publish-demo
Skill46 starsChanged 47 days agoMITView on GitHub
Publish a finished /human-review page as a demo snapshot — copy it into the human-review repo's demo/, render its landing-page card from the page itself, commit and push, which is what makes the Pages copy, the rolling zip and the ghcr image. Explicit invocation only — user types /publish-demo.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- human-review-publish-demoSkill
- human-reviewSkill
- record-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
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:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
/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 "$c/scripts/publish-demo.sh" ] && { "$c/scripts/publish-demo.sh" --push $ARGS; break; }
done$ARGS is empty unless the user named something:
- a slug — pass it as the first positional argument;
- a source directory other than
.human-review— pass--src DIR; - "don't push yet" / "let me look first" — drop
--pushand pass--cardinstead; - "make this the featured demo" / "put this one in the README" — add
--feature; - "skip the screenshots" — add
--no-tour; - several snapshots, "both demos" — pass
slug=DIRper snapshot instead of a slug and--src, and keep--push: one commit and one push, so the three workflows fire once.
The script derives the slug from the project directory, copies the snapshot, leaves
behind the run's own dot-prefixed bookkeeping and *.raw.webm, refuses any file over
50 MB, rewrites that snapshot's card in demo/index.html from review.html and
content.json, then commits and pushes. When the slug is the featured one (demo), it
also screenshots every tab headlessly and rewrites the README's tour, the pages under
docs/tabs/ and the top of the Pages landing page around the new pictures, in the same
commit — about twenty seconds more.
Then print these three, substituting the slug the script reported, and say they take about a minute to appear because three workflows fire on the push:
https://victorrentea.github.io/human-review/<slug>/
https://github.com/victorrentea/human-review/releases/download/demo/human-review-<slug>.zip
docker run --rm -p 8642:80 ghcr.io/victorrentea/human-review:<slug>That is the whole job. Do not read the report, do not open the page, do not check the
deploy, do not describe the change set, do not hand-edit demo/index.html — the card is
rendered from the snapshot precisely so that nobody keeps it up to date by hand. If the
script exits non-zero, show its stderr and stop.
Not this skill: publishing screenshots of a review — one full-page image per tab,
light and dark, for readers who should not have to run anything — is /human-review-publish-demo.
This one publishes the live page.
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.

