后端与 API
后端服务、API、Webhook 和服务端工具
Skills 列表

qianwen-payment
QianWenAI cash balance query and fixed-amount Alipay recharge orchestration. Owns the outer recharge lifecycle while delegating the payment-side step to `alipay-payment-skill` when selected. Covers balance, recharge orders, order results, recharge history, missing current-order QR recovery, Token Plan redirects, and recharge page guidance. TRIGGER when: explicit QianWenAI balance query, confirmed recharge request with amount, model-call error explicitly reporting insufficient QianWenAI balance or account overdue, recharge result/history query, the user reports that the current QianWenAI recharge QR was not displayed, Token Plan purchase redirect, user wants guidance for the QianWenAI recharge page, or user explicitly invokes this skill by name (e.g. use qianwen-payment). DO NOT TRIGGER when: usage/billing/subscription queries (use qianwen-usage), incoming Alipay payment links or unrelated merchant orders (use alipay-payment-skill), refunds, non-QianWenAI products.
qianwen-ai
comfyui-workflow-builder
Generate, build, create, or design ComfyUI workflow JSON from natural language descriptions. Produces valid node graphs with correct class_types, connections, output indices, and model-appropriate settings. Handles txt2img, img2img, inpainting, ControlNet, LoRA stacking, upscaling, and face detailing pipelines. Does NOT cover ComfyUI installation, custom node development, Python scripting, model training, hardware advice, or architectural explanations.
mckruz
comfyui-api
Connect to a running ComfyUI instance, queue workflows, monitor execution, and retrieve results. Supports both online (REST API) and offline (JSON export) modes. Use when executing ComfyUI workflows or checking server status.
mckruz
supabase-server
在规划或编写使用 `@supabase/server` 的服务端代码时使用——包括 Edge Functions、Hono 应用、Webhook 处理器,或任何创建 Supabase 客户端或验证入站认证的后端。在编写或修改任何从 `@supabase/server`(或子路径如 `@supabase/server/core`)导入的文件之前触发;调用 `withSupabase`、`createSupabaseContext`、`createAdminClient`、`createContextClient`、`verifyAuth`、`verifyCredentials` 或 `extractCredentials`;配置 `auth:` 模式(`'none'` | `'publishable'` | `'secret'` | `'user'`,或带键的变体如 `'secret:*'`);或位于 `supabase/functions/` 下并验证入站请求。在规划期间也触发——如果计划中提到上述任何内容,请在起草代码前加载该技能;不要从相邻函数推断 `auth:` 值或认证模式。当看到需要迁移到此包的遗留模式时也触发——`Deno.serve`、`createClient(Deno.env.get('SUPABASE_URL'))`、从 `esm.sh/@supabase` 或 `deno.land/std` 导入、使用 `SUPABASE_ANON_KEY` / `SUPABASE_SERVICE_ROLE_KEY`,或已弃用的 `allow:` 配置选项 / 已移除的 `'always'` / `'public'` 模式值 / 已移除的 `authType` 字段。
supabase
software-solution-architecture
Designs cross-system target states and transition plans from business workflows and system boundaries. Use when comparing end-to-end solution options or phased migrations.
vasilyu1983
claude-peers-mcp
Enable multiple Claude Code instances to discover each other and exchange messages in real-time via a local broker daemon and MCP server.
reason-machines
sent
Routes broad or ambiguous Sent requests to the correct MCP-backed operation or specialist skill. Use when the user asks what Sent can do, says "help me with Sent" or "set up messaging," needs several Sent workflows, or has not made the channel, task, or desired operation clear enough to select a more specific skill.
sentdm
waba-template-author
Writes, classifies, validates, and repairs WhatsApp templates using the Sent v3 template definition contract. Use for utility, marketing, authentication, OTP, Meta review, rejected templates, variables, buttons, channel overrides, or submission-ready Sent payloads.
sentdm
messaging-performance-analyzer
Analyzes Sent message delivery, webhook, and activity data to explain funnel drop-offs, delivery failures, read-rate gaps, channel fallback, and suspicious performance changes. Use when a user says MDR, delivery report, message activity, webhook event, failed messages, low delivery rate, RCS fallback, WhatsApp read rate, SMS filtering, campaign performance, or asks why messages did not arrive.
