AI Agent Skills

去AI味改写助手。当用户说"去AI味""帮我改得不像AI""这段太AI了""humanize""降AI率" "改得像真人写的""去机器味""文案太生硬了""读起来像AI写的"时触发。 也适用于用户说"帮我改稿""润色一下"且上下文暗示文本有AI生成痕迹的场景。 逐句扫描文本中的AI写作痕迹，按六步流程改写为真人风格，输出对照报告和改写后…

Jacky 的短视频开头优化工具。基于谜题理论 + 实战经验，诊断开头问题并生成优化方案。 触发方式：/jacky-hook、「帮我优化开头」「开头怎么写」「这个开头行不行」「帮我改开头」「开头没吸引力」 Short video opening optimizer. Diagnoses issues and generates hook…

把 AI 对话中有价值的内容沉淀到 Obsidian 知识库。 检索知识库内容回答问题，只基于已有内容，不杜撰。 触发方式：/jacky-wiki、「存到知识库」「沉淀一下」「这个记下来」「知识库里有没有…」 Save valuable AI conversation content to the Obsidian knowledge…

小红书敏感词检查助手。当用户说"帮我查敏感词""小红书违禁词检查""检查下这篇笔记有没有敏感词" "小红书合规检查""笔记审查""文案排查""查一下有没有违规"时触发。 将用户的小红书笔记文案逐句排查，对照小红书社区规范和高危词库， 找出潜在的敏感词、违规词和风险点，输出详细的检查报告并给出修改建议。

Generate personalized greetings. Use when asked to greet someone or create welcome messages.

A valid test skill for unit testing

Write or revise Labtasker's README and user documentation, especially product positioning, tutorials, guides, examples, case studies, and navigation. Preserve the projec…

Use Labtasker v2 to queue and run independent ML inference, evaluation, or experiment Tasks; migrate pipelines; design routes and Workers; inspect Task demand and Worker…

Change Labtasker's public Task lifecycle, HTTP API, Python API, CLI, configuration, query language, or persisted schema while keeping every public surface and invariant…

Develop and regression-test Labtasker's public Agent Skill with concise real-user requests, independent examiner and candidate agents, outcome checks, and bounded self-r…

Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.

Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential, publish, deploy,…

Use when a human explicitly asks for a full repository agent-compatibility pass returning a scored report with prioritized fixes. Not for tasks that require source or re…

Use when setting up a project, auditing agent command permissions, or asking which read-only bash commands and domains to allow. Not for remote, credential, publish, dep…

Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or profiling a CLI: u…

Use when the user asks to make the skills framework work in a new harness, IDE, or CLI. Not for remote, credential, publish, deploy, or irreversible changes.