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/war/references/01-design.md
View on GitHub# Design audit
This reference audits the **Target Architecture documents** for a given version against the {{WAF_FRAMEWORK}} pillars. It assesses whether the architecture _as designed and documented_ is sound — not whether the code implements it (use `references/02-implementation.md` for that).
The subject is `docs/Target Architecture (HLD)/{VERSION}/` — container docs, cross-cutting docs, NFRs, sizing. For implementation code audit, use `{{provider:invoke:war}} implementation [VERSION]`. For a single story's design review, the WAF assessment runs inside the `{{provider:invoke:design}}` lifecycle itself (`patterns/waf-review.md`, applied from Solution's gate step) rather than as a standalone command.
> ⚠️ Follow every step in order. Do not skip, summarize, or improvise. If you are unsure, ask before deviating.
## Step 1 — Determine scope
Apply `{{provider:skills_root}}/war/patterns/scope-resolution.md` (fill the placeholder as "Design").
## Step 2 — Read Target Architecture documents
Read all of the following for the target version. Do not ask the developer — read them directly:
**Overview & NFRs:**
- `System Overview.md`
- `Non-Functional Concerns/Requirements.md`
- `System Sizing.md`
**Containers (`Containers/`):** read all files.
**Non-Functional Concerns (`Non-Functional Concerns/`):** read all files.
Do not summarise to the developer. Proceed to Step 3.
## Step 3 — Assess each pillar
Using the architecture documents read in Step 2, assess each pillar in scope. The question for each pillar is: **does the architecture design adequately address this concern?** Flag gaps in the design itself — missing decisions, under-specified failure modes, unresolved trade-offs, or internal contradictions between docs.
### Pillar definitions
{{WAF_PILLARS_TABLE}}
### RAG rating
| Rating | Meaning |
| -------- | ------------------------------------------------------------------------------------------- |
| 🟢 Green | Design adequately addresses this pillar — decisions made, documented, internally consistent |
| 🟡 Amber | Partially addressed — some gaps, open questions, or under-specified areas remain |
| 🔴 Red | Not addressed — material gap in the design that must be resolved |
### Output per pillar
```
### <Pillar name> — <RAG emoji + colour>
**Strengths**
- What the design gets right for this pillar (reference specific doc/section)
**Gaps**
- Specific gaps or unresolved decisions (reference the doc where the gap was found)
**Recommendations**
- P1: resolve before implementation begins
- P2: address in next design iteration
- P3: backlog / nice-to-have
```
## Step 4 — Present, then save
Apply `{{provider:skills_root}}/war/patterns/present-and-save.md` (fill the placeholders as "Design"/"design"), using `{{provider:skills_root}}/war/templates/design-report.md` as the file structure. Replace all placeholders and fill in all audit content.
## Step 5 — Confirm and close
After saving:
> "Design audit saved to `docs/Target Architecture (HLD)/WAR/{VERSION}/{date}-design-audit.md`.
>
> To re-run: `{{provider:invoke:war}} design`
> To scope to one pillar: `{{provider:invoke:war}} design {pillar}` (e.g. `{{provider:invoke:war}} design Security`)
> To audit the implementation against this design: `{{provider:invoke:war}} implementation`"
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 |