Round Verification
SeemSeam/claude_codex_bridge
Verify a CCB execution round and produce a machine-readable round result artifact.
处理当前 PR 的一轮 Codex 评审反馈。从读取评审信号、逐条定位根因、修复、验证、回复线程到推送的完整单轮流程。当用户请求"处理评审意见"、"处理下一轮反馈"、"看看 Codex 说了什么"或类似单轮评审响应任务时触发。不负责合并。
GPL-3.0Auto-check passed
Install Review Round
$ npx skills add sky1wu/Bili-SyncPlay --skill review-round -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sky1wu/Bili-SyncPlay review-round --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sky1wu/Bili-SyncPlay.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/review-round .claude/skills/review-round && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "review-round" agent skill from https://github.com/sky1wu/Bili-SyncPlay/tree/main/.claude/skills/review-round into .claude/skills/review-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-round", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sky1wu/Bili-SyncPlay/tree/main/.claude/skills/review-roundType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sky1wu/Bili-SyncPlay --skill review-round -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sky1wu/Bili-SyncPlay review-round --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sky1wu/Bili-SyncPlay.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/review-round .agents/skills/review-round && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "review-round" agent skill from https://github.com/sky1wu/Bili-SyncPlay/tree/main/.claude/skills/review-round into .agents/skills/review-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-round", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sky1wu/Bili-SyncPlay --skill review-round -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sky1wu/Bili-SyncPlay review-round --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sky1wu/Bili-SyncPlay.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/review-round .cursor/skills/review-round && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "review-round" agent skill from https://github.com/sky1wu/Bili-SyncPlay/tree/main/.claude/skills/review-round into .cursor/skills/review-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-round", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sky1wu/Bili-SyncPlay.git --path .claude/skills/review-round--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sky1wu/Bili-SyncPlay --skill review-round -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sky1wu/Bili-SyncPlay review-round --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sky1wu/Bili-SyncPlay.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/review-round .gemini/skills/review-round && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "review-round" agent skill from https://github.com/sky1wu/Bili-SyncPlay/tree/main/.claude/skills/review-round into .gemini/skills/review-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-round", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sky1wu/Bili-SyncPlay review-roundInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sky1wu/Bili-SyncPlay --skill review-round -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sky1wu/Bili-SyncPlay.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/review-round .github/skills/review-round && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "review-round" agent skill from https://github.com/sky1wu/Bili-SyncPlay/tree/main/.claude/skills/review-round into .github/skills/review-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-round", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sky1wu/Bili-SyncPlay --skill review-round -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sky1wu/Bili-SyncPlay review-round --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sky1wu/Bili-SyncPlay.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/review-round .opencode/skills/review-round && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "review-round" agent skill from https://github.com/sky1wu/Bili-SyncPlay/tree/main/.claude/skills/review-round into .opencode/skills/review-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-round", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
review-round- GitHub stars
- 168
- Token cost
- ~1.5k tokens
- SKILL.md length
- 358 words
- Files
- 8 (incl. scripts)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
处理当前 PR 的一轮 Codex 评审反馈。从读取评审信号、逐条定位根因、修复、验证、回复线程到推送的完整单轮流程。当用户请求"处理评审意见"、"处理下一轮反馈"、"看看 Codex 说了什么"或类似单轮评审响应任务时触发。不负责合并。
- Works in 9 steps: 确定 PR 编号，切到它的 head 分支并校验 → 读未解决的评审线程（权威信号） → 核对每条线程对应的是当前 HEAD → …
- SKILL.md covers 0. 确定 PR 编号，切到它的 head 分支并校验, 1. 读未解决的评审线程（权威信号）, 2. 核对每条线程对应的是当前 HEAD and 3. 逐条陈述根因，再改, plus 6 more sections
- Runs Shell scripts from its folder; calls git, gh and npm
What it does
Review Round is an agent skill from sky1wu/Bili-SyncPlay. 处理当前 PR 的一轮 Codex 评审反馈。从读取评审信号、逐条定位根因、修复、验证、回复线程到推送的完整单轮流程。当用户请求"处理评审意见"、"处理下一轮反馈"、"看看 Codex 说了什么"或类似单轮评审响应任务时触发。不负责合并。
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts (for example `scripts/has-changes.sh`, `scripts/lib.sh` and `scripts/list-unresolved.sh`).
