Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.

Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.

Open Plannotator's browser-based code review UI for the current worktree, another directory, or a pull request URL, then act on the feedback that comes back.

Open Plannotator's annotation UI for a markdown file, plain-text config file (.yaml, .json, .toml, .ini, .csv, .log, …), HTML file, URL, or folder and then respond to the returned annotations.

Adding custom GraphQL queries and mutations using GraphQLSchemaFactory. Use this skill when the developer wants to add custom GraphQL endpoints, create custom queries or mutations, add business logic to the API layer, build custom resolvers, inject backend services (identity, tenancy, CMS use-cases) into their GraphQL schema, add authorization checks to resolvers, or build dynamic GraphQL inputs from CMS models. Covers the full pattern from simple queries to complex resolvers with dependency injection and permission transformers.

Creates and updates OrchardCore admin edit views using the ocat-* CSS class conventions. Use when creating or modifying Edit view files (*.Edit.cshtml, *.Fields.Edit.cshtml) to ensure correct layout and styling.

小红书私信会话、单聊与群聊历史、未读、文本收发、标记已读、撤回消息及删除会话；复用 xhs-hunter PC 会话。

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents under .trellis/agents/, selectable workflow templates, registry-backed spec refresh, cross-session memory (trellis mem) generated by trellis init, or AI-facing bundled skills (trellis-channel, trellis-session-insight, trellis-spec-bootstrap) and bundled-skill auto-dispatch flow.

Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents under .trellis/agents/, selectable workflow templates, registry-backed spec refresh, cross-session memory (trellis mem) generated by trellis init, or AI-facing bundled skills (trellis-channel, trellis-session-insight, trellis-spec-bootstrap) and bundled-skill auto-dispatch flow.

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

Frontend and UI work in www and surfsense_local/frontend — building, refactoring, styling, animating, or reviewing React and Next.js components, shadcn/ui, color tokens and themes, visual polish, and motion. Load this first for any UI task, including adding or changing a shadcn/ui component (dialog, button, dropdown, form, sidebar, table) in a tree with components.json — it owns the color palette, polish rules, and the precedence order, then routes to the separate shadcn skill for component wiring and the CLI. Use for any frontend component, page, style, animation, hover state, icon, layout, or UI review task.

Use before any edit under content/docs, including a one-line fix to existing advice, a Chinese twin or an embedded demo, and to write or audit Plate public documentation, page design, examples, installation, MDX and navigation.

Remove bracketed NemoClaw tags from GitHub issue and PR titles. Use for a requested title cleanup.

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin manager (ov-install as backup), wizard-based configuration, slot activation, gateway restart, verification, multi-tenant root keys, multi-instance and uninstall. The user needs no CLI knowledge — the agent runs everything and only asks for a few values. Assumes the OpenViking server is already running; it does NOT install the server. Trigger on: "install OpenViking", "set up memory", "configure memory plugin", "add long-term memory", "semantic memory", "RAG", "帮我装 OpenViking", "配置记忆插件", "安装记忆功能", "接入 OpenViking".

Maintain resumable task records, select repository verification profiles, inspect revision-bound receipts, and carry work between coding agents. Use for substantial SDK or CLI work spanning sessions, evidence review, or carrying work between coding agents; use package-specific skills for implementation and ordinary small edits.

Create, modify, test, or package Python provider adapters under python/providers, including framework-specific dependencies, public imports, type inference, and provider metadata. Use for Python provider work only; use python-sdk for core SDK changes.

Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs. Use for early-stage research brainstorming or prioritizing candidate directions; hand off empirical validation, study design, ethics or regulatory review, and clinical questions to appropriate experts or skills.

Apply the firm's KYC/AML rules grid to a parsed onboarding record — assign a risk rating, list every rule outcome with the rule cited, and flag what's missing or escalation-worthy. Use after kyc-doc-parse; this skill decides nothing, it scores and routes.

Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.