human-review-publish-demo
Skill46 starsChanged 48 days agoMITView on GitHub
Publish screenshots of an already-generated /human-review report to GitHub Pages — one full-page image per tab, light and dark, plus the feature video, committed and pushed as demo/<slug>/. Explicit invocation only — user types /human-review-publish-demo.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- human-reviewSkill
- publish-demoSkill
- record-reviewSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Run this one command, and nothing else:
- Very specific: line 20
Add --slug NAME only if they asked for a name.
- Distinctive: line 24
Do not read the report, do not open the screenshots, do not check the deploy, do not describe the change set.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/human-review-publish-demo
Run this one command, and nothing else:
for c in "${CLAUDE_PLUGIN_ROOT:-/nonexistent}/skills/human-review" "${HUMAN_REVIEW_HOME:-/nonexistent}" \
"$(readlink -f .claude/skills/human-review 2>/dev/null)" ".claude/skills/human-review" \
"$HOME/workspace/human-review/skills/human-review"; do
[ -x "$c/scripts/publish-demo-shots.sh" ] && { "$c/scripts/publish-demo-shots.sh" "$REPORT"; break; }
done$REPORT is the path the user named, or ./.human-review/review.html if they named none.
Add --slug NAME only if they asked for a name.
Then print the URL the script printed on its last line. That is the whole job.
Do not read the report, do not open the screenshots, do not check the deploy, do not describe the change set. The script shoots every tab, builds the gallery, updates the landing page, commits and pushes on its own. If it exits non-zero, show its stderr and stop.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

