Agent skill

Architecture Document Writer

by imbue-ai in imbue-ai/bouncer

Writes an architecture document for a feature from its goals and requirements, after asking questions and studying the existing codebase.

AGPL-3.0Auto-check passedDevelopment

Install Architecture Document Writer

skills CLI
$ npx skills add imbue-ai/bouncer --skill write-architecture -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install imbue-ai/bouncer write-architecture --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/imbue-ai/bouncer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/write-architecture .claude/skills/write-architecture && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
write-architecture
GitHub stars
400
Token cost
~335 tokens
SKILL.md length
150 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Writes an architecture document for a feature from its goals and requirements, after asking questions and studying the existing codebase.

  • Works in 3 steps: Ask clarifying questions or raise… → Deeply analyze the codebase to… → Create an architecture document at…
  • Turning a set of requirements into a design document before building
  • SKILL.md covers Document structure:, Guidelines: and Do not:
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The agent reads the goals and requirements kept in the feature's folder under docs, raises concerns or asks clarifying questions, studies the codebase to learn its existing patterns, and then writes architecture.md in that same folder.

The document follows a fixed outline: an executive summary with a before and after table, the current architecture, key changes, a deep dive per component, data model changes, migration and code-removal plans where relevant, an appendix of files to modify, create or delete, and a testing strategy overview. The guidelines call for ASCII diagrams, describing how components interact instead of showing code, listing alternatives considered, naming risks and mitigations, preferring YAGNI, and citing requirement IDs for traceability. No code and no time estimates go in the document.

When your agent uses it

  • Turning a set of requirements into a design document before building
  • Planning a migration or refactor that needs a before and after comparison
  • Adding requirement traceability to an architecture document

Example prompts

  • “Write the architecture document for the notifications feature from the requirements in docs/notifications.”
  • “Draft an architecture doc for replacing our queue layer, with ASCII diagrams.”
  • “Analyze the codebase and write architecture.md for the new billing flow.”

Requirements

  • Goals and requirements files in the feature's docs folder

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Ask clarifying questions or raise concerns about the requirements
  2. Deeply analyze the codebase to understand existing patterns and architecture
  3. Create an architecture document at docs/$ARGUMENTS/architecture.md

What it can do on your machine

Read from SKILL.md and the folder at commit 1ed480c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Architecture Document Writer loads about 335 tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 150 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
When it runs · the whole SKILL.md, loaded when a task matches
~335

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from imbue-ai/bouncer at commit 1ed480c, republished under its AGPL-3.0 licence (© imbue-ai). 150 words, ~335 tokens.

Download SKILL.mdSave it as .claude/skills/write-architecture/SKILL.md (or your agent's skills folder).
name
write-architecture
description
Write an architecture document from goals and requirements
argument-hint
<feature-name>

Write Architecture Document

Read my goals and requirements at docs/$ARGUMENTS/

I want you to:

  1. Ask clarifying questions or raise concerns about the requirements
  2. Deeply analyze the codebase to understand existing patterns and architecture
  3. Create an architecture document at docs/$ARGUMENTS/architecture.md

Document structure:

  • Executive summary with before/after comparison table
  • Current architecture overview (with diagrams)
  • Key architectural changes (with diagrams)
  • Component deep dives for each major change
  • Data model changes (schema, API types)
  • Migration strategy (if applicable)
  • Code removal plan (if applicable)
  • Files to modify/create/delete appendix
  • Testing strategy overview

Guidelines:

  • Use ASCII diagrams liberally to illustrate component relationships
  • Describe HOW components interact, not implementation code
  • Identify alternatives you considered and why you chose this approach
  • Call out risks and mitigation strategies
  • Prefer YAGNI over extensibility - build for current requirements, not hypothetical future ones
  • Reference requirement IDs (REQ-*) to show traceability

Do not:

  • Write code in the document
  • Include time estimates

© imbue-ai, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/write-architecture of imbue-ai/bouncer.

Open the folder on GitHubat commit 1ed480c

Compare with similar skills

Architecture Document Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Architecture Document Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architecture Document Writer this skillimbue-ai/bouncer400—~335Automated safety check: PassAGPL-3.0
Dark Architecture Diagram BuilderCocoon-AI/architecture-diagram-generator7.4k1 repos~2.1kAutomated safety check: PassMIT
Deepwiki Rssopaco/deepwiki-rs3.1k—~748Automated safety check: PassMIT
Mermaid Diagramsjjmartres/opencode1336 repos~1.9kAutomated safety check: PassMIT
C4 Architecture Diagramslexler/skill-factory239—~2.3kAutomated safety check: PassApache-2.0
Archify Diagramstt-a1i/archify81k—~2.9kAutomated safety check: PassMIT

Similar skills

  • Dark Architecture Diagram Builder

    Cocoon-AI/architecture-diagram-generator

    Creates dark-themed system, cloud, security and network architecture diagrams as self-contained HTML files with inline SVG and CSS.

