用于【女频爱情】题材下的故事设定审阅任务。作为题材包装层、兼容入口与路由层，负责保留女频爱情入口，补充情绪锚定、成长线优先、关系拉扯、柔爽感与现实共鸣边界，并明确要求加载并使用 `通用-审阅故事设定`。
用于【异能志怪】题材下的知乎平台输出任务。作为题材包装层、兼容入口与路由层，负责保留异能志怪入口、补充规则链与现实解释边界，并明确要求加载并使用 `通用-输出知乎版`。关键词：异能志怪知乎版、知乎盐选、规则链、现实解释。
用于把小说章节改写为更适合纵横小说网的版本。适合中等节奏、现实锚点扎实、慢热逻辑推进、人性落点显化与克制悬念渲染的正文输出；供多个题材的 `题材名-输出纵横小说版` 包装层路由使用。关键词：输出纵横小说版、纵横中文网、中等节奏改写、男频悬疑平台。 — from lornshrimp/Lorn.NovelWriteSkills
用于【都市职场】题材下的故事设定、手法、程序链与证据载体设计。作为题材包装层、兼容入口与路由层，负责保留都市职场入口名、补充都市程序摩擦、异常证据与现实代价边界，并明确要求加载并使用 `通用-设计故事设定`。关键词：都市职场故事设定、程序链、证据载体、规则代价。
用于把小说章节改写为更接近传统出版社审稿口味的版本。适合强调文笔克制、逻辑自洽、出版可读性、结构完整与审读友好的正文输出；供多个题材的 `题材名-输出出版社版` 包装层路由使用。关键词：输出出版社版、传统出版、纸媒投稿、出版社风格。 — from lornshrimp/Lorn.NovelWriteSkills
用于【都市悬疑】题材下的连续性、旧线回收与冷热线管理。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口名、补充旧案回声、关系余波、证据链不断点与回归压力判断，并明确要求加载并使用 `通用-管理连续性冷热线`。关键词：都市悬疑连续性、旧线回收、冷热线、回归窗口、证据链不断点。
用于设计、筛选、重排和审计小说书名。适合为全书、分部、分卷或多平台版本生成真正像书名的候选标题，并形成可复盘的命名方案。关键词：设计书名、书名候选、平台适配书名、标题 Rubric、命名方案。
用于将“微信订阅号/”目录内指定章节批量上传到微信公众平台（订阅号）后台并保存为草稿。支持按 README.md 读取账号、密码、作者笔名、小说名称与微信书籍ID，自动执行登录、获取本次会话…
用于把小说章节改写为更适合七猫平台的版本。适合强调免费阅读、直给反馈、强情节推进、追读驱动与平台节奏压缩的正文输出；当前先承接已存在题材，后续可供更多题材复用。关键词：输出七猫版、七猫免费小说、七猫平台、免费阅读改写。 — from lornshrimp/Lorn.NovelWriteSkills
指定トピックについてWebから情報収集し、ナレッジとして保存。日本語・英語の並列検索で網羅的に調査。Use when: 「調べて」「リサーチ」「○○について調べて」「情報収集」 — from yut0takagi/claude-code-plugin-demo
指定トピックについてWebから情報収集し、ナレッジとして保存。日本語・英語の並列検索で網羅的に調査。Use when: 「調べて」「リサーチ」「○○について調べて」「情報収集」 — from yut0takagi/claude-code-plugin-demo
用于以默认极严、保守、负面证据优先的口径评估作品在目标平台的签约或过稿潜力。适合统一承接评估流程骨架、分阶段准入评估、材料完整度判断、评分维度、概率区间、封顶与一票否决规则，并兼容竞争位 / 竞品威胁评估语境。评估起点项目时，强制要求使用多种可用网络搜索工具检索起点中文网同题材榜单前十作品并做从严对照。关键词：平台签约评估、极严评估、分阶 — from…
用于【女频爱情】题材下的书评撰写任务。作为题材包装层、兼容入口与路由层，负责保留女频爱情入口，补充情绪锚定、成长线优先、关系拉扯、柔爽感与现实共鸣边界，并明确要求加载并使用 `通用-撰写书评`。
用于【异能志怪】题材下的作者有话说、章后小剧场与读者沟通润色。作为题材包装层与路由层，负责保留异能志怪标准入口名，补“一个微异细节 + 一点余波 + 一个小问题”的章后口感，并明确要求加载并使用 `通用-润色作者有话说`。
