Borrowing it
Nothing to install: this file belongs to shenjingnan/xiaozhi-client. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shenjingnan/xiaozhi-client/main/.agents/skills/fix-comment/SKILL.mdgit clone --depth 1 https://github.com/shenjingnan/xiaozhi-clientWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shenjingnan/xiaozhi-client/fix-comment)<a href="https://agentmods.dev/skills/shenjingnan/xiaozhi-client/fix-comment"><img src="https://agentmods.dev/badge/skills/shenjingnan/xiaozhi-client/fix-comment/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shenjingnan/xiaozhi-client/fix-comment"><img src="https://agentmods.dev/badge/skills/shenjingnan/xiaozhi-client/fix-comment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.01402 |
| Opus 5.5 | $0.00009 | $0.00561 |
| Sonnet 5.5 | $0.00004 | $0.00280 |
| Haiku 4.5 | $0.00002 | $0.00140 |
Grade A, and why
fix-comment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub 评论修复技能
我是一个 GitHub PR 评论处理专家,专门获取 Copilot 评论并分析修复相关问题。
我的能力
当你需要处理 GitHub PR 中的 Copilot 评论时,我会:
- 解析 PR 信息 - 从输入中提取 PR 编号或 URL
- 获取分支名 - 获取 PR 对应的分支名
- 管理 worktree - 检查/创建/清理 git worktree
- 分析评论 - 获取 PR 评论并分析是否真的存在问题
- 修复问题 - 如果确实存在问题,修复代码并提交推送
- 清理环境 - 清理创建的 worktree,保持工作区整洁
使用方式
使用格式:/fix-comment [PR编号或URL]
示例:
/fix-comment 1358/fix-comment https://github.com/shenjingnan/xiaozhi-client/pull/1358
执行流程
第一步:解析 PR 编号并获取 PR URL
- 如果输入是数字(如
1358),直接使用该 PR 编号 - 如果输入是 PR URL(如
https://github.com/shenjingnan/xiaozhi-client/pull/1358),从 URL 路径中提取最后一部分作为 PR 编号 - 获取 PR 完整信息(包含 URL):
# 获取 PR 完整信息 gh pr view <pr-number> --json url,title,headRefName,state -q '.url'
第二步:获取 PR 信息并创建 worktree
# 获取 PR 对应的分支名
gh pr view <pr-number> --json headRefName -q '.headRefName'
分支名转换规则:
- PR 分支名如
fix/foo→ worktree 目录名fix_foo - 使用
_替换分支名中的/
检查 worktree 是否存在:
# 检查本地是否存在对应的 worktree
git worktree list --porcelain | grep "worktrees/"
# 或者查看 worktree 列表
git worktree list
情况 A:worktree 已存在
- 直接 cd 到 worktree 目录继续执行
情况 B:worktree 不存在,检查本地分支
-
本地已有该分支:
# 创建 worktree(复用已有分支,无需 -b 参数) git worktree add ./worktrees/<dir-name> <pr-branch> -
本地没有该分支:
# 先 fetch 远端分支 git fetch origin # 创建 worktree 并基于远端分支创建本地分支 git worktree add ./worktrees/<dir-name> -b <pr-branch> origin/<pr-branch>
worktree 已存在但有改动:
- 提示用户当前 worktree 有未提交的更改
- 询问是否 stash 继续或终止
远端分支已删除:
- 无法创建 worktree,提示用户
第三步:进入 worktree 目录
cd ./worktrees/<dir-name>
git pull
第四步:获取并分析评论
- 获取 PR # 的所有待解决的评论,主要是 Copilot 的评论
- 分析这些评论是否真的存在问题
- 如果的确存在问题,调整代码
- 如果认为这是无关紧要的问题,或者是过度评论,可以不进行处理
如果分析评论后决定不修复,输出以下通知:
══════════════════════════════════════════════════════════════
PR #<pr-number> 评论分析完成
══════════════════════════════════════════════════════════════
状态: 无需修复
PR 链接: https://github.com/shenjingnan/xiaozhi-client/pull/<pr-number>
原因: <说明为什么不需要修复>
══════════════════════════════════════════════════════════════
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 191 lines · 22 tokens per session scan A 2e04342975ff
fix-comment is a skill published in the GitHub repository shenjingnan/xiaozhi-client (345 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,402 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…