The repository describes itself as: Synchronize Bilibili playback across a room. The licence is GPL-3.0.
Example prompts
- “处理评审意见”
- “处理下一轮反馈”
- “看看 Codex 说了什么”
- “/review-round”
Requirements
- A Bash shell
Workflow steps
9 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e0c87de. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 7 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
gitghnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, gh and npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Review Round loads about 1.5k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 358 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from sky1wu/Bili-SyncPlay at commit e0c87de, republished under its GPL-3.0 licence (© sky1wu). 358 words, ~1,495 tokens.
Download SKILL.mdSave it as
.claude/skills/review-round/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- review-round
- description
- 处理当前 PR 的一轮 Codex 评审反馈。从读取评审信号、逐条定位根因、修复、验证、回复线程到推送的完整单轮流程。当用户请求"处理评审意见"、"处理下一轮反馈"、"看看 Codex 说了什么"或类似单轮评审响应任务时触发。不负责合并。
review-round — 处理一轮 Codex 评审反馈
处理一轮评审。任何一步失败都先修复再进下一步，不要跳步。
易错的多步操作都在 scripts/ 下，不要把它们抄成一次性命令——脚本里带着错误处理、
翻页和判别力测试，散写在对话里的版本必然会丢掉其中某一项（这份技能的前三轮评审共
20 条意见，绝大多数正是这么来的）。
| 脚本 | 作用 |
|---|---|
verify-branch.sh <PR> | 校验本地分支名 和 SHA 与 PR head 一致；拒 fork |
list-unresolved.sh <PR> | 翻页列出全部未解决线程，正文不截断，标注所属 commit |
has-changes.sh | 判断本轮有无改动（含未跟踪文件） |
reply-resolve.sh | 重读线程 → 回复 → 确认 → resolve |
round-signal.sh <PR> | 无未解决线程时区分「通过」与「没触发」 |
selftest.sh [PR] | 对上述防护做判别力测试 |
改动这些脚本后必须跑 .claude/skills/review-round/scripts/selftest.sh <PR编号>。
0. 确定 PR 编号，切到它的 head 分支并校验
后面每个代码块都用 $PR，先把它定下来（Bash 工具不保留 shell 状态，每次新开的
代码块都要重新赋值，或直接把编号写进命令）：
PR=<编号> # 用户指定了就用指定的
PR=$(gh pr view --json number --jq .number) # 否则取当前分支对应的 PR
[ -n "$PR" ] || { echo "无法确定 PR 编号"; exit 1; }
.claude/skills/review-round/scripts/verify-branch.sh "$PR" --switch技能可能从 main 或别的分支启动。只比分支名不够：同名本地分支可能落后于远端，那样
你会基于旧代码处理反馈、把针对当前提交的意见误判成过时，直到 push 被非快进拒绝才
暴露。脚本同时校验 headRefOid，并拒绝 main/master 与 fork PR。
1. 读未解决的评审线程（权威信号）
.claude/skills/review-round/scripts/list-unresolved.sh "$PR"不要用 reaction 判断有没有意见。 本仓库实测：意见最多的 PR221（11 条）和 PR222
（14 条）reaction 完全为空；而 PR220、PR224 有 👍 但 reviews 和 comments 都是 0。
两种信号各自都会漏判，必须以线程为准。REST 的 pulls/$PR/comments 也不行——它不返回
解决状态，第 2 轮会把上一轮已 resolve 的意见重新摆上清单。
脚本已经处理掉这几件事，看输出即可：正文完整不截断（只剥 shields.io 徽章，保留评审者
贴的截图）、读完线程里每一条评论、按游标翻页取全、每条评论标注 [作者 @sha]。
API 或解析失败时脚本以非零退出——「没读到」绝不能被当成「没有」。
有未解决线程 → 进第 2 步。一条都没有 → 进第 8 步。
2. 核对每条线程对应的是当前 HEAD
git rev-parse --short HEAD拿它和第 1 步输出里每条评论的 @sha 比。要逐线程比，不能只看全局 review 列表：
PR 上有多轮评审时列表里既有旧 SHA 也有当前 SHA，无从对应。本仓库 PR225 实测就同时
挂着 2ab3b09 和 938c337 两轮的线程。@sha 不是当前 HEAD 的，先确认那条是否仍成立。
3. 逐条陈述根因，再改
先把清单摆出来并标注严重级别（P1/P2），不要边看边改。对每一条：
- 用一句话陈述根因，而不是复述现象。
- 点名证明它的代码路径或日志行。
- 然后才编辑。
- 每次 Edit/Write 之后立刻重读改动区域，确认改动真的落地了，再动下一处。 静默失败的字符串替换在本仓库发生过多次；拖到第 5 步才发现，意味着中间的审计全部 建立在一处并不存在的改动上。
宁要单一根因修复，不要层叠补丁。 若修复需要在已有的抑制标志 / 冷却期 / 特例分支
之上再加一个，停下来重新推导根因——见 AGENTS.md 的 ## Debugging Sync Bugs。
编辑前必须先记一份工作树基线，第 5 步要拿它判断本轮到底改了什么：
.claude/skills/review-round/scripts/has-changes.sh --baseline /tmp/rr-baseline4. 审计同类路径（不要只修被标的那一行）
被标出的往往只是同一类问题的一个实例。
- grep 出被改签名的全部调用点，含
server/src/app.ts与各index.ts适配层。 编译器的边界见 AGENTS.md 的## Protocol Changes第 2 条。 - 状态清理 / reset 函数：grep 每一处相关状态，逐一确认。
- 异步 Redis / 锁操作：确认都
await且包了try/catch。 - 协议相关改动：走 AGENTS.md 的
## Protocol Changes清单。
逐个列出「已处理 / 不适用及原因」，再进下一步。
Show full SKILL.md (219 more words)Show less
5. 验证
.claude/skills/review-round/scripts/has-changes.sh /tmp/rr-baseline || echo "本轮无改动，跳到第 7 步"判断的是相对第 3 步基线的新增，两个方向都得防住：
- 用
git status --porcelain而非git diff --quiet——后者看不到未跟踪文件，只新增 测试或文档的一轮会被误判成无改动，跳过验证和提交却仍去 resolve，改动就此丢失。 - 但也不能直接看工作树是否非空——技能启动前就存在的无关未提交文件，会让「本轮只需
解释或拒绝意见」的轮次误判成有改动，卡在无内容可提交的
git commit上，永远到不了 第 7 步。
有改动时：
对全部改动做提交前复核，确认没有被后续编辑覆盖掉。
新增的回归测试必须在修复前的代码上失败。回退修复时只回退源文件：
bash cp <源文件> /tmp/fix.bak # 事前备份 # …验证… cp /tmp/fix.bak <源文件> # 还原不要整仓
git stash：新测试若追加在已跟踪的测试文件里会被一起 stash 走，测试 因「找不到用例」而退出非零，看着是红的，其实什么都没验证。确认失败原因是断言 失败，不是用例不存在。跑完整预提交序列，逐项断言退出码：
bash fail="" for step in format:check lint typecheck build test audit; do npm run "$step" > "/tmp/rr-$step.log" 2>&1 code=$? echo "$step exit=$code log=/tmp/rr-$step.log" if [ $code -ne 0 ]; then echo "===== $step 完整输出 ====="; cat "/tmp/rr-$step.log" fail="$step"; break fi done if [ -n "$fail" ]; then echo "FAILED: $fail"; exit 1; fi echo "ALL-GREEN"失败必须
exit 1，否则依赖退出状态的执行者会带着未通过的检查继续提交。[ $code -ne 0 ] && { …; break; }那种写法的循环退出码是反的（全绿返回 1、 失败返回 0）。失败时cat完整日志而非tail -40——AGENTS.md 要求报告真实输出。 严禁npm run typecheck | tail：管道让退出码变成tail的。
6. 提交、推送
git add <本轮实际改动的具体文件> # 严禁 git add -A / git add .
git diff --cached # 核对暂存内容
git commit -m "fix: ..."