用于【异能志怪】题材下的书名设计、筛选、重排与多平台适配。作为题材包装层、兼容入口与路由层，负责保留异能志怪入口名，补充都市异术、民俗异象、职业规矩与现实危险感，并明确要求加载并使用 `通用-设计标题`。 — from lornshrimp/Lorn.NovelWriteSkills
用于把小说章节改写为更适合番茄小说网的版本。适合免费阅读平台、强钩子、快反馈、高完读率正文输出；供多个题材的 `题材名-输出番茄版` 包装层路由使用。关键词：输出番茄版、番茄小说网、番茄化改写、免费阅读平台。 — from lornshrimp/Lorn.NovelWriteSkills
用于【都市悬疑】题材下的章节创作 SOP 编排。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口名，并明确要求加载并使用 `通用-章节创作闭环`，同时锁定题材写作链、程序证据连续性、城市压迫感与批量回炉护栏。
用于【女频爱情】题材下的内容简介撰写任务。作为题材包装层、兼容入口与路由层，负责保留女频爱情入口，补充情绪锚定、成长线优先、关系拉扯、柔爽感与现实共鸣边界，并明确要求加载并使用 `通用-撰写内容简介`。
用于强化章节开头前 150–300 字的入场抓力。适合章首抢救、首屏留存优化、异常前置、冲突前置与只修前两三段的局部强化。关键词：强化开头、章首抓人、前 150–300 字、首屏留存、开头太慢、只修前两段。 — from lornshrimp/Lorn.NovelWriteSkills
用于润色已有章节正文。适合整章精修、局部重写、节奏提纯、章首抓力增强、中段回报提亮与章末钩子收紧。关键词：润这章、精修正文、整章精修、局部重写、节奏提纯、直接回写。 — from lornshrimp/Lorn.NovelWriteSkills
用于【都市悬疑】题材下的七猫平台输出任务。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口、补充直白短叙、普通人共情、生活化悬念与章末翻页边界，并明确要求加载并使用 `通用-输出七猫版`。关键词：都市悬疑七猫版、七猫、直给反馈、追读。
用于【异能志怪】题材下以默认极严、保守、负面证据优先的口径评估作品的平台签约、过稿与连载潜力。Use when:…
Consult the current state of practice before doing expert work — search a federated catalog of vetted agent skills, read the ones that matter as field notes, install only what…
用于【都市悬疑】题材下的题材定位、卖点校准与入口判断。作为题材包装层与路由层，负责保留都市悬疑入口名、补充职业抓手、异常证据、程序摩擦、现实代价与平台主口径，并明确要求加载并使用 `通用-设计题材定位框架`。
用于【女频爱情】题材下的总大纲审阅任务。作为题材包装层、兼容入口与路由层，负责保留女频爱情入口，补充情绪锚定、成长线优先、关系拉扯、柔爽感与现实共鸣边界，并明确要求加载并使用 `通用-审阅总大纲`。
用于【女频爱情】题材下的投稿材料组包任务。作为题材包装层、兼容入口与路由层，负责保留女频爱情入口，补充情绪锚定、成长线优先、关系拉扯、柔爽感与现实共鸣边界，并明确要求加载并使用 `通用-组包投稿材料`。
Help users create high-quality skills by discovering and incorporating proven methodologies from domain experts.
Session-start meta-skill that enforces the 1% rule: before any action on a processkit entity or context/ file, if there is even a 1% chance a processkit skill applies, you MUST…
Use this skill to evaluate whether a skill is ready for enterprise-wide publish in the Nava Skills Marketplace.
