← All skills
verify-xum
94 / 100 · Low risk
Fine to try.
By coder/xum (GitHub) · design · 2,078 stars · scanned at commit e4c1d0c
Drives the real Xum web UI (a `make dev-server-sandbox` instance with the mock AI, isolated XUM_ROOT and free ports) through agent-browser to prove a change works the way a user sees it, with screenshots, ARIA snapshots and on-disk side effects as evidence. Use to verify a UI or backend change in this checkout end to end, to reproduce a reported Xum bug in the browser, or before claiming a Xum feature works.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README.
Found in 15 places.
Show 12 more
- .xum/skills/verify-xum/SKILL.md, line 174
eval "$(.xum/skills/verify-xum/scripts/verify-xum.sh env)" - .xum/skills/verify-xum/SKILL.md, line 224
verify-xum.sh cli workspace list - .xum/skills/verify-xum/SKILL.md, line 253
.xum/skills/verify-xum/scripts/verify-xum.sh capture chat/reply - .xum/skills/verify-xum/SKILL.md, line 270
.xum/skills/verify-xum/scripts/verify-xum.sh webkit-capture "/workspace/$VERIFY_XUM_WORKSPACE_ID" chat/reply - .xum/skills/verify-xum/SKILL.md, line 363
.xum/skills/verify-xum/scripts/verify-xum.sh cleanup - .xum/skills/verify-xum/features/chat.md, line 41
timeout 10 sh -c 'until grep -qF "Mock response: Second message" "$1"; do sleep 0.2; done' sh "$chat_jsonl" - .xum/skills/verify-xum/features/review.md, line 58
timeout 10 sh -c 'until grep -qsF "\"isRead\": true" "$1"; do sleep 0.2; done' sh "$VERIFY_XUM_ROOT/sessions/$VERIFY_XUM_WORKSPACE_ID/review-state.json" - .xum/skills/verify-xum/features/review.md, line 75
timeout 10 sh -c 'while grep -qF "\"isRead\": true" "$1"; do sleep 0.2; done' sh "$VERIFY_XUM_ROOT/sessions/$VERIFY_XUM_WORKSPACE_ID/review-state.json" - .xum/skills/verify-xum/features/review.md, line 83
timeout 10 sh -c 'until grep -qF "\"includeUncommitted\": false" "$1"; do sleep 0.2; done' sh "$VERIFY_XUM_ROOT/config.json" - .xum/skills/verify-xum/features/settings.md, line 49
timeout 10 sh -c 'until grep -qF "\"sidebarFlatMode\": true" "$1"; do sleep 0.2; done' sh "$VERIFY_XUM_ROOT/config.json" - .xum/skills/verify-xum/features/workspaces.md, line 70
timeout 10 sh -c 'until [ -n "$(verify-xum.sh workspace-field release-notes archivedAt)" ]; do sleep 0.2; done' - .xum/skills/verify-xum/scripts/verify-xum.sh, line 576
VERIFY_XUM_SERVER_OF="$VERIFY_XUM_RUN_ID" setsid sh -c 'printf "export VERIFY_XUM_PGID=%s\n" "$$" >>"$1" || exit 1; exec 9>&- && shift && exec "$@"' sh \
Connects to the internet
This is disclosed by the author in the skill's SKILL.md or README.
Found in 3 places.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'verify-xum' ] || [ -L ~/.agents/skills/'verify-xum' ]; then echo 'A skill folder named verify-xum already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/coder/xum' "$d" && git -C "$d" checkout --quiet 'e4c1d0c81ed06de5de6a98c701e1ac170b43935d' -- '.xum/skills/verify-xum' && mkdir -p ~/.agents/skills && cp -R "$d"/'.xum/skills/verify-xum' ~/.agents/skills/'verify-xum' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'verify-xum' ~/.claude/skills/'verify-xum' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for coder/xum shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/coder/xum/)
Score history
| Date | Version | Score |
|---|
| 2026-11-15 | e4c1d0c | 94 |
| 2026-11-12 | 0b7d9f7 | 94 |