Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.
Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.
Skill Claude CodeCodex
Use this skill when creating or reviewing palettes, contrast, semantic color, dark mode, or chart colors. It adapts Color Expert-style color reasoning into practical UI work.
Skill Claude CodeCodex
Before rendering, turn every explicitly requested workflow outcome into a compact ledger: user outcome -> triggering control/event -> rendered state branch -> recovery/next action. Success and failure are separate outcomes. When a backend is unavailable but the outcome can be modeled locally, make both outcomes…
Skill Claude CodeCodex
Use this comprehensive gate for formal review, QA, launch handoff, exact-fidelity inspection, high-risk complex UI, or when the fast gate exposes a deeper craft problem. Ordinary single-screen work uses ui-design-executor and its bundled validator without loading this full matrix. Pair standalone artifacts with…
Skill Claude CodeCodex
Use this skill before rendering when the direction must persist across multiple screens/components, brand or system work, conflicting references, formal handoff, or a genuinely vague visual system. Ordinary single-screen screenshots and clear briefs use ui-design-executor's compact source/visual thesis instead of…
Skill Claude CodeCodex
Use this as UIDesigner's default execution skill. It contains the baseline design, accessibility, HTML, runtime-safety, responsive, taste, and verification rules needed by ordinary UI work. Do not load the separate system, control, taste, color, renderer, or craft skills merely to repeat these baseline rules.
Skill Claude CodeCodex
Use this skill when the task is to review, critique, QA, or polish an existing UI, screenshot, HTML artifact, or implemented screen.
Skill Claude CodeCodex
Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live Figma runtime.
Skill Claude CodeCodex
Use this skill when creating, extending, or auditing a product UI system. It adapts Better Design-style design-system discipline without requiring an external runtime package.
Skill Claude CodeCodex
Use this specialist for unusually complex stateful HTML, blank/runtime-risk repair, strict source-to-HTML fidelity, reusable component galleries, brand boards, or detailed implementation handoff. Ordinary single-page HTML uses ui-design-executor, which already preserves HTML-default delivery and baseline…
Skill Claude CodeCodex
Use this skill when the user asks for a live dashboard, refreshable report, synced view, recurring data artifact, connector-backed UI, auditable status page, or data-backed HTML that should remain useful after the first render.
Skill Claude CodeCodex
Use this skill after ui-design-contract only when UIDesigner needs a visual-system reference, product pattern, or style benchmark. It adapts OpenDesign's design-system and template catalogue into a small routed reference layer for HTML-first UI work.
Skill Claude CodeCodex
Use this specialist when the user explicitly asks for a less generic/less AI-looking direction, an expressive restyle, brand-led visual thesis, or a taste critique. ui-design-executor already carries the baseline subject grounding and visual thesis for ordinary work.
Skill Claude CodeCodex
Measure whether AI answer engines surface a brand. Split because a skill can't reach the model providers: this skill generates the queries and scores the answers; the agent calls the model / websearch for each query and feeds the answers back.
Skill Claude CodeCodex
Score how citable/ready a page is for AI answer engines, from crawl facts. Pure analysis — no network, no model calls. Deterministic so it is drift-comparable.
Skill Claude CodeCodex
Heuristic content/GEO-readiness analysis of the visible text from seo-crawl. No network. Judgments are heuristic (marked Estimated); raw counts are Measured.
Skill Claude CodeCodex
Agent-wide core connector rule: when any connected search console is used, discover its operations with listconnectortools and invoke each selected operation through callconnectortool; naming listsites or an analytics operation without the core invocation is not execution.
Skill Claude CodeCodex
Measure Core Web Vitals with the free PageSpeed Insights API. Field data (CrUX, real users) is reported as Measured; lab (Lighthouse synthetic) as Estimated.
Skill Claude CodeCodex
Discover the phrasings people actually use, starting from a seed. seo-opportunity ranks queries a site ALREADY has console data for; this skill is the other half — it finds queries the site has no data for yet, which is where a new page or a new site has nothing to rank.
Skill Claude CodeCodex
Detect SEO/GEO regressions over time by snapshotting and diffing. Pure analysis — no network (the agent re-crawls; this compares).
Skill Claude CodeCodex
For product-focused strategy, prefer observed use-case, pricing, comparison, and trust/docs pages. Name missing page types as coverage gaps and map recommendations to owned pages, first-party proof, answer blocks, and one cannibalization owner per overlapping query cluster.
Skill Claude CodeCodex
Render an audit into the deliverable: a dashboard spec the chat can show inline, and a written action plan. Pure formatting — no network, no scoring (it trusts the audit, opportunity and probe inputs).
Skill Claude CodeCodex
Lint existing JSON-LD and generate templates. Pure analysis/templating — no network.
Skill Claude CodeCodex
Judge the technical SEO facts produced by seo-crawl and return falsifiable findings + a health score. This is pure analysis — it does no network I/O and only reasons over the crawl JSON.
Skill Claude CodeCodex
Use the bundled Office tools as the default artifact path. Do not install OfficeCLI, pandas, or openpyxl when the built-in tools cover the task.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: