Hub 内嵌浏览器预览 localhost 应用。 Use when: 写前端代码、跑 dev server、需要看页面效果、调 UI、operator说"看看效果"。 Not for: 后端纯 API 开发、不涉及页面的工作。 Output: 前端页面在 Hub browser panel 中实时预览。

Build a Stockbee-style setup model book from momentum-burst screener candidates, then update 3-day and 5-day forward outcomes with MFE/MAE, stop-hit status, outcome tags, and cohort statistics. Use when the user wants to study Stockbee Momentum Burst examples, track failed candidates, build setup fluency, review A/B setup quality, or convert screener outputs into a learning loop rather than immediate trade signals.

Build and maintain a Stockbee-style daily 20% mover study for US equities by scanning +20%/-20% movers, classifying catalysts and setup context, updating forward outcomes, and summarizing cohort patterns. Use when the user asks to run a daily 20% study, backfill historical 20% movers, find recurring edge patterns, or build a model book of explosive market moves.

Analyze recent post-earnings stocks using a 5-factor scoring system (Gap Size, Pre-Earnings Trend, Volume Trend, MA200 Position, MA50 Position). Scores each stock 0-100 and assigns A/B/C/D grades. Use when user asks about earnings trade analysis, post-earnings momentum screening, earnings gap scoring, or finding best recent earnings reactions.

Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.

Query the QuickGO and Evidence & Conclusion Ontology (ECO) REST API. Use this when you need to map genes to biological processes, molecular functions, or cellular components, find genes associated with a specific pathway/GO term, or explore the Gene Ontology hierarchy. Do not use for querying drug targets (use OpenTargets) or mechanistic signaling pathway diagrams (use KEGG).

Query the ENCODE Registry of cis-Regulatory Elements (cCREs) via the SCREEN GraphQL API, or make custom queries to the ENCODE Portal REST API for experiments and files (ChIP-seq peaks, etc.). Use when you want to query regulatory annotations or raw experimental data across human cell types.

Use when the user asks about Liran Tal's talk at AI Native DevCon on skills security — including questions about the lethal trifecta / toxic flows, the Snyk research finding ~30% of ~4,000 Glow skills had security issues, malicious skill examples (SkillGuard, fake Vercel deployment skill, "buy anything", invisible-character Trojan Source skills), the confused-deputy problem, acceptance fatigue, parallels to NPM supply-chain attacks, or how to think about reviewing and sandboxing AI agent skills.

Use when the user asks about the "Welcome to AI Native DevCon" talk introducing Slick (slick.com) — a browser-native agent that controls the browser it runs in. Covers Slick's architecture (sprinkles, scoops, licks, the cone), how it uses HTTP / Chrome Debug Protocol / WebRTC, pyagent as the agentic loop, skills as "step zero of agent enablement", MCP and webMCP support, remote-controlling Electron apps (Slack, Teams, Claude desktop) via Slick Star, ad hoc generative UI, OAuth token handling, and verbatim quotes from the talk. Also use when the user wants to apply this browser-native agent approach to their own work.

Use when the user asks about Maximiliano Firtman's ("Maxi") AI Native DevCon talk on Web MCP and the agentic web — including questions about how Web MCP differs from MCP, exposing frontend tools to AI agents, the imperative vs declarative Web MCP APIs, tool design guidance (name/description/input schema/execute), the Chrome 149 origin trial, using Chrome DevTools MCP or Puppeteer as a bridge today, the Doom demo, or applying Firtman's "pick one high-value page state" adoption approach to current work.

Performs a COMPREHENSIVE, formal security audit of an entire codebase and produces a written audit report (AUDIT-{PROJECT}-{DATE}.md) with prioritized findings (H/M/L) and a remediation plan. Covers SAST, OWASP Top 10, OWASP LLM Top 10, SCA (dependency analysis), Zero Trust validation, code quality. Takes 30+ minutes. TRIGGER ONLY when the user explicitly requests a formal full-codebase audit producing a report: "security audit", "OWASP audit", "full security review", "AUDIT-Report erstellen", "Codebase auditieren", "SCA audit", "dependency audit", "CVE audit", "Sicherheitsaudit". DO NOT trigger for: PR-level security checks (use the built-in security-review skill), one-off security questions, threat-modeling discussions without an audit report, individual finding fixes, or generic mentions of "secure" / "security".

Activates, reconfigures, or deactivates the Digital Innovation Agents workflow in a project. Writes the .dia/config.toml settings file and manages anchor blocks in agent-facing files (CLAUDE.md, AGENTS.md, GEMINI.md, .cursorrules, .github/copilot-instructions.md, .windsurfrules). Use this skill when the user mentions "DIA aktivieren", "DIA installieren", "DIA initialisieren", "DIA setup", "DIA settings", "Workflow-Modus", "Modus wechseln", "DIA off", "DIA deaktivieren", "Plugin aktivieren". Single skill that covers both first-time activation and later reconfiguration; the skill detects which path applies from the presence of .dia/config.toml.

Conducts structured business analyses: problem and stakeholder analysis, as-is/to-be gap analysis, user personas, scope definition. Creates BA documents as the foundation for requirements engineering. Uses innovation phases EXPLORATION, IDEATION, and VALIDATION. Use this skill when the user mentions "Business Analysis", "BA", "Stakeholder Analysis", "Problem Analysis", "As-Is Analysis", "Gap Analysis", "User Personas", "Define Scope", "Analyze Project", "Explore", "How might we", "Value Proposition", "Idea Potential", "Innovation", or similar. Also when the user wants to start a new project and does not yet have a clear requirement. This skill helps understand the problem before discussing solutions.

当用户明确要求"标书QC/质量控制/润色前质检/引用真伪核查/篇幅与结构检查"时使用。对 NSFC 标书进行只读质量控制：并行多线程独立检查文风生硬、引用假引/错引风险、篇幅与章节分布、逻辑清晰度等，最终输出标准化 QC 报告；中间文件默认归档到 `project_root/.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/nsfc-qc/{yyyy-mm-dd-hh-mm}/`，并兼容 legacy `.nsfc-qc/` 读取/清理。

当用户明确要求“写/生成 NSFC 预算说明书”“写预算说明”“生成 budget.tex / budget.pdf”“写国自然预算 justification”时使用。基于用户标书正文或补充材料，输出一份可提交的预算说明书 LaTeX 项目并渲染 `budget.pdf`。若用户未指定工作目录，必须暂停并先要求其指定。⚠️ 不适用：用户只是想了解预算原则；用户仅要预算表数字而不写说明书；或用户是 2026 青年 A/B/C 默认包干制且无需预算说明书的场景。

Grida AI agent system work: `@grida/daemon` (DaemonServer, loopback HTTP perimeter, files/workspaces, secrets store, daemon discovery) and `@grida/agent` (the agent tenant: sessions, providers/BYOK, runtime/tool execution, skills discovery, prompts, tiers, sandbox hosts). Use for `packages/grida-daemon/**`, `packages/grida-ai-agent/**`, desktop sidecar protocol changes, agent chat transport, and bugs in agent state or streams. For pure Electron window, preload, menu, deep-link, or CDP work, use `desktop`.

Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.

NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone with a Mask2Former-style head and 3D frustum reconstruction. Use when training, evaluating, exporting, or running inference for a TAO NVPanoptix3D model. Trigger phrases include "train NVPanoptix3D", "panoptic 3D reconstruction", "3D scene segmentation", "occupancy completion".

Launch the interactive Slang fluoroscopy viewport with XPBD catheter physics. Use when asked to open the viewport, teleop a catheter, or demo fluoro navigation.

Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.