Doc Co-Authoring
A guided three-stage workflow for co-authoring documentation, proposals, technical specs and decision docs with the agent: gather context with clarifying questions
- What
- A guided three-stage workflow for co-authoring documentation, proposals, technical specs and decision docs with the agent: gather context with clarifying questions
- Cost
- Free
- Needs
- Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — A guided three-stage workflow for co-authoring documentation, proposals, technical specs and decision docs with the agent: gather context with clarifying questions, build the document section by section (brainstorm, curate, draft, refine with surgical edits), then test it with a fresh reader agent that has no context from the conversation, to catch blind spots before other people read it. It works freeform instead if the user declines the workflow. Honest note: unlike most skills in this repository, this folder carries no licence file and its SKILL.md names no licence, so Skill Harbor lists it with the licence unstated and only links to the source. By @anthropics, listed here with credit to its creator. No licence was found in the upstream repository. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into Muse📌 Pinned version: commit dbd4588Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — None to install this skill, and none strictly required to use it. Installing is copying one instruction file; using the workflow creates a document in my own working environment (an artifact or a local markdown file). If I point the agent at team channels or shared documents for context, it may use integrations I have already connected myself, and it should ask before searching anything unknown; without integrations, I paste the context myself. One honest note: this skill folder carries no licence file and names no licence, so treat it as source to read and link, with the licence unstated. Install "Doc Co-Authoring" for me. It guides co-authoring a document in three stages: first gathering context (the agent asks what kind of document it is, who will read it, what impact it should have, and invites a full context dump plus clarifying questions); then building it section by section (clarifying questions, a brainstorm of options for each section, my keep/remove/combine choices, a draft, then surgical edits instead of reprinting the whole document, re-reading for flow and filler near the end); then testing the finished draft with a fresh reader agent that sees only the document, predicting the questions readers would ask and checking for ambiguity, assumed context and contradictions, and looping back to fix the gaps. If I decline the structured workflow, it works freeform instead. Repository: https://github.com/anthropics/skills (the skill is the whole skills/doc-coauthoring/ folder at the pinned commit: SKILL.md only, 1 file) Pinned version: install the code at commit dbd4588f9e1033efb41dad4bef2f7947c8993d44 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/anthropics/skills into a temporary folder, check out commit dbd4588f9e1033efb41dad4bef2f7947c8993d44, and copy the skills/doc-coauthoring/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 2e47d78846faeea4a56e9809c52700087a15a2155a3f293a3efbaded81398ef4 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 1 file only: SKILL.md. There is no script, no code, no configuration and no licence file in it; it is a guided writing procedure, nothing executable. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit. - At use time, the work product is a document in my own environment (an artifact or a local markdown file I asked for). The reader-testing step, when sub-agents are available, shares that document only with a fresh agent in the same environment. If I name team channels or shared documents as context, the skill uses integrations I already connected, and asks before searching unknown entities; it reads or sends nothing on its own. - Do not start a document, do not call any integration, and do not use the skill in any way during this install: using it is a separate step that only starts when I actually ask to write a document. 3. When I say "yes, install", install it as a skill: copy the whole doc-coauthoring folder into the agent's skills directory, in a folder named exactly "doc-coauthoring", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: doc-coauthoring), the 1 file in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: that no licence file ships with this skill, that using it creates documents in my own working environment, and that any connected-tool reading at use time goes through integrations I connected myself; using the skill is a separate step that only starts when I ask for it). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.