Loading...
Loading...
Found 1,743 Skills
Platform basic capabilities exclusively for Feishu CLI, not a universal fallback for all Feishu requests. Covers configuration initialization, OAuth login and Token/Profile management, doctor diagnosis, OpenAPI schema query, general API pass-through, global search, as well as user and department queries. This Skill must be used when users mention Feishu login, Device Flow, scope, User/Tenant Token, Token expiration, profile, doctor, 99991672/99991679, querying API path/parameters/scope, raw api, calling unencapsulated OpenAPI, searching documents/messages/apps, or querying users, emails, departments. It is explicitly prohibited to use this Skill for document content, cloud disk files, messages/group chats, Sheet/Bitable, whiteboard/presentation, calendar/task/approval/attendance/OKR, email, or meetings/Miaoji; these business operations should be handled by corresponding domain Skills. The "global search" here only refers to `search docs/messages/apps`, excluding queries within business domains such as approval, meetings, email, etc. When a request involves approval, approval_code, approval definition/instance/todo, this Skill must not be used; use feishu-cli-work instead. When video conferences, Miaoji, minute, recording or verbatim transcripts are involved, use feishu-cli-meetings instead.
Unified entry for Feishu Visualization and Display, responsible for selecting appropriate carriers, and covering whiteboard, Slides, Miaobi BOX dynamic components, Miaoda HTML applications, and unified data visualization design specifications. This Skill must be used when users request whiteboard/whiteboard, architecture diagrams, flowcharts, flywheels, fishbone diagrams, roadmaps, posters, illustrations, SVG/Mermaid, data charts or dashboards, creating Slides/PPT, embedding dynamic ECharts/maps/3D/window.magic components, or publishing HTML applications with Miaoda/Miaoda/spark. Message cards are constructed and sent by feishu-cli-messaging; Markdown chart import is executed by feishu-cli-docs.
Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges experience against product personas, and writes a durable dogfood report. Manual invocation only.
Use when creating or changing a Bagisto payment method — a payment class, the payment methods config, the checkout redirect and callback flow, or integrating a gateway such as Stripe or PayPal. Trigger phrases include "payment", "payment method", "payment gateway", "Stripe", "PayPal", "Razorpay", "checkout payment", "redirect", "webhook".
Use when building an admin app or UI on the Bagisto Admin API — a back-office dashboard, an order, catalog, customer, marketing, CMS or settings management screen, an admin mobile app, the Create-Order flow, or any admin panel page on the API. Ask the client's platform and stack first, and treat the api-docs as the source of truth for exact shapes. Trigger phrases include "admin orders", "admin products", "customers", "cart rules", "CMS", "settings", "reporting", "admin panel on the API".
Sketch the load-bearing architecture of a complex change as real code stubs - whatever decisions drive the rest of the work (schema, API surface, interfaces, data flow, module boundaries...) - without filling in implementation details. The user reviews and iterates on the skeleton interactively, then hands it to the "ship" skill to implement fully. Use when the user says "probe", "probe this", "sketch the architecture first", or wants to agree on the high-level shape of a complex change before full implementation.
Use this skill whenever the user wants to use AI agents to work with Penpot design files via the Penpot MCP Server. Triggers include: using Penpot through an AI agent, design files, design systems, design tokens, Penpot MCP, design-to-code, generating UI from design, auditing a design system, creating components/variants, renaming layers, exporting assets from Penpot, adding flows, interactions, animations, overlays, or prototyping in Penpot, or prompting an AI agent to read/modify a Penpot file. Also triggers when the user wants to set up Penpot MCP, connect any MCP-compatible AI agent or IDE to Penpot, or produce production-ready HTML/CSS/React from a Penpot design. Use this skill for Penpot-agent workflows — design, code, audit, prototyping, or setup.
Create and modify editable draw.io / diagrams.net diagrams (.drawio XML), output .drawio + PNG/PDF. Three approaches: use built-in templates (5-band technology roadmap, 3-column research framework diagram, 3-column stage flow chart, horizontal task pipeline diagram), write XML from scratch, high-fidelity replication of reference diagrams. Use this when users request technology roadmaps, full-text overviews, research framework diagrams, paper flowcharts, algorithm flowcharts, model/system architecture diagrams, method schematics, turning papers or projects into a single diagram, defense diagrams, or request to draw drawio diagrams, redraw a reference diagram into an editable vector diagram, or fix diagrams (text overflow/arrow misalignment/inconsistent color scheme/misaligned layout). For line charts, heatmaps and other data charts, please use scibox-figure instead.
Map a codebase into a structured vocabulary — surfaces, features, entities, flows, compartments, invariants, tech stack — plus code-health metrics. Produces a JSON map and an interactive local UI. Use whenever the user wants to understand or audit a codebase.
Use when you know what component, flow, or interface you need but not yet the right accessibility approach. Best for turning WCAG 2.2 requirements into an accessible implementation plan with WAI-ARIA APG patterns before code hardens bad interaction and state patterns.
Use when you have an existing component, flow, or interface and need an evidence-backed accessibility design review after basic checks pass. Best for WCAG 2.2 compliance, focus management, ARIA pattern quality, semantics, and state communication gaps automated tools miss.
This skill should be used when the user asks to design a Phaser 4 game, plan game architecture, structure scenes, organize game state, define scene flow, choose module boundaries, or review/refactor an existing Phaser project architecture before implementation.