linus-review
Run a strict Linus-style code review focused on correctness, backward compatibility, simplicity, data structures, special cases, hardcoded values, root-cause proof, maintainability, and verification. Use when the user asks for Linus mode, Linus review, a blunt maintainer review, harsh review, kernel-style review, or an especially skeptical code review.
- License 许可
- MIT
- 最近更新
- 2026-11-03
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- linus-review
- description
- Run a strict Linus-style code review focused on correctness, backward compatibility, simplicity, data structures, special cases, hardcoded values, root-cause proof, maintainability, and verification. Use when the user asks for Linus mode, Linus review, a blunt maintainer review, harsh review, kernel-style review, or an especially skeptical code review.
03 SKILL.md 正文
<!-- agent-workbench: managed portable-skill -->
Linus Review
Dispatch
Use the tier, delivery boundary, and escalation rule for linus-review in AI_AGENT_GUIDE.md's Skill Model and Reasoning Routing table, and resolve the tier through the active platform binding.
Workflow
- Read
.agents/prompts/linus-review.mdif present. - Do not impersonate Linus Torvalds; use a direct maintainer-style review stance.
- Identify the review target: working tree diff, staged diff, branch diff, PR diff, files, or pasted patch.
- Inspect surrounding code before judging.
- Review for correctness, compatibility, simplicity, data model quality, special cases, hardcoded paths or arbitrary values, proven root cause, error paths, and verification gaps.
- Return
ACK,NACK, orNEEDS WORKwith concrete findings and file references. - Do not edit code unless the user explicitly asks for fixes.
Output
Use the structure from .agents/prompts/linus-review.md: verdict, top issues, good taste check, compatibility check, verification gaps, and bottom line.
04 同仓库更多 Skills
sync-agent-workbench
Synchronize the fixture workbench.
sync-agent-workbench
Synchronize, audit, or repair composable agent-workbench policy in a project. Use when a user wants canonical AI_AGENT_GUIDE.md, thin vendor loader entrypoints, project-selected profiles, portable prompts, and standard Agent Skills without depending on a marketplace, plugin, global config, or submodule.
skill-authoring
Create or update portable Agent Skills under .agents/skills with concise SKILL.md instructions and optional scripts, references, or assets. Use when a user wants skill-creator behavior that works across Codex, Gemini, Claude Code, OpenCode, or other agents without relying on one vendor's built-in creator.
math-pdf-reader
Read, transcribe, summarize, or verify mathematical PDFs with high fidelity by combining rendered-page inspection, cautious text extraction, version-matched source checks, and explicit uncertainty. Use for theorem, proof, formula, notation, attribution, or bibliographic work where ordinary PDF text extraction can silently corrupt mathematical content.
loop-until-done
Keep working on a requested task through bounded work, root-cause diagnosis, verification, and retry iterations until explicit completion criteria are met or a maximum iteration limit is reached. Use for Ralph-style self-correction without requiring Claude plugins, Codex plugins, Gemini extensions, or hook support.
integrate-chatgpt-conversation
Retrieve and integrate the current accessible branch of a user-supplied ChatGPT conversation mention or direct ChatGPT URL. Use when a task depends on the full live transcript, including when the user asks to synthesize, review, or update project files from it, with authenticated recovery, scope-preserving acceptance tracking, explicit completeness boundaries, bounded independent mathematical repair, durable deferred-task recording, and downstream validation.