Results for “cross-review”

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

通用跨模型审查：Review LLM 对任意研究制品进行独立评审，输出结构化评分、wiki 实体映射与改进建议

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

Runs independent AI CLI reviewers over phase plans and merges their feedback into a REVIEWS.md file.

Turn a PR, diff, merge request, or patch stack into one evidence-first review brief with severity, missing-proof checks, and route-outs.

Write, review, refactor, and optimize Slang shader code for graphics, compute, tessellation, and ray tracing pipelines with cross-compilation support.

Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.

Use `review-agent` for a high-risk Engineering Brief when a critical path, architecture boundary, material risk, or multiple downstream tasks need deeper design evidence. Skip ordinary work without those signals.

Reviews a pull request: runs its own baseline review of the PR diff, then a persistent Monitor watches CI and incoming reviewer comments, triages each comment through an independent skeptical agent, applies only verified fixes, and commits+pushes via inline git commands until CI passes and no comments remain to adopt — then asks whether to merge. Use this skill when the user asks to "review a PR", "monitor PR review comments", "address reviewer feedback on #123", or "watch CI on a pull request".

Runs read-only parallel review of a PR, branch, commit, or diff across bugs, security, tests, maintainability, performance, and UI.

Reranking retrieved documents with cross-encoders and LLM rerankers. Cohere Rerank v3, Voyage rerank-2, BGE reranker, ColBERT late interaction, Jina reranker. Cost and latency tradeoffs, top-K in / top-N out strategy. USE WHEN: user mentions "rerank", "reranker", "cross-encoder", "Cohere Rerank", "Voyage rerank", "BGE reranker", "ColBERT", "Jina reranker", "bi-encoder" DO NOT USE FOR: initial retrieval - use `advanced-retrieval` or `hybrid-search`; query rewriting - use `query-transformations`; agent decisions - use `agentic-rag`

multi-llm-review

Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'cross-check this', 'get another perspective', /cross-audit

Runs the current git diff through the Codex CLI for an independent, read-only second-opinion review, then triages findings back into the session for Claude to apply fixes.

Review docs, tool output, skills, and memory candidates for prompt-injection risk.

Verifies that every number, comparison, and scope claim in a research paper matches raw result files, using a fresh cross-model reviewer with no prior context to prevent confirmation bias.

Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated, no cross-pollination), critic analysis, synthesis, founder review, and decision extraction. Use when the user invokes /cs:board, calls a board meeting, or wants structured multi-perspective executive deliberation on a strategic question.

Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.

Route LangSmith work into one workflow packet before touching SDK code. Use when the user needs LangSmith tracing, offline evals, annotation/review queues, prompt-registry decisions, audit/gap review, or cross-service trace propagation for an LLM app or agent workflow. Choose one packet: trace-debug, eval, review, prompt-registry, propagation, or audit. Triggers on: LangSmith, LangChain tracing, `@traceable` / `traceable`, `wrap_openai` / `wrapOpenAI`, datasets, experiments, annotation queues, feedback criteria, Prompt Hub, run trees, trace IDs, or production confidence for an AI feature. Not for generic SLO/alert design, non-LangSmith deployment orchestration, or runtime guardrails outside LangSmith.

Audit, plan, implement, or review Model Context Protocol version and SDK migrations. Use for MCP 2026-07-28, stateless Streamable HTTP, server/discover, removal of initialize or Mcp-Session-Id, MCP Tasks extension changes, full JSON Schema 2020-12 tool schemas, OAuth issuer hardening, deprecated roots/sampling/logging, or cross-version client/server compatibility.

Orchestrate a fleet of parallel `codex exec` workers with you (Claude Code) as the supervisor — spawn one per isolated git worktree, dispatch headless, verify each INDEPENDENTLY, PR/merge. The manual "codex-ultracode" pattern for fanning out real implementation, research, or review work onto Codex. Bakes in the hard gotchas (stdin blocking, background tracking, don't-trust-self-reports, writer isolation). Triggers on — orchestrate codex, codex workers, codex fleet, spawn codex, delegate to codex in parallel, manual ultracode, 开 codex 小弟, 派 codex worker — NOT for a single cross-vendor opinion (use the `second-opinion-codex` agent), NOT for web-UI worker decomposition (use `/orchestrate`).