skills

审计智能体 Loop Engineering 项目的运行就绪度，验证契约、状态、权限、隔离、停止、恢复、独立验证、观测与持续反馈。用于试运行前、失控/停不下来的 loop 复盘、或无人值守上线评审；输出可复现阻断项，不替代业务所有者对高风险动作的批准。

设计或重构项目级智能体 Loop Engineering 系统，覆盖任务筛选、循环架构、契约、状态、工具集、运行编排、验证与持续改良。用于搭建 agent loop、Ralph loop、目标驱动编码循环、定时分流循环或无人值守工程流程；不用于一次性脚本或无法验收的开放式探索。

运行已批准的项目级智能体循环：分流工作项、创建隔离执行环境、编排实施与独立验证、管理状态、处理反馈并安全交接。用于启动、恢复、暂停或收尾已有 Loop 工程，不用于绕过契约、权限或人工闸门。

将自然语言目标写成可机器校验的 Loop 契约：触发、架构、证据、权限、预算、状态转换、停止、断路器与人工批准。用于新建或修订 agent loop、Ralph loop、定时或事件驱动循环的完成定义；不负责选择存储实现。

独立审核 Loop 中实施代理产出的代码、配置、测试和运行证据，并给出可追溯的 pass、reject 或 escalate 裁决。用于源码写入任务在草稿 PR、合并或发布前的独立验证；验证者不得实施同一任务的代码、修改工作树、提交、推送、创建 PR 或合并。

为跨轮次、跨上下文和并行智能体 Loop 设计持久状态、项目记忆、尝试日志、检查点、检索、过期、恢复和并发控制。用于 Ralph/目标驱动循环、隔日续跑、重复失败、记忆污染或多工作项协调；不把完整聊天记录当作状态。

基于 Loop 的失败、审查意见、运行证据、成本、质量与漂移，持续改良项目规则、传感器、测试、文档、记忆和编排策略。用于定期 Loop 复盘、失控/低质量循环治理、文档园艺和工具集演化；不把单次失败未经证据直接固化为全局规则。

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

为编码智能体 Loop 构建可执行的前馈指南、确定性传感器、语义审查、运行时观测、权限控制与分层反馈，并把重复问题固化为规则或工具。用于提高 agent loop 的首次正确率、可验证性和长期可维护性；不负责业务目标定义或任务调度。

评估任务应采用智能体循环、确定性自动化、人工主导还是先补工程基础，并为合格 Loop 选择最小架构与试点边界。用于新 Loop 立项、无人值守任务筛选、成本与风险评估；不负责搭建或运行具体循环。

Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "ponytail-audit", or "/ponytail-audit". One-shot report, does not apply fixes.

Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing.

Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".

Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

Agent 工作台迁移。把任意项目整理成 Claude Code / Codex / Grok 三端一致、可长期维护的 Agent 工作台：审计规则文件、识别真源、统一命名并生成 bridge。 触发方式：/dbs-agent-migration、/agent迁移、「迁移到 Codex」「迁移到 Claude Code」「迁移到 Grok」「统一 AGENTS.md」「整理 skill bridge」「我的 Agent 工作台很乱」「帮我统一 Claude 和 Codex 和 Grok」 Agent workspace migration. Turn any project into a maintainable Claude Code / Codex / Grok three-host workspace by auditing rule files, establishing source-of-truth skills, normalizing names, and generating bridges. Trigger: /dbs-agent-migration, /agent-migration, "migrate to Codex", "migrate to Claude Code", "migrate to Grok", "fix AGENTS.md", "organize skill bridges"

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.

AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.

dontbesilent 执行力诊断。用阿德勒心理学框架诊断你「知道该做什么但就是不做」的真正原因。 触发方式：/dbs-action、/action、「我知道该怎么做但就是不做」「为什么我总是拖延」 Execution block diagnosis using Adlerian psychology framework. Trigger: /dbs-action, "I know what to do but can't do it", "why do I procrastinate"

dontbesilent 对标分析。用五重过滤法帮你找到值得模仿的对标，排除一切关于「我」的噪音。 触发方式：/dbs-benchmark、/对标、「帮我找对标」「我该模仿谁」 Benchmark analysis using dontbesilent's five-filter method. Trigger: /dbs-benchmark, "find me a benchmark", "who should I copy"

dontbesilent 商业工具箱主入口。根据你的问题自动路由到最合适的诊断工具。 触发方式：/dbs、/商业、「帮我看看」 Main entry point for dontbesilent business toolkit. Routes to the right diagnostic skill. Trigger: /dbs, "help me with my business"

dontbesilent 商业模式诊断。两种模式：问诊（消解你的问题）和体检（拆解你的商业模式）。 触发方式：/dbs-diagnosis、/问诊、「帮我看看商业模式」「诊断一下我的业务」「我有个商业问题」 Business model diagnosis using dontbesilent's ontological framework. Two modes: consultation (dissolve your question) and checkup (analyze your business model). Trigger: /dbs-diagnosis, "diagnose my business model", "I have a business question"

