Install
openclaw skills install @yangchao228/doc-coauthoringGuide a user through structured co-authoring of substantial documents, proposals, PRDs, technical specs, decision records, RFCs, and similar long-form work artifacts. Use when the user wants help writing, shaping, reviewing, or iterating a document with clear audience, context, structure, reader testing, and final readiness checks. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
openclaw skills install @yangchao228/doc-coauthoringHelp the user create a document that works for its real readers.
Use a guided workflow instead of jumping straight to a finished draft. Preserve the user's judgment over facts, priorities, tone, and final approval.
Collect only the context needed for the document:
If an existing document is provided, diagnose it before rewriting. If the user only has scattered notes, organize them first.
Ask concise questions to close the knowledge gap:
Invite the user to dump raw context without organizing it. Convert that context into a short working brief:
doc_state:
type:
audience:
desired_outcome:
known_facts: []
assumptions: []
open_questions: []
source_materials: []
suggested_structure: []
next_section:
Propose a section structure based on the document type and audience.
For most substantial documents, include:
Start with the section that carries the most uncertainty or decision weight. Leave summaries and introductions for later when the core argument is stable.
For each section:
When editing an existing document, prefer surgical changes over full rewrites. Preserve useful wording and only replace what fails the reader goal.
After the core sections are drafted, reread the whole document and check:
Recommend cuts when a section is accurate but not useful for the reader.
Before calling the document ready, test whether a fresh reader could understand it.
Predict 5-10 realistic reader questions, such as:
If subagents or independent review tools are available, use them with only the document and the reader questions. If not, simulate the reader test yourself and clearly label it as an internal review.
Fix gaps found during the reader test before final approval.
During co-authoring, maintain a compact handoff:
doc_state:
type:
audience:
desired_outcome:
current_stage:
completed_sections: []
active_section:
open_questions: []
reader_test_status:
next_step:
For user-facing responses:
must fix, should improve, and optionalAI生命克劳德