This skill should be used after running cortex assess skill (or the cortex sessions skillinvestigate pipeline that produces PR 3's SkillIncidentEvidence) to analyze…
Use after completing a repeated or newly stabilized workflow, when the user asks to 沉淀 skill, 自动迭代 skill, 技能孵化, 把常用事情变成 skill, or when a task pattern appears reusable enough to…
Use this skill whenever the user wants to create, write, draft, scaffold, review, fix, or improve a SKILL.md file — the metadata + instructions file that defines an Agent Skill.
This skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality report".
Use when reviewing how skills performed during a session, when the user wants to analyze skill invocations and identify improvements, or when the user says "skill retro", "review…
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery. — from general/agents-skills-meta
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery. — from bg-szy/TOP-SKILLS
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery. — from bg-szy/TOP-SKILLS
Interview-driven automation design tool. This skill should be used when the user wants to design a new skill, agent, automation, shortcut, or any other automatable workflow.
A written house style for Claude Code skill-marketplace SKILL.md and README.md files — frontmatter rules, trigger-rich descriptions, Phase/Step body skeletons, recurring honesty…
Validates skills against production-level criteria with 9-category scoring. This skill should be used when reviewing, auditing, or improving skills to ensure quality standards.
Audit and sync Claude Code and Codex CLI configurations so both tools share the same instructions, skills, subagents, MCP servers, hooks, and permission intent.
Your visual catalog of every skill and plugin installed in this CoWork workspace. Use this skill when the user asks to see their system, view installed skills, check what's…
This skill should be used when the user asks to "add a task", "create a Todoist task", "complete a task", "mark task as done", "update a task", "delete a task", "show my tasks",…
Submit feedback about the TRES Claude plugin — bug reports, feature requests, skill improvements, new skill ideas, MCP issues, workflow friction, or positive feedback about what's…
Use this whenever the user mentions Universal AI Skills, skill-router, router, route to a skill, unknown skill names, or wants the best skill selected automatically.
Use this skill specifically when asked by the user to "manage universal skills", not for general coding. Skill Management Orchestrator.
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Download screenshot baselines from the latest CI run and commit them. Use when asked to update, accept, or refresh component screenshot baselines from CI, or after the…
Re-anchor the discipline of actually using the skills available to you — scan the in-context skill listing, map the conversation and the task to the skills that fit, and invoke…
Use this skill before committing ANY code change — this is a mandatory gate in the commit flow. Also trigger proactively when: you've made changes across multiple files and want…
Skill-creation and evaluation coach for the Divan marketplace ("training a new vizier"). Use when the user wants to add, improve, benchmark or test a skill, write a SKILL.md,…
Use as the minimal v6-conformant codebase-grounded fixture for skill-graph package tests. Activate this skill when verifying that lint enforces grounding requireds (domain_object,…
Use this skill to evaluate and review a candidate skill before installing it. Triggers on: 'evaluate skill', 'review skill', 'should I install this skill', 'skill trust check',…
Ship-readiness pass: review, fix, and validate working copy or PR changes. This skill should be used when asked to finalize, harden, do a final pass, or make code shippable.
Use this skill when the user asks to fuzz, stress-test, property-test, or find crashes in existing code. Runs fast-check property-based fuzzing on module exports.
Brief description of what this skill does. Include specific triggers - when should Claude use this skill? Example triggers, file types, or keywords that indicate this skill…
Orchestrate a multi-model code review: spawn 3 review subagents, merge findings. In PR mode, posts GitHub PR comments with reactions. In local mode, outputs findings directly.
Search and select a Claude Code skill in the terminal, then copy /skill to clipboard.
Use when creating, updating, or improving agent skills.
Runs the full development cycle by invoking task-decomposer, task-worker, and work-reviewer subagents each in a separate agent context (not in one agent).