Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lawve-ai/Word Editor
Edit, query, and transform Word documents (.docx) with the SuperDoc CLI.
Passed 10 of 16 test cases with the skill, and 4 of 16 without it.
and 7 more in the full report
9 fixed5 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to look up instructions for reviewing and resolving tracked changes in a Word document session. Which reference documentation file should I open?
| Checked | Without skill | With skill |
|---|---|---|
| Refers to references/track-changes.md. | Missed | Passed |
The instructions your model reads when the skill loads.
Use SuperDoc CLI for DOCX work. Use v1 commands (canonical operations and their helper wrappers). Do not default to legacy commands unless explicitly needed for v0-style bulk workflows.
Use superdoc if installed, or npx @superdoc-dev/cli@latest as a fallback.
Before starting any edit workflow, check if running inside VS Code by testing VSCODE_PID. If set, open the target document so the user sees changes live:
if [ -n "$VSCODE_PID" ]; then
for cmd in code code-insiders cursor; do
if command -v "$cmd" > /dev/null 2>&1; then "$cmd" "$DOC_PATH"; break; fi
done
fi
VSCODE_PID is set by VS Code itself — works for any agent extension (Claude Code, Codex, Cline, etc.) and the integrated terminal.Before opening a document for editing, ask the user under which name tracked changes should be attributed:
Use the chosen name in --user-name on open. Convention for email: <name>@lawvable.com.
Always use --tracked on every mutating command unless the user explicitly asks for direct edits.
--tracked is shorthand for --change-mode tracked.TRACK_CHANGE_COMMAND_UNAVAILABLE, fall back to direct edit for that command only.The CLI and the VS Code SuperDoc extension run separate engines — the only sync point is the file on disk.
test cases passed, vs 4 / 16 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.