orchestration
Automatically use enabled Workbench Roles for useful delegation in ordinary tasks when no registered Workflow matches.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 490
01 前言 Front Matter
- name
- orchestration
- description
- Automatically use enabled Workbench Roles for useful delegation in ordinary tasks when no registered Workflow matches.
02 资源文件 1
- 参考文档agents/openai.yaml257 B
03 SKILL.md 正文
Use Workbench Roles in ordinary tasks
Automatic Role delegation is the default whenever this plugin is loaded. The user does not need to ask for a Role or name one. When no Ready Workflow matches a concrete request and a helper would materially help, select and launch an enabled Role through the procedure below.
A Role is a saved way to assign one helper. It says what kind of work the helper is suited for, which configured model to use, what it may change, and the instructions it receives. It does not start a Workflow.
Choose the least complex adequate enabled Role from its description and configured Provider suitability. Routine inspection, documentation and checklist work do not justify a difficult-planning model. Reserve Astra / medium for concrete difficult planning, novel causal diagnosis or unresolved design tradeoffs; retain the user's configured model when compiling the chosen Role. User intent, task routing, conversation coordination and final acceptance remain with the primary Agent. Role delegation does not turn those duties into an isolated worker assignment.
If no Ready Workflow matches a concrete request and
one helper would materially help, call workflow_role_templates, select the one
enabled Role whose description fits the work, and call workflow_role_template
for that Role only. Pass the complete task boundary, owned files, constraints,
and verification. Do not load every Role's instructions.
For a native Role, launch exactly the returned adapter.spawn_config with
spawn_agent and send the returned instructions. Do not replace the selected
model, effort, access, or fresh-context setting. For another enabled Provider,
follow the returned adapter and its actual tool route. If the route is not
available, report that error; do not silently substitute another helper.
The primary Agent keeps responsibility for the user's intent, task split, integration, verification, and final answer. After launch, it first completes useful work that is independent of the helper's result and owned files. When the next action depends on the helper, wait for an event with the longest supported timeout, up to one hour. Completion or user input wakes the wait. Do not poll, reread the same inputs, or repeat planning while waiting. Inspect the actual changes and verification evidence after the helper finishes.
Use one Role for one clear assignment. Add another only for independent parallel work or when the user requested an independent review. A failed assignment may be corrected with the same helper when the remaining work is local to that assignment; do not replay accepted work.
Workflow nodes are separate. Generation uses the registered Provider suitability catalog and Host routing rules. A running node receives its pinned Provider and node task, without a Workbench Role prompt. Never inject Role instructions into a Workflow node.
04 同仓库更多 Skills
migrate-to-e2e
Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.
e2e
Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.
create-verification-skill
Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.
deja-search
deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.
deja-reflect
End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
revid
Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.