# 推送前复验（中途可能被切走）。--allow-ahead 是必须的：刚 commit 完本地一定
# 领先远端 headRefOid，严格相等会让每个有提交的轮次都在 push 前中止。
.claude/skills/review-round/scripts/verify-branch.sh "$PR" --allow-ahead
git push origin "HEAD:$(gh pr view "$PR" --json headRefName --jq .headRefName)"对第 3 步基线里本来就脏的文件，用 git add -p 按 hunk 只暂存本轮补丁——显式写
文件名并不足以隔离改动，用户在技能启动前的未提交修改会被一起提交。
7. 回复并 resolve 线程
.claude/skills/review-round/scripts/reply-resolve.sh <线程id> "已修。<改在哪、怎么验证的；不采纳则写明理由>" <第1步看到的评论数>脚本会先重读线程：若评论数与第 1 步不一致，说明扫描之后评审者又补了内容，此时拒绝
resolve 并打出最新一条，让你先把它纳入根因分析。确认回复拿到 comment id 之后才
resolve——只跑 resolveReviewThread 会把线程静默关掉，评审者看不到改在哪。
收尾用 .claude/skills/review-round/scripts/list-unresolved.sh "$PR" --count 确认归零。
8. 本轮结束——不要合并
.claude/skills/review-round/scripts/round-signal.sh "$PR"输出 PASSED / REVIEWING / NOT-TRIGGERED。
reaction 长期留存且不带 commit 引用，所以脚本用「当前 HEAD 触发的最早一次 workflow
run 的 created_at」作为推送时刻基准，并且只认 Codex 机器人的 reaction。该 SHA 尚无
run 时直接判 NOT-TRIGGERED——此时若拿空字符串当阈值，created_at > "" 会选中所有
历史 reaction，旧的 👍 就成了「本轮通过」。
NOT-TRIGGERED 不等于没问题：评论 @codex review 触发，别空等。
合并需要用户针对这个 PR 的明确授权，关于发版的含糊表述不是合并授权。
硬性规则
- 严禁在没有用户明确指令的情况下
gh pr merge。 - 严禁只凭 reaction 判断有没有意见——以未解决线程为准。
- 严禁把脚本抄成一次性命令。要改行为就改脚本，并跑
selftest.sh。 - 严禁只修被标的那一行而不审计同类路径。
- 严禁把检查命令管道给
tail/head后据此判断成败。 - 严禁
git add -A/git add .。 - 严禁用
git checkout <file>/git restore <file>回退探针——会连同该文件其它 未提交改动一起冲掉。先cp备份或git stash push -- <仅源文件路径>。 - 未真正跑过的检查，不得声称已验证。
© sky1wu, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files (scripts) in .claude/skills/review-round of sky1wu/Bili-SyncPlay.
- SKILL.md
- scripts/has-changes.sh
- scripts/lib.sh
- scripts/list-unresolved.sh
- scripts/reply-resolve.sh
- scripts/round-signal.sh
- scripts/selftest.sh
- scripts/verify-branch.sh
Open the folder on GitHubat commit e0c87de
Compare with similar skills
Review Round next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Review Round this skillsky1wu/Bili-SyncPlay | 168 | — | ~1.5k | Automated safety check: Pass | GPL-3.0 | |
| Round VerificationSeemSeam/claude_codex_bridge | 3.6k | — | ~228 | Automated safety check: Pass | Custom licence | |
| Round VerificationSeemSeam/claude_codex_bridge | 3.6k | — | ~486 | Automated safety check: Pass | Custom licence | |
| Release Roundethereumjs/ethereumjs-monorepo | 2.8k | — | ~2k | Automated safety check: Pass | None | |
| UI Devwidget RoundafkT/DevUtils | 1.6k | — | ~880 | Automated safety check: Pass | Apache-2.0 | |
| Cy Review Roundcompozy/compozy | 2.8k | — | ~2.7k | Automated safety check: Pass | MIT |
Similar skills
Round Verification
SeemSeam/claude_codex_bridge
Verify integrated round evidence and return a machine-readable round result for script import.
