orchestrator

Generate and complete reusable security test documents under docs/security/ based on the current project implementation and/or a confirmed plan. Use when a developer asks to complete security test docs, add missing security scenarios, or establish a security test baseline for the project.

Generate and maintain reusable UI/UX test documents under docs/uiux/ based on the current project UI implementation and the design-system constraints. Use when a developer asks to complete UI/UX test docs, add missing UI/UX scenarios, align UI constraints, or wants UI consistency/a11y/responsive regression checks during development.

Guide for working with the Agent Orchestrator — a CLI tool for AI-native SDLC automation. Use when writing or editing YAML manifests (Workspace, Agent, Workflow, StepTemplate, ExecutionProfile, SecretStore, EnvStore, Trigger, CRD), running orchestrator CLI commands, designing workflow step pipelines, writing CEL prehook/finalize expressions, configuring triggers (cron/event-driven task creation), or configuring self-bootstrap workflows. Triggers: any mention of orchestrator config, YAML manifests with "orchestrator.dev/v2", workflow steps, prehooks, finalize rules, task create/start/pause, orchestrator run, step filtering, direct assembly, agent capabilities, StepTemplate prompts, execution profiles, sandbox configuration, secret management, or trigger/cron scheduling.

Govern feature request (FR) documents through their full lifecycle — from planning to implementation to closure. Use when the user asks to govern/治理 a feature request, close an FR, check FR status, or says "治理FR", "/fr-governance". Scans docs/feature_request/ for open FR docs, plans implementation, executes governance, and self-checks closure.

Generate or update QA/security/UIUX test documentation after confirmed feature implementation plans or completed refactors. Use this skill AFTER plan approval or code completion to: (1) add new QA test docs for new behavior, (2) generate design docs, and (3) run repo-wide cross-doc impact analysis (docs/qa/, docs/security/, docs/uiux/, docs/guide/ and its translations, docs/design_doc/, docs/showcases/, root Markdown including CHANGELOG.md, and .claude/skills/) to update stale steps, expectations, and assertions. Triggers when users ask to create QA docs, update test docs after implementation, or sync QA/security/UIUX docs after behavior changes.

Govern and periodically remediate QA documentation quality across docs/qa, docs/security, and docs/uiux. Use when users ask to audit QA docs, run recurring documentation checks, fix doc drift after refactors, enforce scenario limits/checklists/UI entry visibility, or synchronize README/manifest/changelog consistency.

Initialize a brand-new project from scratch with a default full-stack scaffold (Rust core + React Router 7 portal + Docker + Kubernetes). Use when a developer asks to bootstrap an empty repo or start a new project and no specific tech stack is requested.

Create or update integration manifest packages in the companion repo (orchestrator-integrations). Use when a user asks to add a new integration (Slack, GitHub, Discord, Jira, etc.), create a webhook trigger for an external service, or extend the integrations library. Routes all integration work to the separate repo while reusing the main project's SDLC infrastructure.

Generate a Design Brief and corresponding UIUX test documents from user design intent. Use when a user describes a UI/UX idea, wants to design a new screen/feature/app from scratch, asks to create a design brief, or says 'design from UIUX'. This skill turns conversational design intent into structured Design Brief documents (docs/design_brief/) and simultaneously produces matching UIUX test scenarios (docs/uiux/). Triggers on: design intent description, 'create design brief', 'design-first workflow', UI/UX planning requests, or when the user provides wireframes/mockups and wants structured documentation.

Govern Design Brief documents through their full lifecycle — from design review to implementation to visual validation and closure. Use when the user asks to govern a design brief, check design brief status, validate a UI implementation against its brief, or says '治理设计', '/design-governance'. Scans docs/design_brief/ for open briefs, orchestrates review, implementation (pure-frontend or cascading to FR for backend), visual validation via UIUX tests and Playwright, and closure.

