tesseract

Use when a skill needs step tracking, progress visibility, and resume support within a single phase. Called by skills, not directly by users.

Use when breaking down a project phase into stories with acceptance criteria, creating ADRs, or planning infrastructure work. Triggers on /plan, story breakdown, detailed plan, architecture doc.

Use when generating, editing, or merging Low-Level Design (LLD) documents at `docs/lld/<component>.md` or `docs/shield/<feature>/lld-<component>.md`. Triggers on /lld command (Path A) and on /plan TRD-driven authoring (Path B, M2 plan). Owns the backend and infra templates, atomic write, provenance stamp, and §14 Changelog convention.

Use when authoring a new PRD or upgrading a lean PRD to standard. Walks user through 20-section problem-first scaffold (or 10-section lean), pre-populates from prior /research transcript if present, defers Terminologies (§2) until after the rest is drafted (auto-fills from research glossary + scan of body), invokes shield:story-coverage between Sections 6 and 8 and shield:milestone-coverage between Sections 8 and 15, prompts for story Type (new/enhancement/existing), supports custom team templates via .shield.json. Triggers on /prd, write a PRD, author a PRD.

Use when the user invokes /backlog or asks to capture, view, promote, or remove an idea from the project backlog at docs/shield/backlog.json. Triggers on /backlog add|view|remove|promote and on agent-side "capture this as a backlog entry" calls during research/PRD/plan/implement flows.

Use when a plan, architecture doc, or execution plan exists and needs expert review before implementation. Produces a scored analysis with a P0-gated verdict and an enhanced plan. Triggers on /plan-review, review my plan, document review.

Use when a PRD exists (file, paste, URL) and needs gap analysis. Dispatches PM, agile-coach, tech-lead, DX, cost reviewer agents in parallel against a 13-dimension rubric; produces scored summary with severity-tiered gaps and P0-gated verdict. Triggers on /prd-review, review my PRD, PRD gap analysis.

Use when code changes need review for security, cost, architecture, or acceptance criteria verification. Triggers on /review, after implementation, pre-merge.

Use when reviewing REST/HTTP or GraphQL APIs for resource modeling, HTTP method semantics, status codes, idempotency, versioning, error response shape, and pagination. Triggers when controllers/handlers/resolvers are in scope.

Use when reviewing backend code for SOLID/DRY/KISS/YAGNI violations, naming, cohesion, and coupling. Triggers when source files in a backend stack (Java, Kotlin, Python, Node/TS, Go) are in scope. Skip for infrastructure code (Terraform, K8s manifests).

Use when reviewing database schema design, migrations, ORM entity definitions, or query patterns. Triggers when SQL files (`*.sql`), migration directories (`db/migration/`, `migrations/`, `alembic/`), JPA entities, or ORM model files are in scope.

Use when reviewing code for error handling, exception flow, logging, metrics, and tracing concerns. Triggers when exception handlers, error responses, logging calls, or observability instrumentation are in scope.

Use when scaffolding milestones for a PRD or for a plan when no PRD milestones exist. Dispatches a PM-lens general-purpose agent and agile-coach in parallel, merges proposals, surfaces conflicts. Consumed by /prd (after stories in Section 8 for standard; after metrics in Section 7 for lean) and /plan (as fallback when PRD has no milestones).

Use when adding or editing any plugin asset in this repo — a SKILL.md, agent definition, slash command, MCP server prompt, hook script, or eval — so the change ships with the required eval coverage and a RED→GREEN paper trail

Use when starting work on a new feature — gathers product + tech context via Q&A walk (Phase 1) with repo auto-detection, then optionally runs external evidence-gathering with citations (Phase 2). Triggers on /research, investigate, compare, evaluate.

Use when authoring or revising any Shield doc — research, PRD, TRD/plan, LLD — to make author-written prose simple, clear, concise, and to the point. Applies to prose only; never rewrites rendered/marker-wrapped sections or JSON.

Use when implementing a feature or story, especially with acceptance criteria to verify. Triggers on /implement, build, create feature, add functionality.

Use when the user asks about sprint planning, syncing plan docs to a PM tool, managing stories/tasks in bulk, or checking sprint status. Triggers on mentions of sprint, sync, stories, PM bulk operations, or epic planning.

Use when scaffolding a .devcontainer/ for Shield. Triggers on /shield init-devcontainer, "set up devcontainer", "isolate /implement".

