DataArt/artisyn-implementation-harness / skills/implementation-harness
implementation-harness
FlaggedInstall the portable AI-dev harness, rebuild its operational graph standalone, harvest project skill improvements into its canonical templates, package direct canonical edits into a portable bundle, or apply canonical updates to an existing project. Use /implementation-harness launch, /implementation-harness reindex-graph, or /implementation-harness patch harvest|prepare|apply.
canonical/skills/design/patterns/design-architect-review.md
View on GitHub# Design — {{DESIGN_ARCHITECT_AGENT}} Review Protocol
After `solution/Architecture.md` is confirmed by the developer, offer to delegate to `{{DESIGN_ARCHITECT_AGENT}}` for a read-only architecture review before beginning `solution/Design.md`. This is the natural gate: Architecture is the highest-level artifact and the hardest to correct once Design and Stack are built on top of it.
## Rules
1. **When to offer** — after Architecture.md is confirmed by the developer, before proceeding to Design.md.
2. **Scope the prompt correctly** — the `{{DESIGN_DOCS_ROOT}}` docs are NOT yet updated during the Solution phase (that happens in Publish). Do not ask `{{DESIGN_ARCHITECT_AGENT}}` to compare against those docs for currency. Evaluate only:
- Structural completeness (components, data flows, integration points)
- Security and reliability fit with the existing platform as currently implemented
- Consistency with existing container/domain boundaries and NFRs
- Missing integration points or failure modes
3. **Explicitly exclude** — tell `{{DESIGN_ARCHITECT_AGENT}}`: "The `{{DESIGN_DOCS_ROOT}}` docs are not yet updated — that happens in Publish. Do not flag documentation gaps as findings."
4. **Max 2 iterations** — if `{{DESIGN_ARCHITECT_AGENT}}` returns findings, address them and re-delegate once. If still unresolved after 2 passes, escalate to the developer.
## Prompt template
> "Read `solution/Architecture.md` and the relevant `{{DESIGN_DOCS_ROOT}}` docs for the areas this design touches. Evaluate the architecture solution itself: structural completeness, security, reliability, and fit with the existing platform as currently implemented. Do **not** flag documentation gaps — those docs are intentionally not yet updated (Publish phase handles that). Return: **OK** or a specific list of gaps (one finding per line)."
## Why
Moving directly from Architecture.md confirmation to Design.md without a `{{DESIGN_ARCHITECT_AGENT}}` gate means that when a structural gap is later found (e.g. via the `patterns/waf-review.md` gate after Design and Stack are already written), corrections cascade across multiple files. An earlier gate catches structural issues cheaply before Design.md locks in the details.
A related pitfall: if the `{{DESIGN_ARCHITECT_AGENT}}` prompt does not explicitly exclude documentation gaps from scope, it will flag intentionally deferred documentation as P1 findings — noise that confuses the publish phase boundary.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |