where-we-are · v0.3.1 · 2026-09-16 · sha256 145499c015e21472
where-we-are v0.3.1A
Immutable. This exact content never changes and is served at /api/v1/blob/145499c015e21472.
---
name: where-we-are
metadata:
version: 0.3.1
description: Delivery gap report (/where-we-are or "what's implemented vs designed?"). Compares HLD containers vs LLD docs and the codebase. Saves snapshot to docs/System Architecture (LLD)/where-we-are/.
---
The developer wants to see the current delivery gap between Target Architecture (HLD) and System Architecture (LLD). Here is their input:
---
## $ARGUMENTS
---
> ⚠️ Follow every step in order. Do not skip, summarize, or improvise. If you are unsure, ask before deviating.
---
## Overview
This skill produces a **delivery gap report**: what has been designed in Target Architecture (HLD) vs what has been documented in System Architecture (LLD) vs what exists in the codebase (the NX monorepo under `apps/`).
It answers the question: _"Where are we relative to where we want to be?"_
Three dimensions are assessed per container:
| Dimension | Source | Meaning |
| --------------- | --------------------------------- | ----------------------------------------- |
| **Designed** | `docs/Target Architecture (HLD)/` | Container is defined in the HLD |
| **Documented** | `docs/System Architecture (LLD)/` | Container has LLD docs (populated folder) |
| **Implemented** | the NX monorepo under `apps/` | Code exists for this container |
Gaps between these three dimensions indicate delivery debt, documentation debt, or both.
---
## Step 1 — Determine scope
Read `docs/Target Architecture (HLD)/README.md` to find the **current active version**.
Parse `$ARGUMENTS`:
- If a version is given (e.g. `MVP`): use that version
- If no argument: use the active version
Present:
> "Generating delivery gap report for **\<VERSION\>**. Confirm? (**yes** / **no**)"
**STOP. Do not read any files or take any further action until the developer confirms.**
---
## Step 2 — Read Target Architecture (HLD)
Read, without summarising to the developer:
- `System Overview.md` — container list and responsibilities
- All files in `Containers/` — one per container
- `Non-Functional Concerns/Requirements.md` — NFR targets
Extract per container:
- Name and stated responsibilities
- Technology choices
- Implementation status as stated in the doc (e.g. "TBD", "not yet built", production-ready)
- Any explicit open questions or gaps noted in the doc
---
## Step 3 — Read System Architecture (LLD)
Read `docs/System Architecture (LLD)/README.md`.
Then inspect each container folder under `docs/System Architecture (LLD)/`. For each folder, determine:
- **Empty** — no LLD docs exist yet
- **Partial** — some docs exist but coverage looks incomplete
- **Present** — docs exist and appear to cover the container
Do not judge quality — only presence.
---
## Step 4 — Delegate code scan to @architect
Invoke `@architect` with this prompt (do not deviate):
> "Scan the NX monorepo under `apps/`. For each NX project, identify:
>
> 1. Name and inferred purpose
> 2. Which HLD container it maps to
> 3. Rough implementation maturity: stub / in-progress / functional
>
> Base your assessment on: file structure, entry points, presence of meaningful logic vs placeholders, test coverage, and any README content.
>
> Return a structured list. Do not write files. Do not make changes."
---
## Step 5 — Build the gap matrix
Combine findings from Steps 2, 3, and 4 into a gap matrix. Populate one row per container discovered from the HLD in Step 2 — do not hardcode container names:
```
| Container | Designed (HLD) | Implemented (code) | Documented (LLD) | Gap |
| -------------- | -------------- | ------------------ | ---------------- | --- |
| <from HLD> | ✅ | ✅ / ⚠️ partial / ❌ | ✅ / ❌ | ... |
```
Gap key:
- **LLD missing** — designed and implemented but not documented at LLD level → documentation debt
- **Not yet built** — designed but no implementation exists → delivery debt
- **In progress** — partial implementation → in-flight
- **Undocumented design** — HLD container has significant open questions or TBD sections → design debt
- **—** — fully covered across all three dimensions
---
## Step 6 — Produce the full report
Structure:
```markdown
# Delivery Gap Report — {VERSION}
_Generated: {YYYY-MM-DD}_
---
## Summary
<2–3 sentence narrative: overall delivery posture, dominant gap type, most critical gaps>
## Gap Matrix
<table from Step 5>
## Delivery Debt
Containers designed and coded but not yet documented in System Architecture (LLD):
<list with recommended LLD content for each — what would be most valuable to capture>
## Documentation Debt
<Same containers with LLD as empty or partial — what specifically is missing>
## Design Debt
HLD containers with significant open questions or TBD sections that should be resolved:
{list}
## Recommended next actions
| Priority | Action | Command |
| -------- | ------ | ---------------------------------------------- |
| P1 | ... | `/dev document {TICKET}` or `/design {TICKET}` |
| ... | | |
```
---
## Step 7 — Present and offer to save
Present the full report in the console.
After presenting:
> "Gap report complete. Save as a dated snapshot? (**yes** / **no**)"
If yes, use `.claude/skills/where-we-are/report-template.md` as the file structure. Replace all `{{VERSION}}` and `{{YYYY-MM-DD}}` placeholders with actual values, populate the gap matrix with the containers discovered from the HLD (one row per container — do not hardcode), and fill in all report sections.
Save to:
```
docs/System Architecture (LLD)/where-we-are/{YYYY-MM-DD}-gap-report.md
```
Create the `where-we-are/` directory if it does not exist.
---
## Step 8 — Close
After saving (or if developer declined):
> "Saved to `docs/System Architecture (LLD)/where-we-are/{date}-gap-report.md`.
>
> To re-run after new deliveries: `/where-we-are`
> To document a container's LLD: `/dev document {TICKET}`
> To run a full WAF code audit: `/war implementation`"