Communitygithub.com

curiositech/windags-skills

>- Refactor apps so backend owns runtime truth and UI only projects snapshots. Use when tools have split authority. NOT for cosmetic UI work or new features before drift is removed.

windags-skills とは?

windags-skills is a Claude Code agent skill that >- Refactor apps so backend owns runtime truth and UI only projects snapshots. Use when tools have split authority. NOT for cosmetic UI work or new features before drift is removed.

対応✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/backend-authoritative-runtime-refactor

お気に入りのAIに質問する

このエージェントスキルを事前に読み込んだ状態で新しいチャットを開きます。

ドキュメント

Backend-Authoritative Runtime Refactor

Refactor only after you can say exactly where execution truth lives and how the UI reads it.

When to Use

  • The UI synthesizes graphs, phases, or provider choices that the backend does not understand.
  • Relaunch or reconnect changes visible runtime state because the frontend cached authority.
  • Old and new schemas, starter formats, or node types coexist in the active authoring path.
  • Approval, review, or downstream execution depends on frontend-only reconstruction.

NOT for

  • Cosmetic visual cleanup with no change to runtime ownership.
  • Isolated component refactors where the backend contract is already authoritative.
  • Shipping new business features before deleting the split-authority seam.
  • Pure backend performance work when the architecture already has one source of truth.

Decision Points

flowchart TD
  A[Workflow refactor request] --> B{Can the UI still invent runtime truth?}
  B -->|No| C[Use a narrower domain or UI skill]
  B -->|Yes| D[Inventory command, query, and event seams]
  D --> E{Can every user action map to command, query, or event?}
  E -->|No| F[Freeze the contract before feature work]
  E -->|Yes| G[Split projection state from backend-owned state]
  G --> H{Are legacy compat paths still active?}
  H -->|Yes| I[Move them to migration edges or delete them]
  H -->|No| J[Add evaluators, replay-safe startup queries, and event subscriptions]
  I --> J
  J --> K[Validate reconnection, approval, and downstream readiness]

Use this routing model first:

  • If the UI cannot be described as command -> backend transition -> query or event projection, the seam is still wrong.
  • If a "temporary compatibility" path sits in the hot path, treat it as refactor debt, not a feature.
  • If restart or reconnect cannot reconstruct visible state from backend truth alone, the refactor is incomplete.

Working Method

1. Inventory the split brain

Find all places where the UI:

  • generates or mutates execution truth
  • invents phases that the backend does not know about
  • simulates execution in active code paths
  • preserves both old and new schemas in the same authoring path
  • mixes abstract routing tiers with exact provider IDs

2. Freeze the contract

Define three classes only:

  • Commands: start, stop, approve, resume, mutate
  • Queries: startup state, review payload, execution snapshot, provider health
  • Events: authoritative transitions, evaluator verdicts, gate status, replay markers

If a UI action cannot be expressed as one of these, the architecture is still muddy.

3. Normalize state ownership

Split stores into:

  • contract input state
  • backend snapshot projection state
  • UI layout state

Do not let any store own both runtime truth and layout concerns.

4. Delete active compatibility seams

Prefer deletion over "supporting both for now."

Typical deletions:

  • singular and plural schema compatibility in active authoring
  • browser or demo simulation in the active desktop runtime
  • deprecated node types in the main path
  • duplicate review summaries
  • multiple starter or import formats

5. Add evaluators before trusting the refactor

Every implementation node should have:

  • a local-output evaluator for correctness
  • a downstream-readiness evaluator for contract safety
  • a restart or reconnect path that rehydrates from backend truth, not frontend guesses

Failure Modes

Projection masquerading as authority

Symptom: the UI looks "read only" but quietly assembles phase, graph, or provider truth locally.

Fix: move that logic into backend commands or queries and treat the frontend as a projector.

Compatibility seam calcification

Symptom: "support both for now" remains in the hot path for weeks and becomes the real architecture.

Fix: push compatibility to one-way migration edges with an explicit deletion date or remove it now.

Approval without inspectability

Symptom: a human can approve work they cannot inspect because the review payload is partial or frontend synthesized.

Fix: backend must emit the exact review payload; the UI only renders it.

Replay-hostile startup

Symptom: relaunching the app changes visible state or loses gate position because the frontend cached authority.

Fix: startup must be a query against backend truth plus event replay, not store reconstruction.

Shibboleth

If relaunching the app changes visible runtime state without any new backend event, authority is still split.

Worked Example

Tauri workflow editor with frontend-owned phase logic

Problem:

  • React stores authored the graph, inferred phase state, and normalized provider tiers.
  • Backend execution used a different contract, so review and restart flows drifted.

Refactor path:

  1. Inventory every place the UI invented execution truth.
  2. Collapse runtime interactions to commands, queries, and events.
  3. Move provider normalization and phase transitions behind backend commands.
  4. Delete starter-format unions from the active authoring path.
  5. Add evaluator gates so downstream work only proceeds from backend-validated outputs.

Success condition:

  • On restart, the UI reconstructs the same visible state from backend snapshot plus events.
  • Approval screens render a backend-emitted review payload, not a React recomposition.

