independent-review

Incorporate feedback from an independent code reviewer to improve your solution. The reviewer is a different agent that analyzed your work.

跳到安装查看文件

仓库: benchflow-ai/benchflow
最近来源活动: 2026年6月3日 05:51
检测到的 SKILL.md 语言: 英语
星标: 355
Forks: 74

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 AI 助手安装

复制这段 Prompt，发给你正在使用的 AI 助手。

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/benchflow-ai/benchflow/tree/main/benchmarks/followup-bench.

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/benchflow-ai/benchflow --skill independent-review

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

文件资源管理器

4 个文件

SKILL.md

来源说明 · 只读预览

name: independent-review
description: Incorporate feedback from an independent code reviewer to improve your solution. The reviewer is a different agent that analyzed your work.

# Independent Review Skill When an independent reviewer provides feedback on your code, incorporate it effectively. ## Process 1. Read the reviewer's feedback carefully 2. Identify each specific issue raised 3. Fix only what the reviewer flagged — don't refactor unrelated code 4. If the reviewer says the code is correct, don't make unnecessary changes 5. Verify your fixes address each point ## When reviewer finds bugs - Fix each bug the reviewer identified - Add edge case handling if reviewer pointed out missing cases - Test mentally that the fix resolves the specific issue ## When reviewer approves - Acknowledge the positive review - Do NOT introduce unnecessary changes to working code - "If it ain't broke, don't fix it"

在 GitHub 查看

返回搜索返回安装

benchflow

Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an AI coding agent, run a benchmark suite, create tasks, view trajectories, or compare agent performance.

2026-09-20

benchflow-experiment-review

Review Benchflow or SkillsBench task-run trajectories and integration-test Benchflow code changes. Use this skill whenever the user asks to audit traj health, failed or timed-out runs, healthy pass/fail/timeout status, no-skill leakage, skill loading, reward hacking, verifier isolation, metadata completeness, token usage, timing, Daytona-vs-Docker parity, path/root handling, coverage gaps, Docker/Daytona failures, or release-readiness of benchmark data.

2026-08-22

benchflow-traj-upload-ops

Operate, test, troubleshoot, and explain `bench traj upload` for public or trusted-direct trajectory contributions, including interactive and fully specified commands, dry runs, input validation, local secret masking, trajectory reports and previews, manifest metadata, upload progress, idempotency, and production promotion checks. Use this skill when a maintainer or operator wants to test, inspect, or debug a trajectory upload; validate a trajectory, report, or manifest; or verify the public upload path end to end. For helping a contributor submit their own session, use `benchflow-traj-upload` instead.

2026-08-17

查看这个仓库的全部 Skills

independent-review

来源信息

安装方式

用 AI 助手安装

检查来源文件

同仓库更多 Skills

用 AI 助手安装

同仓库更多 Skills