把多次 dbs-save 攒下来的诊断状态合并成一份可交付的 markdown 报告。 触发方式：/dbs-report、/出报告、「打包」「整理一份」「给合伙人看的」 Generate a deliverable diagnosis report by merging all dbs-save snapshots. Trigger: /dbs-report, "package this up", "make me a report"

把上次诊断的状态拉出来，接着用。配合 dbs-save 使用。 触发方式：/dbs-restore、/续上、「接着上次」「之前的结论」「上次诊断到哪了」 Restore the most recent diagnosis snapshot saved by dbs-save. Trigger: /dbs-restore, "continue from last time", "where did we leave off"

把当前诊断的关键状态存到本地，下次回来可以接着用。 触发方式：/dbs-save、/存档、「保存这次诊断」「记下来」「这个结论留着」 Save the current diagnosis state to disk for cross-session recall. Trigger: /dbs-save, "save this diagnosis", "remember this"

dontbesilent AI 写作特征识别。扫描文案中的 AI 生成痕迹，输出检测报告。默认只诊断不改。 触发方式：/dbs-ai-check、/AI检测、「帮我看看有没有 AI 味」「检测一下 AI 特征」 AI writing fingerprint detection. Scans copy for AI-generated patterns and outputs a diagnostic report. Diagnosis only by default. Trigger: /dbs-ai-check, "check for AI writing", "does this sound like AI"

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

dontbesilent 内容创作诊断。选题通过后，诊断怎么把这个选题做成好内容。 触发方式：/dbs-content、/内容诊断、「这个内容怎么做」「帮我看看这个文案」 Content creation diagnosis. After topic passes, diagnose how to turn it into good content. Trigger: /dbs-content, "how should I create this content", "review my copy"

dontbesilent 内容结构化系统。把本地大量文稿、推文、选题、案例和课程稿搭成一个可持续生长的内容结构化工程：先审计内容规模与边界，再建立新工程、复制素材、抽取内容单元、生成主题地图与选题装配稿。 触发方式：/dbs-content-system、/内容结构化系统、「把我的内容做成结构化系统」「把本地素材变成可重组系统」「帮我搭内容资产工程」「我想把旧内容变成可复用资产」 Content structuring system. Audits local content volume, then builds a reusable content knowledge project with units, topic maps, and assembly drafts. Trigger: /dbs-content-system, "build a content structuring system", "turn my archive into reusable assets"

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 11 color palettes and 7 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".

Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or improve article layout. Outputs to {filename}-formatted.md.

生成横向翻页网页 PPT（单 HTML 文件），含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格：① "电子杂志 × 电子墨水"（衬线 + 流体背景 + 暖色） ② "瑞士国际主义"（无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮）。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT，或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss Style"、"horizontal swipe deck"时使用。

Generate Guizang-style social card image sets and WeChat official account cover pairs from articles, scripts, screenshots, product notes, subtitles, or photos. Use when the user asks for 小红书图文, Rednote/Xiaohongshu images, social cards, carousel images, 3:4 covers, 微信公众号封面, WeChat 21:9 + 1:1 covers, Swiss Style, or magazine-style social images.

dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式：/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Short video opening optimization with diagnosis and solutions. Trigger: /dbs-hook, "optimize my opening", "how to write opening"

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。

Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".

数字生命卡兹克（Khazix）的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于：写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说"帮我把这个写成文章"或"用我的风格写一下"，只要上下文涉及内容创作和公众号输出，都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说"帮我写篇文章"的场景。不要用于短内容（小红书帖子、推特、朋友圈）或纯标题摘要生成（那个用wechat-title skill）。

Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, Mermaid (rendered to PNG via headless Chrome), PlantUML, footnotes, alerts, infographics, and optional bottom citations for external links. Use when user asks for "markdown to html", "convert md to html", "md 转 html", "微信外链转底部引用", or needs styled HTML output from markdown.

Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "贴图/图文/文章".