talos

Standardized backend implementation guidance for BE Dev using the SRS-declared Backend-Track and Backend-Framework. Use when coding, refactoring, or reviewing backend web APIs, BFFs, microservices, workers, jobs, or service integrations in TypeScript with Express, TypeScript with NestJS, Python with FastAPI, Java with Spring Boot, .NET Core C#, Pure Golang, Java Core, Golang with Gin, Golang with Fiber, Golang with Echo, or Golang with Kratos; BE Dev reads docs/SRS.md Backend-Track and Backend-Framework plus §3.4.5 Source Layout, then selects the matching reference so routing, layering, contracts, validation, observability, errors, transactions, and tests match the chosen stack.

How DevOps composes the local Docker environment for QA and operator trials, including port probing, secret-safe env discovery, test-only runtime-reset endpoint verification for direct-DB fixtures, QA deploy-report fields, and human trial URLs without editing project Compose files.

Concrete how-to for QA-Author writing Playwright specs from markdown TCs — project layout, full-state resets for direct-DB fixtures and caches, parallel-worker isolation, contract-aware URL assertions, network mocking, retries, traces, and visual diffs. Consult after `ui-test-execution` when the target surface is web AND the project uses Playwright.

QA-Exec run contract for executing authored test cases against the deployed build. Use when QA-Exec is dispatched for a task in-test to gather by-us/by-task test cases, check executable specs and instrumentation coverage, invoke the proper runner, execute UI tiers, validate visual specs, route failures, and write docs/qa-reports/<task-id>.md plus artifacts.

Codex-native orchestration entrypoint for Evo Talos. Use when the user asks for /sdlc-loop, sdlc-loop, start project, continue the SDLC loop, run the governed workflow, or auto-dispatch eligible SDLC work until the next gate. Acts as the Codex equivalent of the Claude slash command.

Framework-agnostic principles for executing UI tests against the running build — TC-to-spec mapping, selectors, full-state fixture reset across DB/cache/worker state, shared-resource parallelism, determinism, and visual diffs. Consult when QA-Author writes executable specs or QA-Exec invokes a runner against a deployed build.

Codex-native initializer for Evo Talos. Use when the user asks for /sdlc-init, sdlc-init, initialize the SDLC kit, install the kit into the current project, or update the project's AGENTS.md from the plugin. Runs the plugin script, which auto-detects the active agent tool and chooses Codex or Claude project files.

QA-Author procedure for generating docs/uiux/visual-specs/<task-id>.md from confirmed UI/UX handoff and Figma nodes. Use in QA-Author by-task mode for UI tasks before structural test cases, including Design Element Manifest assertions for every visible field/item/copy/action, introspection-aware property assertions, degraded mode, tolerances, coverage map, and staleness checks.

BA Phase 3 — post-sign-off design completeness verification. Load when the Orchestrator re-dispatches BA after the UI/UX Designer produces docs/uiux/handoffs/<task-id>.md (design sub-status design-ready-for-review). Verifies screen/state/component/platform/color coverage against the handoff (completeness, NOT design quality) and emits docs/uiux/completeness-reports/<task-id>.md.

BA Phase 5 — post-implementation completeness verification (UI tasks). Load when dispatched with mode: post-implementation after FE Dev proposes to_status: ready-for-deploy for a UI-bearing task. Cross-references the design-confirmed handoff + task DoD against the FE Dev git diff (and deployed bundle when present) and emits docs/uiux/post-implementation-reports/<task-id>.md with a qualified/unqualified verdict.

Standardized frontend implementation guidance for FE Dev using the SRS-declared Frontend-Framework. Use when coding, refactoring, or reviewing UI work in React Native, ReactJS, Flutter, Vue.js, Angular, or Next.js; FE Dev reads docs/SRS.md Frontend-Framework plus §3.4.2/§3.4.5 for multi-app projects, then selects the matching reference and, for React Native or Flutter, the focused mobile companion skills for implementation, performance, or platform integration.