Execute formatting and unit-test alignment after large refactors or broad code changes. Trigger when the user explicitly uses the command "-- 对齐测试 --" or asks to align/fix tests after massive modifications. Run formatters, fix code style, run relevant unit tests, analyze failing test cases, update tests and/or implementation, and iterate until stable.

Govern Dependabot dependency upgrade PRs — audit CI, diagnose failures, combine breaking upgrades, rebase, merge, and close. Use when the user asks to handle Dependabot PRs, govern deps, or says '治理依赖', '/dependabot-governance'.

Fix QA tickets by reading docs/ticket/*.md, verifying the issue against real implementation, performing three-way classification (false positive / bug / feature gap), entering plan mode for user approval before acting, applying fixes or creating feature requests as needed, resetting the test environment, re-running QA steps, and deleting the ticket file once verified. Use when a user asks to fix a ticket or resolve a QA failure.

Monitor and evaluate orchestrator test execution plans end-to-end. Use when the user wants to run a test execution plan from docs/showcases/, observe the orchestrator's full-pipeline processing, and get a final assessment. Triggers on: "run test plan", "execute plan", "monitor orchestrator", "test the orchestrator", "run execution plan", "run showcase", or any request to observe/evaluate orchestrator behavior on a showcase plan. This skill is OBSERVE-ONLY — never intervene in the orchestrator's execution.

Execute scenario-based QA testing with optional browser automation, optional database validation, and ticket creation for failures.

Compile-driven user guide alignment. Builds the project, walks the full CLI --help tree, compares against docs/guide/ (EN+ZH), auto-fixes drift, and outputs an alignment report. Use when docs may have drifted from CLI implementation.

Run grpcurl checks from inside the Docker Compose network (useful when host-to-container ports are blocked).

End-to-end deployment workflow for this repo that gates on the latest GitHub Actions run, deploys with deploy/upgrade.sh to Kubernetes, monitors kubectl resources, troubleshoots failures (logs, code, IaC), and performs health checks. Use when the user asks to deploy/release/go-live, says "进行部署", "发布", "上线", or requests a Kubernetes deployment/check.

Run and author Playwright E2E tests for the project (frontend-only or full-stack). Use when the user asks to add E2E tests, run Playwright tests, validate critical user journeys, or stabilize flaky E2E tests.

Run tests, check logs, and troubleshoot services in Docker Compose and Kubernetes environments. Use when debugging local dev env issues, inspecting container/pod logs, restarting services, checking health, or triaging deployment rollouts.

Run lightweight performance/load tests (QPS/latency) against project HTTP endpoints using hey, track regressions, and suggest optimizations. Use when the user asks to benchmark, load test, or measure performance after changes.

Run unit tests and measure test coverage for backend/frontend projects, identify coverage gaps, and improve tests based on project requirements. Use when the user asks to run tests, check coverage, increase coverage, or add missing unit tests.

Consult and apply the repository architecture reference when discussing system architecture, module boundaries, directory layout, service interfaces, Docker Compose, Kubernetes deployment, or operational entry points. Use when a user asks about architecture, refactors, project structure, deployment models, or infra layout.

Consult and apply the project design system when discussing UI design, visual language, design tokens, component variants, accessibility, theming, or styling conventions for the portal frontend. Use when a user asks about design system changes or implementing UI components/styles.

Verify a project is ready for release by checking local Docker Compose startup, Kubernetes manifest sanity, GitHub Actions status via gh, and test/coverage commands. Use when the user asks to confirm readiness, pre-release checks, a release checklist, or to diagnose why CI/build/deploy is failing right before release.

Reset the local Docker Compose development environment to a clean state (rebuild images, drop volumes).

Rust coding conventions and patterns for service development.

Create or improve unit tests and Playwright E2E tests for newly implemented features, and close coverage gaps based on project requirements. Use when the user asks to write/add/complete unit tests, add E2E tests, increase test coverage, or improve existing tests.