القائمة
Reviews code changes using CodeRabbit AI. Use when user asks for code review, PR feedback, code quality checks, security issues, or wants autonomous fix-review cycles.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Beads work ledger — hash-ID tasks, atomic bd update --claim, dependency-aware bd ready, intent memory bd remember/prime. PAUL emits beads instead of markdown phases.
Gate 3 verification — permission-denied holdout scenarios, write-tool-less reviewers, evidence files over self-report, veto-rate logging.
Unified bi-temporal knowledge graph over GBrain (PostgreSQL/pgvector) and Graphify (NetworkX/tree-sitter). Treats both stores as a single citation-addressable graph. Query with `brain query --unified "topic"`.
Advanced Engram patterns — progressive disclosure index→timeline→full-fetch (~10x token savings), citation IDs, Seance (interrogate dead predecessors), temporal search.
Golden task eval harness — 20 deterministic tasks with checks.py, 5-run protocol, judge calibration, CI gate on >0.3 regression vs baseline. SWE-smith for auto-generation.
Two-mode loop system — in-session /goal evaluation and overnight fresh-context runner with dual exit gate, circuit breaker, error gate, and relay notes.
| name | code-review |
| description | Reviews code changes using CodeRabbit AI. Use when user asks for code review, PR feedback, code quality checks, security issues, or wants autonomous fix-review cycles. |
AI-powered code review using CodeRabbit. Enables autonomous development workflows where you can implement features, review code, and fix issues without manual intervention.
When user asks to:
# Check CLI
coderabbit --version 2>/dev/null
# Check auth
coderabbit auth status 2>&1
If CLI not installed, tell user:
Please install CodeRabbit CLI first:
curl -fsSL https://cli.coderabbit.ai/install.sh | sh
If not authenticated, tell user:
Please authenticate first by running in your terminal:
coderabbit auth login
coderabbit review --plain
Options:
-t all - All changes (default)-t committed - Committed changes only-t uncommitted - Uncommitted changes only--base main - Compare against specific branchGroup findings by severity and create a task list for issues found.
When user requests implementation + review:
coderabbit review --plainFor more details: https://docs.coderabbit.ai/cli/claude-code-integration