Other skills

Agent skill for agentic-payments - invoke with $agent-agentic-payments

The English summary is being prepared. Showing the original description.

Detects when user requests warrant critical analysis via /advise command

The English summary is being prepared. Showing the original description.

Use when creating or updating a pull request in this repository — how to fill in each section of the PR template with concise, reviewer-friendly content, including the behavior-change table.

The English summary is being prepared. Showing the original description.

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

The English summary is being prepared. Showing the original description.

Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.

The English summary is being prepared. Showing the original description.

Apply an approved sub-skill grouping by moving user-specified skills into a parent bundle, with timestamped backups of every modified directory.

The English summary is being prepared. Showing the original description.

Discover and reorganize the skill inventory into hierarchical sub-skill bundles. Use when the user asks to review, group, or consolidate skills into a parent bundle.

The English summary is being prepared. Showing the original description.

Use when reviewing a pull request in this repository — check the description against the PR template section by section, then run a separate regression and user-impact pass that produces impact levels and a review summary.

The English summary is being prepared. Showing the original description.

Start or end a forked session for exploring rabbit holes without losing the main conversation's context.

The English summary is being prepared. Showing the original description.

Fetch and display diffs for various scopes (PR, commit, branch, staged, working tree). Used by other skills that need to analyze changes.

The English summary is being prepared. Showing the original description.

Create or update a pull request with a structured description.

The English summary is being prepared. Showing the original description.

Iteratively review and fix issues on the current branch until the review passes.

The English summary is being prepared. Showing the original description.

Execute a plan file — parse phases, spawn parallel subagents, handle failures.

The English summary is being prepared. Showing the original description.

Stage changes and create a commit with a conventional commit message.

The English summary is being prepared. Showing the original description.

Amend the last commit with current changes and/or an updated message.

The English summary is being prepared. Showing the original description.

给已经写好的中文去 AI 腔。六段流水线的第二段：输入可以是第一段的产物， 也可以是用户手上任何一篇 AI 生成的稿子。做法是定点修改，不是重写 —— 只动踩线的句子，没踩线的一个字不碰。它只能删掉 AI 腔，补不出人味。 这份文件和 write-cn 一样，刻意写成它要求的那种中文： 指令的版式会被模型当范文，清单腔教出清单腔。

The English summary is being prepared. Showing the original description.

技术博客与公开技术输出的原创性核验：整段正文逐字检索比对来源、全量标题批量筛查、分层抽样给出可复现的命中率，判断内容是原创实践还是未标注的搬运，并与简历经历做时间与内容交叉印证。凡是要评估某人技术写作的真实性或含金量就使用本技能——包括用户说"他博客写得怎么样""这些文章是不是抄的""原创 200 篇是真的吗""公众号/掘金/CSDN 这些内容可信吗"时。

The English summary is being prepared. Showing the original description.

学术、竞赛与资质凭证核验：对论文、专利、竞赛名次、职业证书、开源社区身份、公开 benchmark 成绩逐条比对权威公开源，核对作者顺序、名次分母与定语、专利法律状态、头衔层级，识别申请写成授权、Workshop 写成主会、省略分母等拔高手法。凡是简历上出现可对外部权威源核对的凭证就使用本技能——包括用户说"他这个论文是真的吗""这个竞赛奖含金量如何""专利查得到吗""他说自己是 Committer 靠谱吗"时。

The English summary is being prepared. Showing the original description.

面试官出题技能：基于最难核验或最可疑的经历，生成 3—6 道扎在候选人自己项目具体实现细节上的追问题，通过锚定私有细节、反事实推理、错误前提陷阱、现场量级估算四种机制让通用 AI 难以代答，并附参考答案要点、评分标准、典型错误回答与"答不上来不说明什么"。凡是要为一次面试准备问题就使用本技能——包括用户说"面试该问他什么""帮我准备几个问题""怎么问才能问出他是不是真做过""出几道能压住他的题"时。

The English summary is being prepared. Showing the original description.

批量简历生产线识别：在一批简历中检测版式、句式、项目组合、开源模式的结构性雷同，识别可能出自同一简历工具或培训模板的群体，产出的是"这些共性表述不具备区分度"的提问策略建议，绝不用于淘汰任何候选人。凡是同时面对多份简历要做批量判断就使用本技能——包括用户说"这批简历怎么都长一个样""这几个人是不是一个班出来的""帮我筛一下这十份简历"时。

The English summary is being prepared. Showing the original description.

项目经历真实性与质量核验：核对项目实际代码与简历描述是否吻合、复杂度与声称难度是否匹配、个人贡献边界、是否有真实使用痕迹，并比对同质化项目难度基准表判断简历描述强度是否超出该类项目的典型范围。凡是要判断一个项目的真实分量就使用本技能——包括用户说"这项目有多难""是不是套模板的""这个项目能说明什么水平""他是不是真做过"时。

The English summary is being prepared. Showing the original description.

麦门胃。读你的麦当劳历史订单（无账号走备用问卷），带证据提炼口味规则，确认后生成可携带的个人胃。说「蒸馏我的胃」「饿了」「我们的胃合不合」时用。

The English summary is being prepared. Showing the original description.

Grafana Mimir provider for obz. Covers all 6 metric commands using standard PromQL. Mimir is a horizontally-scalable Prometheus-compatible TSDB. This skill should be used when the user mentions "Mimir", "Grafana Mimir", "obz metric -p mimir", or needs to query metrics from a Mimir cluster.

The English summary is being prepared. Showing the original description.

Elasticsearch provider for obz. Supports log search and trace operations using Elasticsearch Query DSL (Lucene-based). Requires --index flag. This skill should be used when the user mentions "Elasticsearch", "obz -p es", or needs to search logs or traces from an Elasticsearch cluster.

The English summary is being prepared. Showing the original description.