Use guide-builder

Turn raw notes, a spec, a thread or a messy procedure into a guide someone else can follow

Turn raw notes, a spec, a thread or a messy procedure into a guide someone else can follow — a setup guide, a how-to, an onboarding walkthrough, or a reference for developers — in the length and voice its reader needs. Holds only what the notes say, marks anything inferred where it appears, orders steps so nothing is used before it is set up, and keeps open questions out of the guide so it can be sent as it stands.

Reach for it when the user wants setup or getting-started instructions, a walkthrough of how something works, or reference docs for an API or event schema — and it is NOT an SRE operational runbook (use runbook-generator) or a design proposal for review (use design-doc).

Install it

npx skilldrop-cli install guide-builder                 # Claude Code, your user folder
npx skilldrop-cli install guide-builder --project       # Claude Code, this repo
npx skilldrop-cli install guide-builder --ide cursor    # or kiro, codex, antigravity, copilot

It is part of the Stakeholder comms pack: --pack stakeholder-comms installs it with its neighbours.

Ask for it

Say it the way you would to a colleague. Requests like these route to it:

• "Write setup instructions for getting our service running locally from these notes"
• "Turn this architecture description into an onboarding walkthrough for new engineers"
• "Document these webhook events and payloads for the developers who'll consume them"
• "Make a quickstart guide out of this messy README"

Requests like these belong to a different skill, so it shouldn't answer them:

• "Write the on-call runbook with escalation and rollback for the billing service"
• "Draft a design proposal with options and trade-offs for the new billing architecture"
• "Summarize this 20-page spec for the executive team"

If another skill answers instead, ask for this one by name: "use guide-builder".

Check what you get

A good result:

• Every fact in the guide is in the notes; every inference is marked where it appears.
• The guide can be sent as written: no questions, internal notes or to-do markers in it.
• A reader following top to bottom never uses something before it is set up.
• One action per step; success checks only where the notes give them.
• References say "not stated" rather than guessing types, required fields or meanings.
• Length and voice fit the reader asked for.

Use something else when

• SRE operational runbook — incidents, on-call escalation, deploy/rollback, SLOs → runbook-generator.
• Proposing a design for review/approval — options, trade-offs, risks, rollout → design-doc.
• Compressing a long doc for an exec audience → exec-summary.
• Raw unstructured mess that isn't ready to shape (a transcript, a Slack thread) → run brief-intake first, then come back.

Next

• SKILL.md, the instructions the agent reads
• Its page on the site
• Related: brief-intake, design-doc, exec-summary, runbook-generator

Edit this page on GitHub · View source