Fork Guidance

Fork when the work separates cleanly:

  • Contract lane: inventory split-authority seams and define commands, queries, and events.
  • Deletion lane: remove compatibility layers, deprecated node types, and starter-format unions.
  • Verification lane: add evaluator gates, replay tests, and restart or reconnect coverage.

Keep final ownership decisions in the parent lane so one actor decides what the backend truly owns.

Quality Gates

  • The UI cannot fabricate graph, phase, provider, or gate truth locally.
  • Every user action maps to a command, query, or event.
  • Runtime state survives relaunch and reconnect from backend truth alone.
  • Review and approval payloads are emitted by the backend and rendered by the UI.
  • Compatibility logic lives only on migration edges, not in the active path.
  • Downstream execution stops on upstream contract failure.
  • Exact provider IDs and model choices are visible at the contract boundary.
  • Tests cover restart, reconnect, approval, and evaluator failure paths.

Reference Map

  • references/architecture-patterns.md — backend-owned workflow contract patterns and state-ownership splits.
  • references/windags-lessons.md — concrete lessons from a real split-authority runtime migration.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

curiositech/windags-skills

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

curiositech/windags-skills

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

curiositech/windags-skills

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

curiositech/windags-skills

Implement WCAG 2.2 AA/AAA compliance with automated testing, keyboard navigation, screen reader support, and focus management. Activate on: accessibility audit, WCAG compliance, keyboard navigation, screen reader, aria attributes, axe-core, focus trap. NOT for: design-level accessibility review (use design-accessibility-auditor), color contrast only (use css-in-js-architect).

curiositech/windags-skills

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.

curiositech/windags-skills

Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.

curiositech/windags-skills

>- Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

curiositech/windags-skills

Extend and modify the admin dashboard, developer portal, and operations console. Use when adding new admin tabs, metrics, monitoring features, or internal tools. Activates for dashboard development, analytics, user management, and internal tooling.

curiositech/windags-skills

Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-in, supervisor-worker, and peer negotiation. Deep analysis of AutoGen conversation patterns, CrewAI delegation, LangGraph state passing, and FIPA-ACL performatives. Teaches how to design what agents say to each other and in what order. Activate on: "agent conversation", "agent protocol", "multi-agent debate", "agent delegation", "supervisor worker pattern", "agent voting", "consensus protocol", "fan-out fan-in", "agent negotiation", "blackboard pattern", "agent dialogue", "conversation topology", "agent handoff". NOT for: wire format or serialization (use agent-interchange-formats), orchestration infrastructure (use agentic-infrastructure-2026), single agent behavior (use agentic-patterns).

curiositech/windags-skills

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).

curiositech/windags-skills

AI-powered calendar management and agent-based scheduling coordination. Covers calendar APIs (Google Calendar, CalDAV/iCal), AI scheduling assistants (Reclaim, Clockwise, Motion, Cal.com), building custom calendar agents with MCP, multi-calendar merging, timezone management, focus block protection, meeting fatigue detection, and agent-to-agent meeting negotiation protocols. Activate on: "calendar agent", "AI scheduling", "calendar coordination", "meeting scheduling", "calendar API", "focus time protection", "calendar optimization", "Google Calendar MCP", "Reclaim", "Clockwise", "Motion", "Cal.com", "smart scheduling", "calendar-aware agent", "timezone scheduling", "agent negotiation meetings". NOT for: manual calendar UI component design (use form-validation-architect), project management scheduling or Gantt charts (use project-management-guru-adhd), general time-tracking or pomodoro apps (use adhd-daily-planner for time-awareness), building the agent itself from scratch (use agent-creator).

curiositech/windags-skills

Build and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI, building trust in autonomous systems, and scaling adoption across teams. Activate on: "agent infrastructure", "agent framework comparison", "which agent framework", "sell AI tools internally", "agent adoption", "agent observability", "agent evaluation", "MCP architecture", "agentic mesh", "enterprise AI agents", "AI change management", "agent ROI". NOT for: building specific agents (use ai-engineer), designing agent behavior patterns (use agentic-patterns), prompt tuning (use prompt-engineer).

curiositech/windags-skills

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

curiositech/windags-skills

Automated discovery and matching of agent skills for dynamic task routing and capability assessment

curiositech/windags-skills

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

curiositech/windags-skills

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Deep comparison of A2A protocol, MCP, OpenAI function calling, and LangChain message types. Teaches when to use rigid schemas vs free-form with validation, typed vs untyped, streaming vs batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

curiositech/windags-skills

Logic-based agent programming language implementing BDI architecture for practical autonomous agent development

curiositech/windags-skills

>- Design AgentSpeak(L)-style BDI agents with context-guarded plans, selection functions, and intention stacks. Use for interruptible autonomy, agent policy, and multi-agent orchestration in dynamic environments. NOT for simple rule engines, static planners, or centralized workflows.

curiositech/windags-skills

Foundational concurrent computation model where actors communicate exclusively through asynchronous message passing

curiositech/windags-skills

license: Apache-2.0 NOT for unrelated tasks outside this domain.

関連スキル