Results for “rev-ai”

Run an AI-assisted PR code review using multi-layer lenses with confidence scoring.

Review pull requests against repository standards using automated validation and manual content review.

Reviews code changes with a second AI reviewer, validates reported issues against the actual code, and reports only confirmed findings.

Evaluate scientific manuscripts and grant proposals with structured, checklist-based peer review covering methodology, statistics, reproducibility, ethics, and reporting standards.

Structured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts preserving user autonomy.

Remove AI writing patterns from prose. Use this skill when writing, drafting, editing, reviewing, or revising any text to eliminate predictable AI tells, slop, and formulaic patterns. Trigger this skill whenever the user asks to "deslop", "de-AI", "make it sound human," "remove AI patterns," "remove AI tropes," "clean up AI writing," fix "slop," "deslop" text, or review prose for authenticity. Also use when the user asks you to write or draft anything and wants it to sound natural rather than AI-generated. Common use cases include scientific writing (manuscripts, abstracts, cover letters, grant narratives, discussion sections, peer review responses), blog posts, newsletters, memos, reports, and any other substantial prose.

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Use when a draft in Turkish, English, or both reads as AI-generated and needs revision that removes machine writing patterns and translation calques while preserving meaning, citations, statistics, and the author's voice.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Use when serving as a peer reviewer and deciding whether and how AI may assist, when a manuscript under review must never be pasted into an external tool, or when a confidentiality-preserving review and disclosure are needed.

Interact with GitLab via helper functions for merge requests, issues, pipelines, and code review comments.

Detect and respond to Adversary-in-the-Middle (AiTM) phishing attacks that use reverse proxy kits like EvilProxy, Evilginx, and Tycoon 2FA to bypass MFA and steal session tokens.

Compose custom Vue components with Reka UI v2 headless primitives, covering asChild/as composition, controlled state, portals, and Radix Vue migration.

任意のリポジトリ（アプリ/ライブラリ/運用スクリプト/コンテンツ等）の種別を判定し、 種別に応じた評価軸（品質・テスト・依存、または検証ゲート等）で**実測ベース**評価して優先度付き改善案を出すスキル。 言語非依存（Python は AST 詳細・その他は近似と明記）。ベンダーコード混入・除外の空振り・偽の成功終了コードなど、 「黙って間違った数値を出す」失敗を構造的に封じる。 「リポジトリレビューして」「コード品質を評価して」「このプロジェクトを診断して」「包括レビュー」「repo-review」 「アーキテクチャ評価して」等で発火。/repo-review でも起動。

Builds or modifies a RAG pipeline with intent-based routing, vector store search, citation rendering, and book fidelity enforcement.

Build production-ready LLM applications, RAG systems, and intelligent agents with architecture design, model selection, and cost controls.

Create a GitHub issue and pull request in oracle/graalvm-reachability-metadata, link the PR to the issue, and request reviews from the standard reviewer set except the PR author.

Prevents AI-introduced regressions with sandbox-mode API testing, automated bug-check workflows, and patterns that catch blind spots where the same model writes and reviews code.

Build or modify a RAG retrieval pipeline with vector store search, corpus routing, citation rendering, and book fidelity enforcement.

Build interactive animations with Rive — load .riv files, control state machines, respond to user input, and embed runtime animations in web and mobile apps. Use when tasks involve interactive UI animations, character animations with state logic, animated icons with hover/click states, or game-like interactions in production apps.

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

Analyzes runtime history to identify failures and inefficiencies, then autonomously writes improvements using a protocol-constrained evolution engine. Communicates with EvoMap Hub via a local Proxy mailbox.

Structures a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

AI code reviewer grounded in classic software engineering books for catching design smells, coupling issues, and architectural risks.