Eval Reviewer — Development agent for Claude Code
Eval reviewer for an organization on GTM OS.
How to install Eval Reviewer
Installs to ~/.claude/agents/ay-automate-gtmos-skills-eval-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ay-automate/gtmos-skills/HEAD/agents/eval-reviewer.md -o ~/.claude/agents/ay-automate-gtmos-skills-eval-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Eval Reviewer does
name: eval-reviewer description: "Eval reviewer for an organization on GTM OS. Use to check what the org's agents and missions did: \"review the agent runs\", \"did any agent break a rule\", \"agent regressions this week\", before widening an agent's autonomy. Reads run journals, approvals, ledger and audit, scores each run PASS / NEEDS_IMPROVEMENT / FAIL per check, and reports regressions. Never writes." tools: Read, Grep, Glob, mcp__gtmos__gtm_describe, mcp__gtmos__gtm_query, mcp__gtmos__g
Alternatives in Development
- Civitai Perf Review — Reviews a feature segment in the main Civitai Next.js app (src/) for production performance — N+1 queries, uni 7.2k ★
- Powersync Sync Reviewer — Use to review any change that touches PowerSync synced tables before merging — diffs that modify shared/powers 4.8k ★
- Fatal Error Check — Fast pre-review check for fatal errors in LaTeX papers 130 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Deal Reviewer
Deal reviewer for an organization on GTM OS. Use for \"review this deal\", \"which deals are at risk\", \"deal
Org Reviewer
First-pass code review against the organization rubric before a change goes to main. Read-only; reports findin
Ads Analyst
Ads analyst for an organization on GTM OS. Use for campaign performance, pacing, CAC against target, \"where s
Lw Verifier
Adversarial verification. Use to independently check that a change is correct, that tests genuinely pass, or t
Org Conformance
Reports what a repository is missing against the organization standard (flake, agent baseline, settings, ADR f
Progression Planner
Defines how the programme advances week by week — the overload rule per session type, the deload, autoregulati
Related Skills
Jidoka Health
Full jidoka health check — eval, engine self-tests, ghosts, measured judges, regressions
Livewire Alpine Skills
Agent Skills for Laravel Livewire v4 + Alpine.js v3. Recipes EXECUTED against a real install (14 tests), a 21-
AI Marketing OS
Run your marketing org as an orchestrated AI team instead of a $50K/mo tool stack and scarce specialists. 9 ag