Write docs
Draft or revise technical documentation, specifications, proposals, ADRs, and README content for readers who do not share the current session context. Use when durable written guidance is the deliverable.From its SKILL.md
npx -y skills add kevinb361/agent-skills --skill write-docsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
3 things to look at
- 22 days oldThe repository was created 22 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 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.
SKILL.md
1.4 KB, 214 tokens by cl100k_base, as published. Nobody here has run it
Write technical documentation
Build the reader model
Identify the intended reader, what they are trying to accomplish, what they already know, and what decisions or actions the document must support. Gather facts from code, existing documents, and live behavior where relevant; do not turn assumptions into documentation.
Draft
Lead with purpose and scope. Organize around the reader's path rather than the author's discovery process. Include prerequisites, concrete examples, failure modes, verification, and rollback where they matter. Separate current behavior from proposals and future work.
Use exact names and commands, but avoid secrets, machine-specific details in public documentation, and stale duplicated source-of-truth content.
Reader check
Before finishing, reread as someone without this conversation:
- Are terms defined before use?
- Can the reader find the common path quickly?
- Are dangerous or irreversible actions explicit?
- Are examples internally consistent?
- Does every claim have a source or clear status?
- Is ownership of future updates clear?
Verify referenced paths, commands, and links when practical.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.