Release Round
ethereumjs/ethereumjs-monorepo
Runs a coordinated EthereumJS npm release round in six human-gated phases — intent and readiness, CHANGELOG, version bump, publish (human executes), post-publish verification, and announcements.
UI Devwidget Round
afkT/DevUtils
在需要圆角矩形纯色背景、描边边框时，优先用 DevWidget（io.github.afkt:DevWidgetX）的 dev.widget.ui.round 包替代 shape / layer-list drawable。流程与核心坑在 SKILL，Round 系列 View、R.styleable.DevWidget 中 app:dev 属性及源码对照见…
Cy Review Round
compozy/compozy
Performs a comprehensive code review of a spec implementation and generates a review round directory with issue files compatible with cy-fix-reviews.
Rounding
RConsortium/pharma-skills
Audit R code that prepares CSR/TLF statistics for SAS-compatible rounding compliance (ties away from zero, round-once-at-display, fixed trailing-zero precision).
More from sky1wu/Bili-SyncPlay
Add Feature
sky1wu/Bili-SyncPlay
端到端的 GitHub feature 开发工作流。接受 feature 简述或 issue 编号，从澄清需求到建分支、设计、实现、测试、推送、开 PR、处理评审、合并的完整流程。当用户请求"新增功能 X"、"实现 feature Y"、"给我加一个 ..."等端到端特性开发任务时触发。
Fix Issue
sky1wu/Bili-SyncPlay
端到端的 GitHub issue 修复工作流。接受 issue 编号作为参数，从查看 issue 到建分支、实现修复、推送、开 PR、处理评审、合并的完整流程。当用户请求"修复 issue
Questions about Review Round
What does Review Round do?
处理当前 PR 的一轮 Codex 评审反馈。从读取评审信号、逐条定位根因、修复、验证、回复线程到推送的完整单轮流程。当用户请求"处理评审意见"、"处理下一轮反馈"、"看看 Codex 说了什么"或类似单轮评审响应任务时触发。不负责合并。. Review Round is an agent skill from sky1wu/Bili-SyncPlay.
How do I install Review Round in Claude Code?
Run `npx skills add sky1wu/Bili-SyncPlay --skill review-round -a claude-code`. Or copy the skill folder (.claude/skills/review-round in sky1wu/Bili-SyncPlay) into .claude/skills/review-round in your project. Claude Code loads it when a task matches its description.
How do I install Review Round in Codex?
Run `npx skills add sky1wu/Bili-SyncPlay --skill review-round -a codex`. Or copy the skill folder (.claude/skills/review-round in sky1wu/Bili-SyncPlay) into .agents/skills/review-round in your project. Codex loads it when a task matches its description.
Can I use Review Round in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sky1wu/Bili-SyncPlay --skill review-round -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-round, .gemini/skills/review-round, .github/skills/review-round and .opencode/skills/review-round in your project.
What does Review Round need to run?
Going by SKILL.md and its folder, Review Round needs a shell for the scripts in its folder and the command-line tools its instructions call (git, gh and npm). Our summary lists: A Bash shell.
Does Review Round access the network?
SKILL.md contains no URLs. Its commands use git, gh and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Review Round safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Review Round use?
Review Round is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Review Round use?
About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Review Round?
Skills that share tags, products or a category with Review Round: Round Verification (SeemSeam/claude_codex_bridge, 3.6k stars), Round Verification (SeemSeam/claude_codex_bridge, 3.6k stars), Release Round (ethereumjs/ethereumjs-monorepo, 2.8k stars) and UI Devwidget Round (afkT/DevUtils, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Review Round?
sky1wu (a GitHub user) maintains it in sky1wu/Bili-SyncPlay, which has 168 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 21, 2026.
Source: sky1wu/Bili-SyncPlay on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.