How do I install the Pr Agent Judge skill?

Run npx skillmds@latest add gonzalezpazmonica/pr-agent-judge in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Pr Agent Judge skill do?

Usar cuando se añade pr-agent como juez externo en el Code Review Court. It is listed under AI & ML on SkillMD.

Is Pr Agent Judge safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Pr Agent Judge?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Pr Agent Judge free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Pr Agent Judge?

gonzalezpazmonica (@gonzalezpazmonica) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Pr Agent Judge by gonzalezpazmonica

Name: Pr Agent Judge
Rating: 4.666666666666667 (3 reviews)
Author: gonzalezpazmonica

File contents

Skill: pr-agent-judge (SPEC-124)

Wrapper sobre qodo-ai/pr-agent (10.9k ⭐, 60.1% F1) como juez externo opt-in del Code Review Court.

Rol dentro del Court

Court actual: 4 jueces (correctness, security, architecture, cognitive). Con opt-in: 5 jueces → añade diversidad (jueces externos con benchmark público).

Se activa solo si COURT_INCLUDE_PR_AGENT=true en pm-config.md.

Invocación

# Modo local (sin CI)
bash scripts/pr-agent-run.sh --pr-number 593 --mode review --output court-format

Salida JSON compatible con formato Court:

{
  "judge": "pr-agent",
  "version": "qodo-ai/pr-agent@0.27",
  "verdict": "approve | request_changes | comment",
  "findings": [
    {
      "severity": "medium",
      "category": "correctness",
      "file": "src/foo.ts",
      "line": 42,
      "message": "..."
    }
  ],
  "summary": "..."
}

Modos

review — code review completo
describe — descripción automática del PR
improve — sugerencias de mejora

Requirements

pr-agent instalado: pip install pr-agent o Docker
GITHUB_TOKEN env var (para acceder al PR)
Anthropic API key o compatible (PR_AGENT_MODEL en pm-config.md). Por defecto resuelto via tier: mid → ~/.savia/preferences.yaml model_mid.

Si pr-agent no está instalado, el wrapper falla gracefully reportando {"status":"SKIPPED","reason":"pr-agent not installed"} sin bloquear al Court.

Feature flags en pm-config.md

COURT_INCLUDE_PR_AGENT   = false        # default opt-in
PR_AGENT_VERSION         = "0.27"       # pin
PR_AGENT_MODEL           = "mid"        # tier, resuelto via preferences.yaml
PR_AGENT_MAX_LINES       = 1000         # evita token blowout

Relación con agentes internos

Complementa correctness-judge, security-judge, architecture-judge, cognitive-judge.
NO reemplaza ninguno — opt-in para diversity, no para rebaja.
Orchestrator (court-orchestrator) agrega los 5 verdicts con policy ya definida.

Cuándo NO usar

PRs > 1000 líneas (coste token excesivo — usar flag PR_AGENT_MAX_LINES)
PRs de docs-only (rendimiento bajo del tool en ese contexto)
Rama agent/* autogenerada (evitar feedback loop self-review)

Referencias

qodo-ai/pr-agent
SPEC-124 — docs/propuestas/SPEC-124-pr-agent-wrapper.md
.claude/agents/court-orchestrator.md

---name: pr-agent-judgedescription: Usar cuando se añade pr-agent como juez externo en el Code Review Court.---# Skill: pr-agent-judge (SPEC-124)> Wrapper sobre [qodo-ai/pr-agent](https://github.com/qodo-ai/pr-agent) (10.9k ⭐, 60.1% F1) como juez externo opt-in del Code Review Court.## Rol dentro del CourtCourt actual: 4 jueces (correctness, security, architecture, cognitive).Con opt-in: 5 jueces → añade diversidad (jueces externos con benchmark público).Se activa solo si `COURT_INCLUDE_PR_AGENT=true` en `pm-config.md`.## Invocación```bash# Modo local (sin CI)bash scripts/pr-agent-run.sh --pr-number 593 --mode review --output court-format```Salida JSON compatible con formato Court:```json{ "judge": "pr-agent", "version": "qodo-ai/pr-agent@0.27", "verdict": "approve | request_changes | comment", "findings": [ { "severity": "medium", "category": "correctness", "file": "src/foo.ts", "line": 42, "message": "..." } ], "summary": "..."}```## Modos- `review` — code review completo- `describe` — descripción automática del PR- `improve` — sugerencias de mejora## Requirements- [pr-agent](https://github.com/qodo-ai/pr-agent) instalado: `pip install pr-agent` o Docker- `GITHUB_TOKEN` env var (para acceder al PR)- Anthropic API key o compatible (`PR_AGENT_MODEL` en pm-config.md). Por defecto resuelto via tier: `mid` → `~/.savia/preferences.yaml` model_mid.Si `pr-agent` no está instalado, el wrapper **falla gracefully** reportando `{"status":"SKIPPED","reason":"pr-agent not installed"}` sin bloquear al Court.## Feature flags en pm-config.md```COURT_INCLUDE_PR_AGENT = false # default opt-inPR_AGENT_VERSION = "0.27" # pinPR_AGENT_MODEL = "mid" # tier, resuelto via preferences.yamlPR_AGENT_MAX_LINES = 1000 # evita token blowout```## Relación con agentes internos- Complementa `correctness-judge`, `security-judge`, `architecture-judge`, `cognitive-judge`.- NO reemplaza ninguno — opt-in para diversity, no para rebaja.- Orchestrator (`court-orchestrator`) agrega los 5 verdicts con policy ya definida.## Cuándo NO usar- PRs > 1000 líneas (coste token excesivo — usar flag PR_AGENT_MAX_LINES)- PRs de docs-only (rendimiento bajo del tool en ese contexto)- Rama `agent/*` autogenerada (evitar feedback loop self-review)## Referencias- [qodo-ai/pr-agent](https://github.com/qodo-ai/pr-agent)- SPEC-124 — docs/propuestas/SPEC-124-pr-agent-wrapper.md- `.claude/agents/court-orchestrator.md`

Frequently asked questions

Pr Agent Judge