AI Agent Workflow Collection

Full-stack AITuber (AI VTuber) orchestrator for planning, implementation, and operation. Designs real-time streaming pipelines (Chat → LLM → TTS → Avatar → OBS), live chat integration, TTS, Live2D/VRM avatar control, lip-sync, and OBS WebSocket automation.

Terminal UI construction, CLI development, and dev-tool integration (linter/test-runner/build-tool wiring). Use when CLI/TUI design or implementation is needed. Language-agnostic — supports Node.js, Python, Go, and Rust.

Planning career strategy for job change/side-business/independence. Owns self-analysis, market & salary research, positioning, skill-gap plans, job search (target lists, tracker, outreach), interview prep, and salary negotiation. Advisory only — no code. Use when planning career moves. Not for engineer SNS branding (Crest), UX research (Field), product competitive (Compete), or JP tax filing (Levy).

Analyze dependencies, circular references, and God Classes; author ADRs/RFCs. Use for architecture improvement, module decomposition, and technical debt assessment.

Spec compliance verification agent. Extracts ACs from specs, adversarially verifies implementation conformance. Generates BDD scenarios, traceability matrices, and compliance reports with evidence-based verdicts. Does not write code.

Orchestrating super-premium landing-page studio chains. Orchestrates the full LP pipeline (Discover → Audience → Strategy → Structure → Design → Build → Optimize → Verify → Launch) across 6 craft axes (Design/Animation/Branding/Marketing/SEO/IA) with explicit rubrics and quality gates. Use when a request asks for a complete, conversion-tuned, brand-defining LP. Not for single LP section (Funnel), design-only pipeline (Atelier), product-wide build (Titan), generic orchestration (Nexus), or A/B execution (Experiment).

App Store & Google Play release-navigation specialist — review-guideline compliance, console submission workflow, store listing & privacy declarations, and rejection remediation. Don't use for rollout/versioning strategy (Launch), screenshot assets (Snap), native implementation (Native), or CI upload automation (Gear).

Legal document review for Terms of Service, Privacy Policy, and Tokushoho compliance. Clause gap detection, risk flagging, and regulatory alignment. Don't use when legal advice is needed — consult a lawyer.

Video script, storyboard, and narration design. Used for product videos, explainer videos, and onboarding content planning.

Continuous application auto-tuning architect. Designs the profile->parameter->optimize->verify loop for GC/threadpool/pool/cache/worker settings. Don't use for one-shot perf fix (Bolt), DB query plan (Tuner), load test (Siege), or AI/ML hyperparameter (Oracle).

Pixel art specialist agent. Generates pixel art as code (SVG/Canvas/Phaser 3/Pillow/CSS). Also supports SVG generation delegation to Gemini CLI.

Legacy code archaeology. Extract implicit business rules from undocumented code and assess migration risk. Use for legacy investigation.

Designing hiring processes and team structure (employer side). Produces recruitment strategy, job descriptions, competency matrices, interview rubrics, scorecards, outreach templates, candidate-journey maps, 30/60/90 onboarding, performance reviews, culture docs, and bias-reduction checklists. Does not write code; flags labor-law content for professional review. Use when designing the hiring process or team structure. Not for regulatory audit (Oath), persona generation (Cast), candidate side (Ascent), or engineer personal branding (Crest).

Product image search and high-precision download specialist. Multi-source aggregation (e-commerce APIs, image search, brand sites), SKU/JAN/UPC matching, perceptual-hash dedup, license-aware curation. Don't use for generic browser tasks (Navigator), fleet-scale crawl architecture (Spider), AI image generation (Sketch), or mockup-to-code (Pixel).

Supply-chain malware infection scanner. IoC-based local scan + safe eradication for npm/PyPI worm campaigns (Mini Shai-Hulud 1st/2nd, S1ngularity, lottie-player). Detects OS persistence (LaunchAgent/systemd), IDE-hook implants (.claude/.vscode/.github/workflows), lockfile-pinned malicious versions, and known C2/Session-Protocol exfil traces. Orchestrates credential rotation in the correct order so revocation does not trigger the rm -rf ~/ retaliation payload. Don't use for static SAST (Sentinel), skill/MCP/.claude/ supply-chain audit (Chain), Sigma/YARA rule authoring (Vigil), or incident coordination (Triage).

Super-premium landing-page studio chain. Orchestrates the full LP pipeline (Discover → Audience → Strategy → Structure → Design → Build → Optimize → Verify → Launch) across existing agents, enforcing 6 craft axes — Design, Animation, Branding, Marketing, SEO, IA — each with explicit rubrics and quality gates. Use when a request asks for a complete, conversion-tuned, brand-defining LP. Don't use for single LP section work (Funnel), design-only pipeline (Atelier), product-wide build (Titan), generic multi-domain orchestration (Nexus), or A/B test execution (Experiment).

Mobile development specialist. Implements best practices for React Native/Flutter/SwiftUI/Jetpack Compose, navigation, offline support, and store review preparation. Use when mobile app development is needed.

Auditing regulatory compliance and mapping business requirements (SOC2/PCI-DSS/HIPAA/ISO 27001), checking control implementations, designing audit trails, and implementing Policy as Code. Use when compliance auditing is needed.

Faithful reproduction agent that generates pixel-accurate HTML/CSS code from image mockups (PNG/JPG/screenshots) and performs visual verification. Use when mockup-to-code generation is needed.

Web-to-native porting design specialist (2026 spec — Liquid Glass / Material 3 Expressive / Swift 6.2 / Compose 1.7+ / Xcode 26 / targetSdk 36 / 16KB page / Passkey / Privacy Manifest / DMA / EAA / 5.1.2(i) AI disclosure aware). Designs complete porting blueprints from Web apps (React/Vue/Svelte/Angular SPA, RSC/SSR included) to iOS Swift/SwiftUI and Android Kotlin/Jetpack Compose pure-native apps. Optionally proposes a hybrid path (Pure-Native UI + Kotlin Multiplatform shared logic) when the survey justifies it. Produces feature parity matrices, native architecture maps, platform-UX adaptation plans, data/auth/CRDT porting strategies, BFF redesigns, regulatory-compliance plans, and Strangler-Fig phased roadmaps. Don't use for cross-platform UI implementation (Native — RN/Flutter), generic framework migration in the same language (Shift), dependency upgrades (Horizon), legacy code archaeology only (Fossil), or full mobile feature implementation (Native/Builder).

Score and order items by user-specified criteria. Reads items from prior primitive output in context. Keywords: sort, score, prioritize, order, compare, evaluate, weight.

YC-style office hours advisory. Surfaces the 1 bottleneck via socratic probing, gives pattern-matched honest feedback, detects founder anti-patterns, and extracts concrete 1-2 week action items. Don't use for exploratory brainstorming (Riff), structured triadic deliberation (Magi), long-term scenario simulation (Helm), feature generation (Spark), or implementation (Builder).

Search engine and vector DB design specialist. Use when full-text search, vector search, or hybrid search design, index optimization, or RAG retrieval layer implementation is needed.

Migration and upgrade orchestrator for frameworks, libraries, APIs, databases, and infrastructure. Provides codemod generation, incremental strategies (Strangler Fig/Branch by Abstraction), before/after verification, and rollback plans.