Doc coauthoring

Skill BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/doc-coauthoring

Portable open-source Codex toolkit with reusable skills, custom agents, plugins, project profiles, validation tools, and SDK examples.

Install

npx -y skills add BAKUGOS1/SkilledAgents-Toolkit --skill doc-coauthoring

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Structured coauthoring workflow for documentation, PRDs, RFCs, technical specs, decision records, proposals, handoffs, roadmaps, postmortems, and project plans. Use when the user wants to write, refine, review, or stress-test a substantial document so it is clear for real readers and execution-ready.

SKILL.md

2.0 KB, as published. Nobody here has run it

Doc Coauthoring

Overview

Use this skill to turn rough context into a document that readers can understand and act on. It borrows the useful staged workflow pattern from Anthropic's public doc-coauthoring example and adapts it for concise Codex collaboration.

Workflow

1. Context Gathering

Collect only the context needed to draft well:

Document type and audience.
Desired reader action or decision.
Required format, template, length, and tone.
Background facts, constraints, open questions, and non-goals.
Source files or links that must be reflected.

If context is already sufficient, do not ask more questions; draft.

2. Structure And Draft

Propose the outline before writing long docs.
Make the main point obvious near the top.
Separate facts, decisions, options, risks, and next steps.
Use headings that help scanning.
Avoid filler, vague promises, and unsupported claims.

3. Reader Test

Before finalizing, inspect the doc as a fresh reader:

Can the audience understand the problem and decision?
Are assumptions and ownership clear?
Are risks and tradeoffs named?
Are next steps specific enough to execute?
Is anything missing that would cause back-and-forth?

Common Outputs

PRD: problem, user, scope, non-goals, requirements, UX notes, metrics, risks.
RFC/design doc: context, options, decision, architecture, migration, test plan.
Proposal: opportunity, recommendation, cost, risk, timeline, ask.
Handoff: current state, changed files, verification, blockers, next owner.
Postmortem: impact, timeline, root cause, contributing factors, actions.

Final Handoff

Provide the finished doc or a clean outline, plus assumptions and unresolved questions.