smithery/managedcode

mcaf-architecture-overview

Create or update `docs/Architecture.md` as the global architecture map for a solution. Use when bootstrapping a repo, onboarding, or changing modules, boundaries, or contracts. Keep it navigational and use `references/overview-template.md` for scaffolding.

Installation

$ npx skills add smithery/managedcode --skill mcaf-architecture-overview

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery/managedcode.

npx skills add smithery/managedcode

Browse all from smithery/managedcode

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

CompatibilityRequires repository write access; produces Markdown docs with Mermaid diagrams.
More metadata
compatibility
Requires repository write access; produces Markdown docs with Mermaid diagrams.

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 5,011 B
  • docs SUMMARY.md 312 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

MCAF: Architecture Overview

Trigger On

  • create the first repo-wide architecture map
  • modules, boundaries, interfaces, or ownership changed
  • onboarding is slow because there is no short "start here" system map

Value

  • produce a concrete project delta: code, docs, config, tests, CI, or review artifact
  • reduce ambiguity through explicit planning, verification, and final validation skills
  • leave reusable project context so future tasks are faster and safer

Do Not Use For

  • recording a single architecture decision with alternatives
  • writing feature-level behaviour details

Inputs

  • current solution layout and entry points
  • the in-repository backend, frontend, contract, test, infrastructure, and docs roots plus the canonical slice convention required by MCAF-ARCH-001
  • existing ADRs, feature docs, and boundary docs
  • feature REQ-/AC- and ADR implementation links required by MCAF-REQ-001
  • the nearest AGENTS.md files

Quick Start

  1. Read the nearest AGENTS.md and confirm scope and constraints.
  2. Run this skill's Workflow through the Ralph Loop until outcomes are acceptable.
  3. Return the Required Result Format with concrete artifacts and verification evidence.

Workflow

  1. Start from the current docs/Architecture.md; if it is missing, scaffold it from references/overview-template.md.
  2. Build a short navigational overview:

- the single repository boundary and every solution-owned surface - a repo-wide vertical-slice map using one canonical name per feature across backend, frontend, contracts, tests, and docs - system or module map - key boundaries and contracts - scoping hints - links to ADRs, feature docs, and high-signal code paths - traceability from each non-trivial slice to its feature requirements and architecture-affecting ADR implementation contracts

  1. Use only real names from the repo. No placeholders like "Module A".
  2. Prefer Mermaid diagrams plus a tiny link index over long prose.
  3. Split diagrams by boundary if the map becomes noisy.

Deliver

  • docs/Architecture.md
  • a short architecture map that routes the reader to deeper docs
  • explicit evidence that MCAF-ARCH-001 is applied to the real repository topology

Validate

  • diagram nodes use real repo names
  • every important box or boundary links to deeper material
  • the file stays navigational instead of becoming an inventory dump
  • the overview lets a new agent scope work without reading the whole repo
  • no solution-owned surface points to another repository
  • slice names and internal conventions match across every applicable technical root; non-applicable surfaces are explained
  • non-trivial slices link to stable requirements and acceptance criteria, and architecture-affecting decisions link to ADRs whose status and implementation contract match reality

Ralph Loop

Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.

  1. Brainstorm first (mandatory):

- analyze current state - define the problem, target outcome, constraints, and risks - generate options and think through trade-offs before committing - capture the recommended direction and open questions

  1. Plan second (mandatory):

- write a detailed execution plan from the chosen direction - list final validation skills to run at the end, with order and reason

  1. Execute one planned step and produce a concrete delta.
  2. Review the result and capture findings with actionable next fixes.
  3. Apply fixes in small batches and rerun the relevant checks or review steps.
  4. Update the plan after each iteration.
  5. Repeat until outcomes are acceptable or only explicit exceptions remain.
  6. If a dependency is missing, bootstrap it or return status: not_applicable with explicit reason and fallback path.

Required Result Format

  • status: complete | clean | improved | configured | not_applicable | blocked
  • plan: concise plan and current iteration step
  • actions_taken: concrete changes made
  • validation_skills: final skills run, or skipped with reasons
  • verification: commands, checks, or review evidence summary
  • remaining: top unresolved items or none

For setup-only requests with no execution, return status: configured and exact next commands.

Load References

  • use references/overview-template.md only when scaffolding the file

Example Requests

  • "Create an architecture overview for this repo."
  • "Update the overview after splitting the API and worker."
  • "Make onboarding easier by adding a real module map."