stark-ai-de/agent-skills / plugins/stark-ai-developer/skills/architecture-zoom
architecture-zoom
VerifiedPlan a product or feature as a readable architecture blueprint and complete product increments. Use when the user needs a whole-product view, progressive detail, module contracts, or an MVP delivery map. Not for direct implementation, codebase audits, or exhaustive implementation specs.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.4 KB |
| agents/openai.yaml | config | 620 B |
| assets/blueprint-template.md | markdown | 3.7 KB |
| assets/openai-icon.png | binary | 6.0 KB |
| assets/openai-icon.svg | other | 860 B |
| assets/work-item-template.md | markdown | 2.6 KB |
| references/design-contracts.md | markdown | 5.1 KB |
| references/orchestration.md | markdown | 2.0 KB |
assets/blueprint-template.md
View on GitHub# `<Product or feature>` blueprint
> Derived working template, not an accepted ADR or evidence of implementation. Use only relevant sections. Replace placeholders; do not invent facts to fill them.
## Overview
**Purpose and audience:** `<problem, user, intended benefit>`.
**Agreed target breadth:** `<all essential capabilities and core journeys>`.
**Current state:** `<what exists, with evidence>`.
**Non-goals:** `<explicit exclusions>`.
**Next usable increment:** `<complete bounded user promise>`.
**Important uncertainty:** `<risks and unresolved decisions visible at this level>`.
Navigation: [Structure](#structure) · [Delivery](#delivery) · [Contracts](#contracts) · [Evidence and decisions](#evidence-and-decisions)
## Structure
| ID | Responsibility | Interactions | Authoritative contract |
| -------- | ------------------------------- | ------------------------------------------------ | ---------------------- |
| `<M-01>` | `<one coherent responsibility>` | `<required inputs/outputs and other module IDs>` | `<link>` |
Describe one central end-to-end journey. A diagram may clarify the same relationships; do not introduce undocumented modules or hide external dependencies in it.
## Delivery
| Increment | Complete user promise | Included journey and dependencies | Excluded variants | Acceptance and recovery |
| --------- | -------------------------------- | ---------------------------------- | -------------------- | -------------------------------------------------- |
| `<R-01>` | `<independently useful outcome>` | `<existing + this increment only>` | `<scope boundaries>` | `<demonstration, failures, recovery, environment>` |
| `<R-02>` | `<next useful outcome>` | `<R-01 plus new work>` | `<deferred scope>` | `<planned proof, not a result>` |
**Closure check:** Does any increment need a later increment to fulfill its own promise? Fix the slice or narrow the promise before calling it an MVP.
**Enablers/POCs:** `<question or dependency, consuming increment, effort limit, stop/cleanup condition>`. These are not automatically product increments.
## Contracts
### `<M-01: name>`
**Parent and responsibility:** `<ID, purpose, exclusions>`.
**Interface:** `<inputs, observable outputs, errors, side effects>`.
**Required behavior:** `<invariants and conditions>`.
**Dependencies:** `<required guarantees and cross-cutting constraints>`.
**Decision status:** `<proposed/accepted, source and owner>`.
**Evidence:** `<claim, source, revision, environment, result, limitations; or not available>`.
**Planned acceptance:** `<scenarios not yet run>`.
**Open risks:** `<decision-relevant assumptions and questions>`.
**Drill-down:** `<links; deferred details and revisit triggers>`.
## Evidence and decisions
| Claim or requirement | Kind | Owning contract/journey | Decision or evidence reference | Limitation / next check |
| -------------------- | ------------------------------------------------------------------- | ----------------------- | ------------------------------ | ------------------------- |
| `<statement>` | `<requirement/assumption/proposal/accepted decision/observed fact>` | `<ID>` | `<reference or missing>` | `<scope and uncertainty>` |
**Consistency review:** `<coverage, composition, conflicts, invalidated evidence>`.
**Still unknown:** `<material unanswered questions only>`.
**Next bounded action:** `<selected slice or missing prerequisite>`.
**Persistence:** `<requested/not requested/pending/saved with read-back; no implied implementation approval>`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |