Demo Reviewer — Development agent for Claude Code
Judges screenshots of one book2sim demo against what each cue's note promises.
How to install Demo Reviewer
Installs to ~/.claude/agents/ccy5123-book2sim-demo-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ccy5123/book2sim/HEAD/.claude/agents/demo-reviewer.md -o ~/.claude/agents/ccy5123-book2sim-demo-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Demo Reviewer does
name: demo-reviewer description: Judges screenshots of one book2sim demo against what each cue's note promises. Read-only; returns a JSON verdict per cue. tools: Read, Glob, Grep model: sonnet effort: medium
You review one interactive demo of a book2sim companion by looking at screenshots. You did not write it; judge it as a reader would. Be strict about what is visible, not about style.
Inputs (given in your task)
WORK: the book's work folder; the viewer's book folder is `WORK
Alternatives in Development
- PHP Review — Read-only reviewer for PHP code cleanliness a linter cannot catch 80 ★
- Uxaudit L4 Judge — L4-journey Judge for the uxaudit pipeline 52 ★
- Userguide Reviewer — Use this agent to review user guide documentation against actual system features 48 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Reviewer Dev
Independent read-only reviewer for the dev lane. Judges a diff against the approved acceptance criteria in a f
Comprehension Gate
Cold-reads code review comment bodies with no diff and no code access and judges whether a reader can tell wha
Pin Auditor
Audits validator checks for VACUITY — a pin that reports green against the mutation it was written to catch. R
Harnie Reviewer
Read-only code reviewer with a REJECT bias. Reviews the builder's changes in the cross-model code loop and ret
Re Reviewer
Read-only verifier that checks whether prior review findings have been addressed in a PR's new commits. Return
Casper
CASPER-3, the woman. Judges a proposition on pragmatics — whether it can actually be run, maintained, and live
Related Skills
Claim Audit
A Claude skill that audits AI-written text claim by claim: quotes each checkable claim, tags it with one of te
Dsh Auto Review
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns stru
Squad Review
Run only the reviewer agent against the current run's code and tests. Produces a PASS/FAIL verdict and routes