UI/UX Designer post-sign-off design workflow for `create`, `import`, `revise`, and `incorporate` modes. Produces or refreshes Figma-backed handoff artifacts, SRS Design References Node IDs, and plan updates while respecting Design-Flow A/B/C, Foundation tokens/components, page scoping, canvas lint, and human-edited Figma reconciliation. FE Dev owns `docs/uiux/refs/<task-id>.md`.

Extract requirements and design-system evidence from a Figma file (screens, components, states, exact copy, form fields, interaction flows, design token evidence, accessibility hints) and write to docs/requirements/design-extracted/<figma-file-id>-<ISO-date>.md as additional source corpus for BA synthesis + srs-source-validator coverage check. Use when a PRD references Figma URLs and Design-Flow: A is in effect — runs PRE-BA so BA's first US/FR pass and Design-Guideline selection are informed by what the design already specifies. Strictly read-only against Figma (consumer pattern); strictly inferred-vs-confirmed discipline (no invention).

How to scan a Figma file provided in the SRS and produce a structured mapping of Figma frames/layers to SRS surfaces (User Stories + FRs). Consult when UI/UX Designer is in `map` mode — invoked by BA Phase 1.X pre-sign-off when a Figma URL is present in the requirements. Mapping qualifies surface coverage BEFORE SRS sign-off; task-scoped import handoffs still run before FE work.

Backend logging and traceability standard for BE Dev. Use when implementing, refactoring, or reviewing backend handlers/controllers, services, repositories, workers, schedulers, jobs, queue consumers/producers, external integrations, auth paths, state transitions, retries, or error handling, especially when code has sparse logs, poor operator traceability, missing debug/info/warn/error coverage, missing correlation/request IDs, or weak incident-diagnosis evidence.

Deploy Dockerfile or docker-compose based services for DevOps tasks. Use for local Docker deploys, remote Docker hosts reached through ssh-remote-operations, image build/pull/tag checks, docker compose release directories, health checks, rollback notes, and deploy reports while keeping `.env`, registry credentials, SSH credentials, and compose-resolved secrets out of model context.

Diagnose incidents in deployed environments from a DevOps operating stance. Use when a staging or production-like service is failing, error rates spike, rollouts regress, infrastructure degrades, or operators need timeline, impact, mitigation, rollback, and routing evidence without mutating systems or exposing secrets by default.

Deploy services to a Kubernetes cluster for DevOps tasks. Use when manifests, Kustomize overlays, Helm charts, namespaces, rollout status, kubectl, or kubeconfig under project-root `.k8s/` are involved, while preventing kubeconfig tokens, client keys, Secret manifests, and cluster credentials from entering model context.

Evaluate database, schema, data, queue, index, or storage migrations before deployment. Use when DevOps must verify migration ordering, dry-run results, backups, expand-contract strategy, lock/runtime impact, data-loss risk, rollback constraints, and operator approvals.

Verify that a deployment is observable before promotion. Use when DevOps must check logs, metrics, traces, dashboards, alerts, health endpoints, synthetic probes, SLO/error-budget signals, correlation IDs, runbook links, and incident triage evidence without exposing credentials or sensitive telemetry.

Assess whether a build is ready to deploy or promote. Use when DevOps must verify release candidates, artifact provenance, test evidence, dependency/security gates, environment config, migration and rollback readiness, observability, and approval status before staging or production deployment.

Verify that a deployment can be safely rolled back. Use when DevOps must define previous version, rollback command, data compatibility, feature flag fallback, artifact retention, operator ownership, rollback test evidence, and stop conditions before staging or production rollout.

Audit secret and runtime configuration readiness without exposing values. Use when DevOps must verify required env vars, config maps, secret injection, rotation status, registry/cloud credentials, SSH/Kubernetes credential references, safe templates, and redacted deploy-report config evidence.

Run DevOps remote operations through project-root SSH configuration. Use when DevOps must execute commands, install software or packages, inspect a remote host, stage release artifacts, or prepare a non-local server through `.ssh/config` without exposing private keys, SSH config contents, passwords, or environment secrets to the model.

Deploy and verify software in a staging or testing environment. Use when DevOps must promote a build beyond local deployment, run staging smoke checks, coordinate SSH/Docker/Kubernetes staging rollout, preserve rollback evidence, and produce a deploy report without exposing environment credentials or secrets.

