasks.

Write or revise a useful Paperclip plan with a clear outcome and verification. Use when a plan is requested or uncertainty needs resolving before execution.

Write and run the tests for a subtask with a red-green-refactor loop, and diagnose the failures when they break. Run it after the code is written, before the subtask is delivered.

Structured analysis and planning of a spec. Use when: analyzing a spec, planning its solution, identifying affected files. Do NOT use for: pure code implementation, TDD cycle, code review

Creative-direction layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop family — a named-genre aesthetic vocabulary, mood + color + light system, beat-synced editing grammar, and a pipeline chaining ECC's video skills from b-roll generation to distribution. Use when a video must feel intentional rather than merely functional — music videos, fancams, moodboard-driven reels, or giving AI-generated b-roll a coherent visual direction.

Generate new video against a distilled style pack and cut it into a finished piece - plan takes from the reference's cut rhythm, generate on fal, grade with the pack's measured LUT, cut at the measured cadence, weave in existing footage, composite overlay plates, mint 3D props, and verify the result numerically. Use when the user wants to make a video in a captured style, supplement existing footage, or assemble generated clips into a real edit.

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

Measure a set of reference videos into a reusable style pack - colour grade as a 3D LUT, cut rhythm as a shot-length distribution, hero stills, screen-blend overlay plates, and a text spec for a generative model. Use when the user wants to capture the look of reference footage, build a repeatable look, mint assets from references, or reproduce someone's grade and pacing.

Use for file-driven multimodal image, video, and 3D-asset discovery; taste interviews; distill or apply workflows; style-pack validation; editable EDL/FCPXML export; provenance audits; and offline planning that must fail closed before provider generation.

Web search, content extraction, crawling, and research capabilities using Tavily API

Use when tracking technical changes as records, or handing work between AI sessions with a change record. Creates, updates and validates change records with tc_create.py, tc_update.py and tc_validator.py.

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Test-Driven Development guidance. Use when writing tests before implementation, applying Red-Green-Refactor, testing Value Object contracts, typed domain failures/Results, DDD Aggregates, Domain Events/subscribers, transaction or cache boundaries, data migrations/backfills, Criteria/query adapters, repository contracts or persistence adapters, choosing between test doubles, deciding test granularity, reviewing test suite quality, or diagnosing brittle tests.

Test-Driven Development methodology. Use when: implementing new functionality, refactoring existing code, ensuring high test coverage. Do NOT use for: task analysis and planning (use task-workflow-assistant), codebase exploration without implementation

Test-first development and test generation for Jest, Pytest, JUnit, Vitest or Mocha: red-green-refactor, fixtures and mocks, coverage gaps. Use whenever the user asks to write tests (before or after the code), mock a dependency or raise coverage.

Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices.

Test-driven development workflow: write a failing test first, watch it fail, implement the smallest change to green, then refactor with 80%+ coverage across unit, integration, and E2E tests. Use when writing a new feature, fixing a bug, refactoring, or when told to write failing tests first.

新機能の作成、バグ修正、コードのリファクタリング時にこのスキルを使用します。ユニット、統合、E2Eテストを含む80%以上のカバレッジでテスト駆動開発を強制します。

새 기능 작성, 버그 수정 또는 코드 리팩터링 시 이 스킬을 사용하세요. 단위, 통합, E2E 테스트를 포함한 80% 이상의 커버리지로 테스트 주도 개발을 시행합니다.