Retenta has not executed this skill.
Evidence record · captured 2026-10-11
Doc Co-authoring
Runs a three-stage co-authoring workflow for specs, proposals, PRDs, RFCs and decision docs: context gathering (the agent asks targeted questions), refinement and structure (iterative drafting section by section), and reader testing (checking the document works for someone without the author's context). The agent offers the workflow when the user starts a substantial writing task.
Editorial assessment
This is a source-only assessment. It does not claim runtime or security testing.
What it does
Runs writing as a gated three-stage session: numbered questions to draw out context, section-by-section drafting from brainstormed options, then a test on a fresh model that never saw the conversation.
Best for
- Design docs, decision docs, PRDs and RFCs that other people will read without the author present
- Getting scattered context out of someone's head and into a structured draft
- Checking whether a finished document answers the questions its readers will ask
Strengths in the source
- For each section the agent asks 5 to 10 clarifying questions and brainstorms 5 to 20 options for the user to keep, remove or combine before drafting.
- Edits are made in place with str_replace instead of reprinting the document, and the user is asked to request changes rather than edit directly so preferences carry forward.
- Reader testing gives a subagent only the document and predicted reader questions, then loops back to fix the sections it misread.
- Offers to write alt-text for images in shared docs, because a later reader using a model cannot see them.
Limitations
- Has no license file in the skill folder or at the repository root, so Retenta links to the upstream file rather than hosting a copy.
- Slow by design: several question-and-answer rounds per section, which is heavy for a short document.
- Written around Claude surfaces such as artifacts, sub-agents and Claude.ai connectors; without them it falls back to a local markdown file and manual reader testing.
When not to use it
- Short or routine writing such as an email, a status update or a changelog entry.
- Documents whose content is already settled and only need formatting or copy edits.
Reviewed by Retenta editorial on 2026-10-11; scope: source only.
Files included in this review
skills/doc-coauthoring/SKILL.md
Evidence and boundaries
The skill folder bundles no executable scripts. Retenta has not run a security scan.
- Pinned publisher source
- skills/doc-coauthoring/SKILL.md
- Revision
- dbd4588f9e1033efb41dad4bef2f7947c8993d44
- License evidence
- NOASSERTIONRetenta preserves the license text captured with this immutable upstream snapshot; no independent legal or security review is claimed.
- Last source change
- 2025-12-04
- Independent verification
- Published by Anthropic, which does not own the product this skill covers. Not independently verified.
- Upstream repository
- Open publisher repository
Compatibility
Claude Code (plugin marketplace)
documentedNamed in the upstream skill or repository documentation; not tested by Retenta.
Claude.ai
documentedNamed in the upstream skill or repository documentation; not tested by Retenta.
Claude API (Skills API)
documentedNamed in the upstream skill or repository documentation; not tested by Retenta.
Requirements and access
- None required
Referenced tools
No named tool is required by the reviewed SKILL.md.
Install from the source
Clones the current default branch, which may be newer than the reviewed revision dbd4588. The destination shown is Claude Code's personal skills folder; other agents read the same folder from their own skills directory. No license file in the skill folder or the repository, so Retenta links to the source instead of hosting a copy.
View the SKILL.md at its source Verify the publisher's install documentationInstall the full skill folder
git clone --depth 1 https://github.com/anthropics/skills.git
cp -R skills/skills/doc-coauthoring ~/.claude/skills/doc-coauthoringThyme RAG Capsules
Make this skill’s state durable, governed, and portable.
A Retenta capsule lets agents recall prior work, append provenance-stamped progress, and carry the memory to the next run.