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/TEMPLATE.md
View on GitHub---
name: war
metadata:
version: 2.0.0
description: Well-Architected Review ({{provider:invoke:war}} [design|implementation] [VERSION]). Prompts design vs implementation if ambiguous, then follows the matching reference exactly. @architect assesses against the configured {{WAF_FRAMEWORK}} pillars.
---
The developer wants to run a Well-Architected Review. Here is their input:
---
## {{provider:input}}
---
> ⚠️ Follow every step in order. Do not skip, summarize, or improvise. If you are unsure, ask before deviating.
## Route
Parse `{{provider:input}}` into an optional leading stage word and the remaining version/pillar input:
- `design {input}` or a leading `d` → follow `references/01-design.md` exactly
- `implementation {input}` or a leading `impl`/`i`/`code` → follow `references/02-implementation.md` exactly
- A version only (e.g. `MVP`, `V1`), or no argument → present the options below and ask which audit to run
Present:
> "Which audit would you like to run?
>
> - **A — Design audit** (`{{provider:invoke:war}} design`): reviews Target Architecture documents against WAF pillars. Use this to validate the design before implementation begins, or to assess an existing design version.
>
> - **B — Implementation audit** (`{{provider:invoke:war}} implementation`): reviews the codebase against the Target Architecture. Use this to find gaps between design intent and what was built.
>
> (**A** / **B** / **both**)"
**Stop and wait.** Then follow the selected reference exactly (both, in sequence, if "both").
**Compatibility:** `/war-design`, `/war-implementation` are retired as separate skills — use `{{provider:invoke:war}} design|implementation [VERSION]` instead.
---
## Companion
For a delivery gap view across all three dimensions (designed / implemented / documented):
```
{{provider:invoke:where-we-are}}
```
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: 471k | 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 |