一键导入
trigger-autocomplete-catalog
Use when adding webhook events to make sure integrations properly register the webhook events they carry
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when adding webhook events to make sure integrations properly register the webhook events they carry
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when creating, updating, or reviewing a Workforce cloud persona (`persona.ts` + `agent.ts`) for the current deploy/runtime shape. Covers cloud, useSubscription, integrations with scope mounting/enabledByInput gating/adapter config passthrough, inputs, memory, sandbox modes, onEvent, runtime fields, capabilities, defineAgent triggers/schedules/watch/team-dispatcher launch, provider IO via @relayfile/relay-helpers, multi-transport delivery, ctx.relay messaging, and the deploy flow.
Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup instructions, use https://agentrelay.com/skill and the orchestrating-agent-relay skill.
The canonical way to run agent-relay - self-bootstrap the local broker and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, message-based reading via the relay MCP, and team coordination.
Use when creating, editing, or validating an Agent Relay Factory factory.config.json file, including repo routing, Linear state/team settings, GitHub issue ingestion, live mode, babysitter options, and Relayflows dispatch wiring boundaries.
Use when an agent or human needs to set up relayfile end-to-end so agents can read and write provider files through a local mount. Covers `relayfile setup`, dynamic integration discovery with `relayfile integration available/search`, Nango and Composio backend selection, Atlassian site selection and metadata, cloud login, OAuth/connect flows, mount verification, `RELAYFILE_LOCAL_DIR` handoff, writeback status and retry commands, and key May 2026 cloud-mount gotchas.
Use when an agent is exploring a relayfile mount for the first time or trying to locate a specific resource (Notion page, Linear issue, Slack channel, GitHub PR). Tells the agent to start with `<mount>/LAYOUT.md` and `<provider>/LAYOUT.md` rather than guessing paths from memory, and to use the `by-title/`, `by-id/`, `by-name/`, `by-edited/<date>/`, `by-state/` alias subtrees instead of recursively grepping. Filename convention is `<identifier>__<uuid>` (ticket number / slug first so listings are scannable). NOT for activity-summary questions, which should use the `activity-summary` skill instead.
| name | trigger-autocomplete-catalog |
| description | Use when adding webhook events to make sure integrations properly register the webhook events they carry |
Use this whenever a provider has webhook/event triggers.
The trigger catalog is owned by @relayfile/adapter-core and generated from
adapter sources. It does not live in this (cloud) repo's packages/core -
that's a different package.
import("@relayfile/adapter-core/triggers") exposes
KNOWN_TRIGGER_CATALOG and ADAPTERS_WITHOUT_KNOWN_TRIGGERS.@relayfile/adapter-<provider> package you already work in when wiring a
provider (the relayfile-adapters checkout from the persona's adapter-package
steps). Declaring events is one more edit in that package - no separate
location to track.Ensure persona trigger autocomplete and deploy-time lint include the provider via KNOWN_TRIGGER_CATALOG.
Only providers that actually emit webhook/event triggers belong in the catalog.
Pure storage / polling providers with no event source (e.g. s3, gcs, postgres)
legitimately remain in adapters-without-known-triggers.generated.json - do not
fabricate events for them.
KNOWN_TRIGGER_CATALOG (regenerated catalog.generated.ts).adapters-without-known-triggers.generated.json for missing trigger metadata.eventType and/or the events the cloud
nango-integrations/<provider>-relay syncs subscribe to).supportedEvents(): string[] to the adapter class, or<provider>.mapping.yaml with a top-level webhooks: block whose keys
are the event names (mirror packages/granola/granola.mapping.yaml). The
generator only reads the keys.# Build ALL workspaces first. The generator imports each adapter's
# supportedEvents(); if dependencies/dist are missing, those providers fail to
# import and are silently dropped from the catalog into the gap list. A core-only
# build is NOT enough.
npm ci
npm run build
node --import tsx packages/core/src/cli.ts triggers generate --repo-root .
node --import tsx packages/core/src/cli.ts triggers check --repo-root .
npm run build --workspace=packages/core
node --import tsx --test packages/core/tests/triggers/catalog-generator.test.ts
After the change merges, publish @relayfile/adapter-core (the Publish Package
workflow, e.g. package=core, version=patch). Publishing is what makes the
catalog change take effect - the trigger-autocomplete / deploy-time lint tooling
reads it via its @relayfile/adapter-core dependency. Cloud's
packages/core also depends on @relayfile/adapter-core and has tests that
import KNOWN_TRIGGER_CATALOG; normally no cloud package.json edit is
required because the dependency is a caret range that accepts new patch
releases. Bump Cloud's dependency only when the catalog fix requires a new
minor/major adapter-core version or Cloud needs to pin a specific published
version for CI.
relayfile-adapters#115 when closing missing-provider autocomplete gaps.without-known-triggers list.