Docs & Best Practices

Set up your workspace for efficient AI-assisted development.

ContextLoom doesn't run Claude or any LLM. It complements CLI tools like Claude Code and Cursor by organizing the files they create on disk.

Recommended workspace setup

A clean workspace structure makes it easy for both you and your AI tools to find, create, and update context files.

1

Keep a single workspace folder

Choose one root directory for your project context. This could be inside your project repo (e.g., `/project/context/`) or a standalone folder. ContextLoom opens this as your workspace.

2

Point your AI tool at the workspace

Configure Claude Code or Cursor to read from and write to your workspace directory. Add the ContextDB conventions to your Claude.md or project rules file.

3

Create the ContextDB structure

Add the taxonomy folders (00-inbox through 70-prompts) inside a `ContextDB/` subfolder. This gives agents a clear, predictable structure to follow.

4

Add the Claude.md snippet

Paste the ContextDB conventions snippet into your Claude.md file. This tells Claude Code exactly where and how to write files in your workspace.

Best practices

Prefer adding new files over rewriting old ones

When context evolves, create a new file rather than overwriting. This preserves history and lets you track how decisions changed over time.

Link related documents

Use relative Markdown links between files (e.g., a spec linking to its requirement). This creates a navigable knowledge graph and reduces duplication.

Keep summaries separate from raw notes

Write summaries in 50-summaries/ — never overwrite the source material in other folders. Summaries are compressed views; raw notes are the source of truth.

Use Context Bundles for prompts

Instead of pasting entire folders into a prompt, select only the files relevant to your question. ContextLoom's bundle export makes this one click.

Store and reuse prompts

Keep proven prompts in 70-prompts/ and reference them by path. This makes your prompting repeatable and lets agents follow established patterns.

Review agent output before committing

ContextLoom's preview pane lets you review what an agent wrote before you save or share it. Catch errors early.

Prompt patterns

These patterns work well with ContextDB-organized workspaces. Store them in your 70-prompts/ folder.

Update spec based on requirements

When requirements change and specs need to catch up.

Read the requirement at 10-requirements/[feature].md. Update the spec at 20-specs/[feature]-spec.md to reflect the current requirements. Preserve existing sections. Add new sections as needed.

Summarize folder into a single file

When a folder has accumulated many files and you need a quick overview.

Read all files in [folder]. Write a concise summary to 50-summaries/[folder]-summary.md. Include: key points, decisions made, open items, and links to source files.

Generate TODOs from requirements

When starting implementation and you need a clear task list.

Read the requirement at 10-requirements/[feature].md. Generate a TODO list in 40-todos/[feature]-todos.md with actionable tasks derived from the acceptance criteria.

Create a decision record

When facing a technical or product decision that should be documented.

We need to decide between [Option A] and [Option B] for [topic]. Create an ADR-lite in 30-decisions/ with context, options, pros/cons, and a recommendation.

Build a context bundle

When preparing a focused prompt for another LLM session.

I need to prompt Claude about [topic]. Build a context bundle with the minimum set of files from this workspace that provide relevant context. Output in the Context Bundle format.