Websoft9

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Strategic business analyst and requirements expert. Use when the user asks to talk to Mary or requests the business analyst.

System architect and technical design leader. Use when the user asks to talk to Winston or requests the architect.

Senior software engineer for story execution and code implementation. Use when the user asks to talk to Amelia or requests the developer agent.

Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.

Technical documentation specialist and knowledge curator. Use when the user asks to talk to Paige or requests the tech writer.

UX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer.

Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.

Use when working on a Websoft9 docker-library issue, update, new app, bug, archive, restore, or batch task. Routes the issue's hidden workflow marker to the canonical workflow documents and skills under skills/.

Use when the user wants to implement an approved app update after assessment, update one app to a target version, adjust app files, run validation, and produce a short test report. Trigger phrases: update app, implement update, 升级应用, 更新应用, update <app> to…

Use when the user wants to update a batch of apps in one run, using either an explicit app list or one or more starting letters such as n,m to target all apps whose names start with those letters. Orchestrates per-app updates through the existing app-update…

Use when an app package has been created or changed and must be proven deployable. Runs structure/policy gates, docker compose deploy, reachability, and log checks, and returns validation evidence. Trigger phrases: run validation, deploy check, validate…

Use when the user wants to install one app package with a repeatable runbook, choose local vs remote host, pre-check and allocate server ports (prefer 9000-9999), verify Docker Compose deployment health, and return access URL plus backup reminders. Trigger…

Use when the user wants to add one new application package, create a new app from official deployment docs, or asks for a new app implementation workflow. Trigger phrases: new app, create app package, add app, 新应用, 新增应用.

Use when the user wants to assess whether an app is worth updating, check for a newer upstream version, or asks for an update decision before implementation. Trigger phrases: update assessment, assess update, 更新评估, 是否值得更新, check if <app> is worth updating.

Use when the user wants to create or update one app's repo commercial data file under metadata/catalog, choose catalog bindings, and preview the Contentful push. Trigger phrases: catalog data, 商业数据, catalog file, create catalog metadata, 更新商业文案.

Interactive escalation-resolution workflow for the bmad-loop orchestrator. A bmad-loop run paused on a CRITICAL escalation (a contradiction or gap a dev/review session could not safely resolve alone); you and the human disambiguate the frozen spec so the…

Sets up BMAD Loop Skills module in a project. Use when the user requests to 'install bmad-loop module', 'configure BMAD Loop Skills', or 'setup BMAD Loop Skills'.