Highest-trust agent skills

Choose, generate and validate agent simulation environments using source-backed guides and structured evidence. Use when comparing stateful simulators, API mirrors, generated environments or world models, designing…

Coding/repo add-on overlay for the agent-memory framework — wizards, doc-gen, QA, fleet, localization, push/pull. Depends on the memory core (agent-memory-system); composes on top for coding agents.

Review the current branch for merge blockers only, using the setkernel reviewer subagent, check each reported blocker yourself, then summarize for the owner. Use when asked to review a branch or PR.

Use when landing a change in a project the user does not own — choosing a repository worth contributing to, checking whether outside pull requests actually merge, opening an issue or a PR, or responding to review.…

This skill should be used when inserting tracked changes (修订模式 / redline revisions) into a .docx document with python-docx + lxml, especially for Chinese official documents that must open cleanly in WPS without the…

Split a job across cheaper and stronger Claude models - the manager plans and talks to the user, runner (Haiku) / researcher (Sonnet) / builder (Opus) do the work, checker (Fable) reviews it before it counts as done.…

Plan and draft a pillar + cluster content set (필러 콘텐츠와 클러스터 콘텐츠) for a WordPress site using the AI Auto Poster abilities: split a seed keyword into one pillar and a few cluster keywords, reject keywords with the same…

INVOKE THIS SKILL when the user asks to 审查代码, 代码质量, 可维护性, AI 味, slop, 重构风险, 安全扫描, Sonar E 到 A, quality gate, ruff/mypy/radon/vulture/coverage, or before committing/refactoring a large change. Runs a unified local…

Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2,…

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step /…

Generate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync),…

Compare scientific agents, check remote laboratory access and verify AI4Science claims using source-backed guides and structured evidence. Use when choosing an AI scientist, literature agent or physical experiment…

在文章好看但用途不清、想让写作回应读者与现实时使用。提供让表达回应真实问题的具体工作流,区分资料依据与现代转译,输出可复核的分析与行动。

在知识库分类混乱、比较不同历史叙述与门类时使用。提供让分类说清材料边界的具体工作流,区分资料依据与现代转译,输出可复核的分析与行动。

薄肌黄毛:把个人成长目标转成可记录、可验证的行动指南。用于用户要求按薄肌黄毛理念制定计划,或结合 AI 工作流、身体习惯、抗评价干扰、职业机会探索做个人行动规划与复盘。侧重低成本实验、反馈和认知更新,不用于诊疗、交易指令或操纵亲密关系。

陪读助手——用户分享书籍/长篇小说/长文后,零跳过完整通读(边读边记、一批一记防失忆),产出结构化"阅读笔记"文件(剧情大纲/人物档案/事件×章节/场景速查表/阅读体验分析),使后续讨论可精确定位到章节与细节、无需重读原文。当用户说"帮我读这本书/读一下/读完它/做下笔记/整理成读书笔记/以后聊到书里内容别忘/按笔记查剧情"或分享电子书(txt/epub 等)时使用。

在观点来自权威或习惯、需要检查自主判断与实际用途时使用。提供让主张接受科学检验的具体工作流,区分资料依据与现代转译,输出可复核的分析与行动。

在儿童学习只有讲解、需要设计安全的观察与做中学活动时使用。提供从生活活动设计学习的具体工作流,区分资料依据与现代转译,输出可复核的分析与行动。

Make a ~35 s 9:16 comedy explainer Short the way the "Bad Days in History" episodes were made (dino extinction, Great Emu War, Titanic): Claude writes the brief, one Opus subagent builds picture + local voice + comedy…

A founder's handbook for Claude Code - the skills, hooks, prompts and workflows I actually run across three companies. 136 entries, each says why it earned its place.

How to correctly drive the Enrichr MCP tools (reverse_engineer_dom, extract_site_profile, extract_design_system, reverse_engineer_animations, reverse_engineer_webgl, extract_assets, interact_with_page, take_screenshot,…

Implement motion graphics as editable code using the available project stack and render a verifiable preview. Use for programmatic animations in web, SVG, canvas, Python, or an existing video-rendering framework.

Turn a document, script or notes into a short animated explainer video (MP4), written as HTML and rendered locally with HyperFrames. Use when the user asks for a motion video, an animated explainer or a "Claude…

Explain unfamiliar code, trace execution paths, plan changes, and check onboarding docs against current source. Use for architecture questions, finding where a change belongs, or verifying codebase claims. Works with or…