Read when using the Evo Talos SDLC devkit plugin. Defines the orchestrator operating contract, source of truth, SRS sign-off protocol, open-issues gate, and universal hard rules.

SA pre-sign-off procedure for validating and completing docs/external-integrations/<system-slug>.md placeholders. Use when Solution Architect is dispatched in `external-integration-adequacy` mode to fill operations, authentication, NFR posture, failure modes, regional/compliance constraints, adequacy issues, and to set Adequacy: adequate only when complete.

Flutter implementation guidance for FE Dev. Use after fe-framework-coding-standard selects Flutter, when building or reviewing widgets, pages, state, navigation, theming, accessibility, selectors, and ordinary Dart/widget tests without changing native platform channels.

Flutter performance guidance for FE Dev. Use for slow widgets, rebuild churn, jank, large lists, image-heavy UI, animations, startup time, memory pressure, isolates, expensive layout/paint, or performance review of Flutter code.

Flutter native/platform integration guidance for FE Dev. Use when a task touches platform channels, plugins, permissions, flavors, dart-define config, deep links, push notifications, secure storage, app lifecycle, native iOS/Android files, or platform-specific behavior.

Commit discipline for any agent or human committing to this repo. Verify identity before the first commit, follow the conventional-commits format with task traceability, exclude secrets via .gitignore, attribute human and AI contributors honestly.

QA-Author by-task mode procedure. Use when QA-Author is dispatched for a master-plan task after TL, and after design-confirmed for UI tasks, to author task-scoped structural/api/e2e/functional test cases under docs/test-cases/by-task/<task-id>/ and coordinate visual-spec generation for UI tasks.

QA-Author by-us mode procedure. Use when QA-Author is dispatched after SRS sign-off to author User Story scoped functional test cases under docs/test-cases/by-us/<US-ID>/, create executable spec scaffolding, perform Pass 1 selector TODO marking, or perform Pass 2 selector backfill from docs/instrumentation-contract.md.

React Native and Expo implementation guidance for FE Dev. Use after fe-framework-coding-standard selects React Native, when building or reviewing screens, components, navigation, state, styling, accessibility, selectors, and ordinary tests without changing native modules.

React Native and Expo performance guidance for FE Dev. Use for slow screens, large lists, image-heavy UI, animations, startup time, memory pressure, expensive renders, bridge/native-module overhead, or performance review of React Native code.

React Native and Expo native/platform integration guidance for FE Dev. Use when a task touches Expo config, native iOS/Android files, permissions, deep links, push notifications, secure storage, app lifecycle, native modules, build settings, or platform-specific behavior.

SA design-mode procedure for producing docs/architecture.md, ADRs, and docs/instrumentation-contract.md from a signed-off SRS. Use when Solution Architect is dispatched in `design` mode after SRS sign-off to create or revise greenfield architecture, choose dependencies through the approval gate, define C4 C1-C3, API/data/async/cross-cutting sections, and establish format-boundary and gate-field contracts.

SA extract-mode procedure for brownfield onboarding Stage 2. Use when Solution Architect is dispatched in `extract` mode before SRS exists to turn Codebase Archaeologist reports and existing code/docs into a provisional docs/architecture.md with Source: extracted and confidence tags, plus extracted API/message contract stubs, route/dependency/async workflow coverage, and confirmation-pending open issues.

BA ingestion backbone run on every ingestion dispatch (after the mode-specific setup skill). Contains Phase 1.X common procedure (structural conformance, US/FR pairing, self-containment, external-integration identification, Design-Flow + Design-Guideline + Frontend-Framework + Backend-Track/Framework detection), Phase 1.Z delta detection (iteration trigger), and Phase 2 sign-off gate (caps at Ready-for-Sign-off; BA never self-signs-off).

How to build a Figma Foundation page (design tokens + reusable components) BEFORE drawing screens, so spacing / text sizes / button styles / element alignment stay consistent across every surface. Consult on every UI/UX Designer dispatch (create / revise / import / incorporate). Pre-handoff token-compliance lint mandatory in every mode.