where-we-are
Skill9 starsChanged 47 days agoMITView on GitHub
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/.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- l3rowniecakez/Claude_Skilltheir own version, first seen Oct 19, 2026
- Soul-Brews-Studio/arra-oracle-skills-clitheir own version, first seen Apr 13, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Soul-Brews-Studio/arra-oracle-skills-cli★ 121same name
- l3rowniecakez/Claude_Skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 40
Read docs/Target Architecture (HLD)/README.md to find the current active version.
- Very specific: line 44
If a version is given (e.g.
- Distinctive: line 45
If no argument: use the active version
- Distinctive: line 57
Read, without summarising to the developer:
- Very specific: line 60
All files in Containers/ — one per container
- Distinctive: line 82
Do not judge quality — only presence.
- Very specific: line 175
If yes, use .claude/skills/where-we-are/report-template.md as the file structure.
- Very specific: line 183
Create the where-we-are/ directory if it does not exist.
- Distinctive: line 189
After saving (or if developer declined):
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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:
- Name and inferred purpose
- Which HLD container it maps to
- 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:
# 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.mdCreate 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-areTo document a container's LLD:/dev document {TICKET}To run a full WAF code audit:/war implementation"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

