Menú
Bridgebuilder — Autonomous PR Review
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| name | bridgebuilder-review |
| description | Bridgebuilder — Autonomous PR Review |
| capabilities | {"schema_version":1,"read_files":true,"search_code":true,"write_files":true,"execute_commands":true,"web_access":true,"user_interaction":false,"agent_spawn":true,"task_management":false} |
| cost-profile | heavy |
| zones | {"system":{"path":".claude","permission":"read"},"state":{"paths":["grimoires/bridgebuilder"],"permission":"read"},"app":{"permission":"none"}} |
gh CLI installed and authenticated (gh auth status)ANTHROPIC_API_KEY environment variable set/bridgebuilder # Review all open PRs on auto-detected repo
/bridgebuilder --dry-run # Preview reviews without posting
/bridgebuilder --pr 42 # Review only PR #42
/bridgebuilder --repo owner/repo # Target specific repo
/bridgebuilder --no-auto-detect # Skip git remote detection
git remote -v (unless --no-auto-detect)gh CLI<!-- bridgebuilder-review: {sha} -->)COMMENT or REQUEST_CHANGES){ reviewed, skipped, errors }Set in .loa.config.yaml under bridgebuilder: section, or via environment variables:
| Setting | Env Var | Default |
|---|---|---|
| repos | BRIDGEBUILDER_REPOS | Auto-detected from git remote |
| model | BRIDGEBUILDER_MODEL | claude-opus-4-6 |
| dry_run | BRIDGEBUILDER_DRY_RUN | false |
| max_prs | — | 10 |
| max_files_per_pr | — | 50 |
| max_diff_bytes | — | 100000 |
| max_input_tokens | — | 8000 |
| max_output_tokens | — | 4000 |
| persona_path | — | grimoires/bridgebuilder/BEAUVOIR.md |
Override the default reviewer persona by creating grimoires/bridgebuilder/BEAUVOIR.md. The default persona reviews across 4 dimensions: Security, Quality, Test Coverage, and Operational Readiness.
This skill runs entry.sh which invokes the compiled Node.js application:
.claude/skills/bridgebuilder-review/resources/entry.sh [flags]
| Code | Meaning |
|---|---|
| 0 | All reviews completed successfully |
| 1 | One or more reviews encountered errors |
Security and quality audit of application codebase
Autonomous agent execution mode
Browse and install construct packs from the Loa Constructs Registry
Triage a bug report through structured phases and create micro-sprint
BUTTERFREEZONE Generation Skill
Autonomous skill extraction from debugging discoveries. Activates when agents find non-obvious solutions through investigation, experimentation, or trial-and-error. Captures these discoveries as reusable skills for future sessions.