Use when reviewing Spring Boot configuration code — `@ConfigurationProperties`, `application.yml`/profiles, `@Bean` lifecycle, `@ConditionalOn*`, externalized config, secrets management. Triggers when `application*.yml`/`.properties` files or Spring `@Configuration` beans are in scope and Spring Boot is detected.

Use when reviewing Spring Security configuration — `SecurityFilterChain`, password encoding, CSRF/CORS, method-level security (`@PreAuthorize`), session management, authentication providers, JWT/OAuth2 wiring. Triggers when Spring Security config is in scope.

Use when any workflow needs a product lens — user impact analysis, prioritization, scope discipline, or stakeholder framing. Triggers on product analysis, PM review, user impact, business value.

Use when checking that a PRD's user stories cover all persona-goal combinations and archetypal flows for its feature domain. Consumed by agile-coach reviewer (dim 4 eval points 4f/4g) and /prd author flow. Derives expected stories from personas + goals + domain hints.

Use when reviewing Kubernetes workloads for production readiness, checking probes, PDBs, rollout strategy, or observability. Also use when investigating CrashLoopBackOff, OOMKilled, Evicted, FailedScheduling, or pods stuck in Pending. Only triggers when K8s manifests are detected.

Use when a pipeline phase completes and needs an audit trail summary. Called by other skills, not directly by users.

Use when reviewing Java/Kotlin source for language-idiom concerns — records, sealed types, immutability, var, Optional, exception design, Kotlin null safety, data classes, sealed classes, scope functions, coroutines. Triggers when Java/Kotlin source files are in scope and Spring or other JVM stack is detected.

Use when reviewing Spring Boot test code — test slice selection (`@SpringBootTest` vs `@WebMvcTest` vs `@DataJpaTest`), `@MockBean` overuse, Testcontainers vs H2, `@DirtiesContext` hygiene, security context in tests. Triggers when Spring Boot test files are in scope.

Use when reviewing Spring Data JPA code — `@Transactional` placement and propagation, self-invocation, JPQL fetch strategies, `@Modifying` queries, repository patterns, equals/hashCode on entities. Triggers when JPA repositories or `@Transactional` methods are in scope and Spring Boot Data is detected.

Use when reviewing Spring MVC / WebFlux controllers — `@RestController` patterns, dependency injection style, `@Valid`, `@ExceptionHandler`/`@ControllerAdvice`, `ResponseEntity`, request mapping clarity. Triggers when controllers are in scope and Spring Boot web/webflux is detected.

Use when reviewing code for concurrency concerns — race conditions, lock granularity, async pitfalls, retry idempotency, shared mutable state. Triggers when threading, async patterns, or shared state are in scope.

Use when reviewing code for deployment safety — feature flags on risky changes, backwards-compatible API/schema evolution, rollback paths, blast-radius scoping, multi-instance safety, expand/contract migration patterns. Triggers when migration files, config beans, or production-critical paths are in scope.

Use when reviewing test code for strategy quality — pyramid balance, mock boundaries, fixture/setup correctness, flaky patterns, behavior-vs-implementation tests, missing assertions. Triggers when test files (`*Test.java`, `test_*.py`, `*.test.ts`, `*_test.go`) are in scope.

Use when auditing Kubernetes manifests for security vulnerabilities, reviewing RBAC policies, checking pod security, or validating network policies. Also use when investigating ImagePullBackOff from untrusted registries or permission errors from over-permissive RBAC. Only triggers when K8s manifests are detected.

Use when reviewing Kubernetes manifests for cost optimization, resource right-sizing, or identifying over-provisioned workloads. Only triggers when K8s manifests are detected.

Use when checking Kubernetes manifests for deprecated or removed APIs, planning K8s version upgrades, or migrating manifests to newer API versions. Also use when another K8s review skill flags deprecated APIs.

Use when reviewing Kustomize overlay structure, patch hygiene, and base/overlay separation. Only triggers when kustomization.yaml is detected.

Use when reviewing Helm chart structure, values, templates, and best practices. Only triggers when Chart.yaml is detected.

Use when the user asks about sprint planning, syncing plan docs to ClickUp, managing stories/tasks in bulk, or checking sprint status. Triggers on mentions of sprint, sync, stories, ClickUp bulk operations, or epic planning.

Use when adding, modifying, or reviewing Terraform components in an Atmos components repository - checks for common mistakes like committed provider.tf, missing terraform-docs, broken linting config, or missing baseline variables

Use when reviewing Atmos infrastructure repositories, evaluating IaC structure, or assessing components/stacks organization for quality and best practices