    7.4k GitHub starsUsed in 1 repo~2.1k tokens
    DevelopmentAuto-check passed
  • Deepwiki Rs

    sopaco/deepwiki-rs

    AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation.

    3.1k GitHub stars~748 tokensUpdated 25 days ago
    DevelopmentAuto-check passed
  • Mermaid Diagrams

    jjmartres/opencode

    Helps an agent pick the right Mermaid diagram type and write the syntax for class, sequence, flow, ER, C4, state and other software diagrams.

    133 GitHub starsUsed in 6 repos~1.9k tokens
    DevelopmentAuto-check passed
  • C4 Architecture Diagrams

    lexler/skill-factory

    Creates C4 model diagrams at every zoom level, from system landscape to code, in ASCII, Mermaid or Structurizr, for designing or documenting software architecture.

    239 GitHub stars~2.3k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Archify Diagrams

    tt-a1i/archify

    Creates interactive architecture, workflow, sequence, data-flow and lifecycle diagrams as standalone HTML with inline SVG, themes and image or video export.

    81k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Diagram Design

    cathrynlavery/diagram-design

    Creates branded diagrams, from architecture, flowchart and sequence to charts and maps, as self-contained HTML with inline SVG, with import from draw.io, Mermaid and Excalidraw.

    47k GitHub starsUsed in 1 repo~7.5k tokens
    DevelopmentAuto-check passed

More from imbue-ai/bouncer

  • HTML Feature Mocks

    imbue-ai/bouncer

    Explores a feature idea through HTML mocks that match the project's existing UI, keeping every earlier version and logging each requested tweak in a context file.

    400 GitHub stars~677 tokensUpdated yesterday
    Auto-check passed
  • Turns a feature's goals, requirements and architecture documents into a set of self-contained task files that a developer with no project context can follow.

    400 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Turns an HTML mock iteration session into a requirements document that describes only user-facing behavior.

    400 GitHub stars~410 tokensUpdated yesterday
    Auto-check passed
  • Works through the task files of a feature's implementation plan one at a time, with a TODO list and a verification step and commit for each task.

    400 GitHub stars~425 tokensUpdated yesterday
    Auto-check: warnings

Categories

Questions about Architecture Document Writer

What does Architecture Document Writer do?

Writes an architecture document for a feature from its goals and requirements, after asking questions and studying the existing codebase. md in that same folder.

When should I use Architecture Document Writer?

Architecture Document Writer fits situations like: turning a set of requirements into a design document before building; planning a migration or refactor that needs a before and after comparison; adding requirement traceability to an architecture document.

How do I install Architecture Document Writer in Claude Code?

Run `npx skills add imbue-ai/bouncer --skill write-architecture -a claude-code`. Or copy the skill folder (.claude/skills/write-architecture in imbue-ai/bouncer) into .claude/skills/write-architecture in your project. Claude Code loads it when a task matches its description.

How do I install Architecture Document Writer in Codex?

Run `npx skills add imbue-ai/bouncer --skill write-architecture -a codex`. Or copy the skill folder (.claude/skills/write-architecture in imbue-ai/bouncer) into .agents/skills/write-architecture in your project. Codex loads it when a task matches its description.

Can I use Architecture Document Writer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add imbue-ai/bouncer --skill write-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/write-architecture, .gemini/skills/write-architecture, .github/skills/write-architecture and .opencode/skills/write-architecture in your project.

What does Architecture Document Writer need to run?

SKILL.md names no scripts, command-line tools or credentials: Architecture Document Writer is instructions for the agent only. Our summary lists: Goals and requirements files in the feature's docs folder.

Does Architecture Document Writer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Architecture Document Writer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Architecture Document Writer use?

Architecture Document Writer is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Architecture Document Writer use?

About 335 tokens (SKILL.md is roughly 1.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Architecture Document Writer?

Skills that share tags, products or a category with Architecture Document Writer: Dark Architecture Diagram Builder (Cocoon-AI/architecture-diagram-generator, 7.4k stars), Deepwiki Rs (sopaco/deepwiki-rs, 3.1k stars), Mermaid Diagrams (jjmartres/opencode, 133 stars) and C4 Architecture Diagrams (lexler/skill-factory, 239 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architecture Document Writer?

imbue-ai (a GitHub organization) maintains it in imbue-ai/bouncer, which has 400 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.

Source: imbue-ai/bouncer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.