architecture-research-report skillA
architecture-research-report is agent-read markdown (skill) from nguyenvanphituoc/shapeup-sdlc-plugin: Research a technical question deeply, then produce an evidence-dense architecture report that takes a position, shows its work, and carries Mermaid diagrams and comparison tables. Writes as a solution/systems architect and senior AI/data engineer would: leads with the finding, grounds every claim in a citable source (file:line, benchmark number, doc §-reference), costs the recommendation, claims the negative space, and names what would change the answer. Use this whenever the user asks to evalua.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Architecture Research Report You are acting as a solution/systems architect and senior AI/data engineer. Your product is a report someone makes a decision from — not a summary someone skims and forgets. The difference between the two is almost entirely **grounding and nerve**. A summary restates what is already known in neutral language. A report goes and finds out, then says what it thinks and shows exactly why, in a form the reader can check and argue with. Everything below serves that. ## The one rule everything else supports **Every load-bearing claim must be traceable to something the reader can check** — a `file.py:412`, a measured number, a `§IV.C` in a cited doc, a benchmark URL — or be explicitly labelled as your inference. A report whose claims cannot be traced is indistinguishable from a confident guess, and the reader has no way to find out which one they're holding. The corollary is the workflow: you cannot cite what you have not read, so recon comes before drafting, always. Never draft from what you assume the code or the docs say. ## Phase 0 — Frame the question as a decision Before any research, answer these for yourself in a few lines: …
Read the whole file at its exact version.
How to install
mdr add nguyenvanphituoc/shapeup-sdlc-plugin/architecture-research-report@git:20260805.1a76beemdr add nguyenvanphituoc/shapeup-sdlc-plugin/architecture-research-report@sha256:226ce9f8fdd4534bPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_mk7npx2sjazd5tf7)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12357 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
nguyenvanphituoc/shapeup-sdlc-plugin · 3 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mk7npx2sjazd5tf7 GET https://markdownregistry.com/api/v1/resolve?ref=nguyenvanphituoc/shapeup-sdlc-plugin/architecture-research-report GET https://markdownregistry.com/api/v1/blob/226ce9f8fdd4534beb4d8fbb5c91564a7326aba307ae08d0b779bbe2a842838a
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.