docs-a-bead

Identify documentation gaps and produce code-validated docs with M1–M5 verification.

Updated May 3, 2026
One-click install
npx skills add https://github.com/fkberthold/loom --skill docs-a-bead
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: docs-a-bead
Source: https://github.com/fkberthold/loom/tree/main/skills/docs-a-bead
Command: npx skills add https://github.com/fkberthold/loom --skill docs-a-bead

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill owns ONLY the docs-specific middle of the bead lifecycle, ensuring that the documentation associated with code changes is accurate, well-structured, and aligned with the bead's voice and decisions. The deliverable is a tracked file in the repo (e.g., README.md or a docs folder entry), not an internal memory artifact.

Core Features & Use Cases

  • Provides the docs-focused middle (gap identification, voice sampling, drafting, and code-aligned review) while deferring lifecycle scaffolding to bead-lifecycle-shell.
  • Supports explicit invocation or router-driven activation to produce well-formed, code-validated documentation across doc-only and doc-as-a-bead scenarios.
  • Ensures the produced doc matches code references, is runnable where applicable, and surfaces only necessary decisions via optional overhead.

Quick Start

Invoke docs-a-bead with a target document (e.g., update README) to begin drafting and reviewing a tracked doc against code.

Frequently Asked Questions about docs-a-bead

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I identify and fill documentation gaps in my code repository?

Documentation gap finding scans tracked repo files to locate missing sections, then drafts accurate, code-validated docs that align with the project voice to resolve the gaps.

What is the best way to ensure my README documentation matches the actual code?

Code-reviewed verification validates drafted docs against actual code references and ensures examples are runnable, enforcing M1–M5 verification steps to guarantee documentation and code alignment.

How do I calibrate documentation to match a project's specific voice and style?

Voice calibration samples existing project documentation during session startup to capture tone and style, applying this voice consistently across gap finding, drafting, and final code-reviewed verification.

When should I capture project decisions within my documentation workflow?

Conditional M5 decision-drawer capture activates only when a real project decision is encoded, ensuring decision tracking adds no overhead to standard doc-only or doc-as-a-bead documentation scenarios.

Can I use this documentation approach for doc-only updates without full lifecycle scaffolding?

Yes, explicit invocation or router-driven activation supports doc-only scenarios by deferring lifecycle scaffolding to a separate shell and focusing strictly on drafting and reviewing tracked documentation.