sentdm
sender-profile-architect
Designs Sent Sender Profile architecture for multi-tenant, multi-brand, and multi-channel systems. Use for API-key scoping, x-profile-id, isolation, inheritance, sharing, billing, WABA, 10DLC campaigns, webhooks, or tenant offboarding.
sentdm
sms-10dlc-registration
Prepares and validates Sent US A2P 10DLC brand and campaign registration through Sender Profiles, including inheritance, all campaign use cases, opt-in evidence, sample-message policy, autoresponses, sandbox validation, TCR status, and rejection remediation.
sentdm
sent-two-way-messaging
Designs inbound and conversational Sent flows — opt-out and opt-in keyword handling, consent state on contacts, auto-replies inside the WhatsApp 24-hour window, RCS STOP chips, conversation history retrieval, and per-channel inbound capability. Use when handling message.received events, implementing STOP or HELP behavior, restoring consent after an opt-out, building a support inbox or chatbot on Sent, or paginating conversation history.
sentdm
sent-routing-strategist
Decides how a Sent message should reach the recipient — automatic routing versus a pinned channel, what the channel array actually does, how fallback and reroute work, and why a message ended as FAILED, FILTERED, BLOCKED, or channel "auto". Use when choosing the channel field, expecting WhatsApp-to-SMS fallback, debugging an unexpected route or duplicate charges from multiple channels, or interpreting message status and activity evidence.
sentdm
sent-integration-starter
Stands up a production-ready Sent v3 integration in an existing codebase — SDK selection and client construction, x-api-key configuration, idempotent sends, retry and rate-limit handling, the 46-code error catalog, sandbox verification, and a verified webhook receiver. Use when adding Sent to an app for the first time, choosing an SDK or framework wiring, handling 429 or 409 responses, deciding what to log, or hardening an integration before launch.
sentdm
sent-webhook-engineer
Builds and debugs Sent v3 webhook receivers end to end — endpoint registration, HMAC signature verification, replay rejection, event dedupe, retry and auto-disable behavior, secret rotation, and delivery-log triage. Use when handling Sent webhook events, verifying x-webhook-signature, fixing 401 or signature-mismatch failures, recovering a disabled endpoint, choosing event_types or event_filters, rotating a signing secret, or interpreting the webhook delivery log.
sentdm
sent-profile-provisioning
Executes the Sent Sender Profile lifecycle over the API — creating profiles with the right inheritance, sharing, billing, and WhatsApp options, driving profile completion and its callback, managing 10DLC campaigns per profile, and administering users and roles. Use when calling POST /v3/profiles, handling a completion callback or unclear profile status, choosing inherit or dedicated resources, wiring per-tenant onboarding, or inviting and role-managing users.
sentdm
neon
Neon平台概述,涵盖Postgres、Auth、Data API以及新服务:对象存储、计算函数和AI网关。当提到“Neon”或其任何单个能力(如“对象存储”或“S3”、“存储桶”、“无服务器函数”、“AI网关”、“调用LLM”、“postgres”、“数据库”或“后端”)时使用。
neondatabase
asr
Transcribe audio files to text using local speech recognition. Triggers on: "转录", "transcribe", "语音转文字", "ASR", "识别音频", "把这段音频转成文字".
marswaveai
edict-multi-agent-orchestration
Install and use the Edict (三省六部) multi-agent orchestration system with 12 specialized AI agents, real-time kanban dashboard, and audit trails
reason-machines
metaclaw-evolving-agent
Deploy and configure MetaClaw — an agent that meta-learns and evolves from live conversations using skills injection, RL training, and smart scheduling.
reason-machines
voicebox-voice-synthesis
Expert skill for Voicebox — the open-source local voice cloning and TTS studio built with Tauri, React, and FastAPI
reason-machines
crucix-intelligence-dashboard
Personal intelligence agent that aggregates 27 OSINT data sources into a self-hosted Jarvis-style dashboard with Telegram/Discord bots, LLM analysis, and real-time alerts.
reason-machines
mirofish-offline-simulation
Fully local multi-agent swarm intelligence simulation engine using Neo4j + Ollama for public opinion, market sentiment, and social dynamics prediction.
reason-machines
modly-image-to-3d
Desktop app that generates 3D models from images using local AI running entirely on your GPU
reason-machines