Exploration symbolique du code avec Serena MCP. Utiliser pour naviguer dans le code par symboles (fonctions, classes, hooks), trouver des définitions, et comprendre l'arc — from…
Service mesh configuration and operations expertise for Istio, Linkerd, and Consul Connect
Clean code, robust architecture, no test slop. Foundational skill for high-quality software engineering, code structure, and reviews.
Thorough code-quality audit of the Solarxy workspace. Reviews Rust idioms, wgpu + WGSL correctness, egui patterns, ratatui (where used), architecture, performance, safety,…
Enterprise architecture patterns following TOGAF ADM methodology. Implements capability-driven design, federated architecture, and technology-agnostic specifications.
Target Operating Model (TOM) Architect for enterprise transformation across any platform. TRIGGER when: user asks to design a Target Operating Model, TOM, operating model,…
AI-powered analysis of tumor clonal architecture, subclonal dynamics, and evolutionary trajectories from multi-region sequencing and longitudinal liquid biopsy data.
AI-powered intratumor heterogeneity analysis for clonal architecture reconstruction, subclonal evolution tracking, and therapy resistance prediction using multi-region and…
Vertical Slice Architecture (VSA) 向け UI 強化スキル。 Phase 1（spec-kit + カタログ）で生成されたプレーンな .razor ファイルを、 Phase 2 で MudBlazor ベースのリッチな UI に変換する。 アーキテクチャには一切手を触れず、UI だけを強化する。
Xử lý từng GROUP một cách có hệ thống trong Whole Knowledge Architecture. Hỗ trợ expand, refine, và enrich nội dung từng nhóm khái niệm.
Explore and understand an existing codebase. Use when the user wants to understand the code, explore a project, discover an architecture, or before modifying existing code.
Use when the user asks to write a technical doc, runs /writing:write-doc, or mentions drafting an architecture overview (AO), feature design, runbook, getting-started guide,…
Create a new Architecture Decision Record in .context/decisions/. Use when documenting an architectural decision.
SAM-style feature initiation workflow: discovery -> codebase analysis -> architecture spec -> task decomposition -> validation -> context manifest.
Adds support for a new MoE language model to PithTrain. Use when the user asks to "add support for model X", "implement model Y in pithtrain", "port model Z", or otherwise…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
ADR(Architecture Decision Record) 작성 스킬. 두 개 이상의 기술 선택지를 비교하고 추천안과 그 근거, 숨겨진 비용, 확장성, 2년 뒤 기술 부채까지 입체적으로 평가한다. 비개발자도 이해할 수 있도록 한국어 위주 설명 + 추천안 강조.
Generate architecture guidelines for the project. Analyzes tech stack from DESCRIPTION.md, recommends an architecture pattern, and creates .ai-factory/ARCHITECTURE.md.
Analyze a codebase to generate a comprehensive architecture and structure report. Use when user wants to understand a codebase, explore project structure, or generate analysis.
Drive an Arc42 + 12-Factor questionnaire to baseline architecture and operability decisions before /spec:design.
Use when starting, resuming, or continuing a software architecture patterns curriculum with an interactive tutor in the current repo.
Create, extract, or convert an ADR (architectural decision record) using the ADR template. Use when creating new ADRs, extracting an ADR from existing documentation, converting a…
Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and…
Evaluate an architecture against foundational principles of state, change, and time — five grounded principles PLUS a fixed set of named, executable review checks (C1–C7) run as a…
Use when: comparing two or more candidate architectures, designs, or technical approaches against weighted quality attributes: performance, consistency and correctness,…
Generate a static architecture page that reads ADRs, Mermaid diagrams, CHANGELOG, SBOM, tech-debt log into one navigable UI; per frontend stack
Review software architecture, including package cohesion and inter-package coupling
Analyze project/namespace boundaries, detect circular refs and layering violations via dotnet-depends and solution graph.
Get a second opinion from leading AI models on code, architecture, strategy, prompting, or anything. Queries models via OpenRouter, Gemini, or OpenAI APIs.
Decomposes a spec or architecture into buildable tasks with acceptance criteria, dependencies, and risk-first implementation order, for AI agents or human engineers.
Build a working application from an AutoGherk spec-output folder containing architecture blueprints, design tokens, and reference screenshots
Author a numbered, dated, user-attributed Architecture Decision Record under .codearbiter/decisions/.
Report the health of Architecture Decision Records — aged, unchallenged, supersession candidates, unresolved CONFIRM-NN. Read-only.
Create the next-numbered Architecture Decision Record in the project's docs/ADR/ directory, using the Nygard format (Status, Context, Decision, Consequences).
Use when the user asks to "plan my paid account structure", "pick Search vs PMax", "lay out ad groups / asset groups", or "audit paid-vs-organic cannibalization"; designs…
Check if a proposed change aligns with mangrove-agent's stated principles, architecture, and trading-bot safety invariants.
Read-only audit of GitHub Actions workflow runner compatibility for one repository, an explicit repository set, one Apache project with multiple repositories, or the full Apache…
Activate Mythic Engineering mode — architecture-first, document-guided, AI-orchestrated development with six specialist roles.
Predict, prevent, and mitigate context window failures before they happen. Analyzes workflows for overflow risk, designs disk-as-memory architectures, and produces recovery-ready…
After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer.
Translate approved GDDs + architecture into epics — one epic per architectural module. Defines scope, governing ADRs, engine risk, and untraced requirements.
Create a new composable pattern — a multi-block sequencer composition that solves a recurring agentic architecture problem.
Feature audit: finds implemented but user-unreachable functionality in any project. Discovers tech stack and architecture automatically, then checks connectivity between layers…
Design media and DAM architecture including storage, processing, and delivery. Covers images, video, and documents.
Opinionated guide to software design principles and architectural patterns. Use when reviewing code design, planning feature architecture, asking "is this the right design?", "how…
Use when: a specification, architecture, README, or other doc claims to reflect the current implementation ('amended from implementation', 'current state') and may have drifted;…
Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout.
Generate wiki documentation from completed spec files — architecture decisions, usage guide, API changes. Posts to ADO Wiki or Confluence depending on provider config.
Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and c — from…
Generate comprehensive architecture documentation for complex code modules with Graphviz diagrams and examples.
Codebase exploration techniques for rapid discovery, architecture analysis, pattern detection, and dependency mapping. — from fusengine/agents
Codebase exploration techniques for rapid discovery, architecture analysis, pattern detection, and dependency mapping. — from engineering/architecture
Multi-angle codebase exploration spawning 3-5 parallel agents for code structure, data flow, architecture patterns, and health assessment.
Reviews or guides implementation of a 12-factor cloud-native application. Audits an existing codebase for 12-factor compliance, or provides concrete implementation guidance when…
Use when: designing failure behavior for an architecture or component design before implementation: per-dependency failure modes (slow, down, wrong, partial), degradation policy,…
Design React components from Figma files. Use when given a Figma URL to analyze a design and propose React component architecture, props API, and variant handling.
Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG.
Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap
Invoke when the user works with Unreal Engine 5 or asks about C++/Blueprints, GAS, replication, Nanite, Lumen, CommonUI, Enhanced Input, or World Partition.
Scaffold an Architecture Decision Record (Nygard format) in docs/adr/ with auto-numbering, status lifecycle, and supersedes cross-linking. Args: