Skills
Security-reviewed skills, MCP servers, and toolkits for AI agents. Filter by type, price, and delivery, then install any listing with one command. Every listing is scanned before an agent can run it.
Quality Refinement Autoloop
Run a refinement loop when a Blender result is subpar, user expectations are not met, validation fails, or repeated issues reveal a missing method. The loop freezes the work, captures evidence, diagnoses the failing dimension, decides which existing skill repairs it, records the lesson, and repairs the artifact from the correct baseline.
Claude 3d Harness
Entry point for every 3D or Blender task - modeling, materials, lighting, cameras, rendering, animation, product shots, environments, cinematic scenes, exports. Classifies the job (fast, standard or cinematic), picks a workflow, asks the harness registry which library skills to load, then drives Blender through the harness's single Blender MCP server with render, inspect and refine checkpoints. U…
Blender Research
>
Perfect Loop
Seamless looping 360-degree turntable. First and last frames match perfectly for infinite loop playback.
Text To Blender
Drive Blender from natural language. Converts plain-English requests ("model a sword and render it with cinematic lighting", "make this glass look frosted", "set up three-point lighting", "export this scene as glTF for the web") into Blender Python code executed via the Blender MCP server. Acts as the orchestrator that picks and chain-loads specialised sub-skills (blender-modeling, blender-materi…
Translation Distillation
Distill recurring lessons from a translation project's completed units into its glossary, background, character, and translator-style references. Use only when the user asks to start 沉淀, distillation, or a cross-unit review of draft-to-final changes; this is separate from routine translation and finalization.
Wireframe To 3d
Convert 2D orthographic wireframe PNG drawings to 3D Blender models exported as glTF/GLB. Use this skill whenever the user provides wireframe images (technical drawings, line drawings, orthographic views, side/front/back panels) and wants to generate a 3D model, mesh, or .glb file. Triggers on phrases like "convert this wireframe to 3D", "make a 3D model from these drawings", "build a model from…
Crane Shot
Camera starts low and rises up to reveal the full product. Great for dramatic product reveals on a pedestal.
Blender Rig
>
Blender Coordinator
>
Blender Physics
>
Blender Texture
>
Blender Geonodes
>
Git Sync Upstream
Fork 仓库同步 upstream 最新代码到当前分支，使用 rebase 方式保持提交历史整洁。当用户说"同步upstream"、"rebase upstream"、"更新upstream main"、"拉取upstream更新"、"同步上游仓库"、"fork仓库更新"、"更新PR分支"时触发。自动处理未提交更改（stash/rebase/pop）、fetch upstream、rebase 到最新、强制推送更新 PR。专门用于 fork 仓库同步上游更新的场景，不适用于普通的 git pull 操作。
Git Smart Update
智能 Git 更新工具，支持自动暂存、冲突解决和本地提交处理。当用户说"更新代码"、"拉取最新代码"、"git pull"、"更新当前分支"、"更新所有分支"、"保留本地修改并更新"时触发。自动处理 stash-update-restore 循环，智能解决冲突（优先采用远程改进，同时保留本地调试代码），支持 rebase 和 merge 两种模式。
Code Reviewer Agent
代码审查专家，使用独立上下文的 subagent 执行深度代码审查，覆盖安全漏洞、性能优化和生产可靠性
Trellis Check
Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.
Planning With Files
Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear.
Plugin Creator
Comprehensive plugin development skill for Claude Code. Analyzes business requirements and creates complete plugins including MCP servers, skills, slash commands, or combinations thereof. Supports TypeScript, Python, and any other language. Provides architecture guidance, templates, and end-to-end implementation.
Text To Sql
|
Git Commit
使用约定式提交规范执行 git commit
Bug Analyzer Agent
Bug 根因分析专家，使用独立上下文的 subagent 执行深度代码执行流分析和根因定位
Trellis Before Dev
Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to refresh project conventions and standards.
Obsidian Note Workflow
Use when creating, querying, or managing Obsidian notes with preview-first workflow, intelligent classification, automatic directory creation, and vault initialization
Architecture Patterns
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or when debugging dependency cycles between application layers.
Extension Dev Skill
>-
Daily Report
根据 git 提交记录生成工作日报，支持指定日期查询和智能归类
Tailored Resume Generator
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Trellis Meta
Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents under .trellis/agents/, selectable workflow templates, registry-backed spec refresh, cross-session memory (trellis mem) generated by trellis init, or AI-…
Deep Research
Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.
Trellis Brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.
Maintain Loop
开源项目的维护闭环流程——规划、实现、发布、继续规划的完整循环，以及踩坑沉淀的硬规则。当需要在项目中继续迭代（新功能、修缺陷、补文档）、发布新版本、盘点未完成事项，或有人说「继续」「走维护流程」「按开源流程开发」时使用。
Trellis Update Spec
Captures executable contracts and coding conventions into .trellis/spec/ documents. Use when learning something valuable from debugging, implementing, or discussion that should be preserved for future sessions.
Browser Use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
Github Issue Autofix Workflow
使用 superpowers 工作流修复 GitHub issue。支持自动化模式（用户输入"自动化处理"时全程无需确认）。强制使用 brainstorming 理解需求，test-driven-development 编写测试，verification-before-completion 验证，requesting-code-review 代码审查。适用于用户请求修复 issue、处理 bug、添加功能等场景。
Trellis Session Insight
Reach into past AI conversation history through the `trellis mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-wor…
Cumcm Paper Writer
把已定稿的赛题、建模方案、代码结果与图表写成一篇可提交的全国大学生数学建模竞赛论文：按国赛格式规范组织摘要页、正文、参考文献与附录（含全部源码），遵守匿名与篇幅要求，并用真实获奖论文语料的风格基线把“AI 味”压到人类水平，最后跑格式、风格与数字一致性三重校验。当用户要求“写论文/成文/按国赛格式整理成论文/把结果写成论文/补附录/降低 AI 味”时使用；不负责建模选型、不写求解代码、不做代码检测，也不给奖项位次。
Cumcm Fullflow
数模竞赛全流程总指挥：把“建模 → 方案评审 → 代码实现 → 代码检测 → 结果驱动的模型复盘与优化 → 论文起草/改写/校验”串成一条留痕流水线，每个阶段用全新独立会话完成（评审与检测不得看到作者推理），并在数据确认、模型定稿等关键门禁停下等用户拍板。当用户要求“从赛题一路做到论文”“把整套流程跑完”“重跑某年某题”“帮我组织一条数模流水线”时使用；只要评论文、只要写代码、只要建模等单项任务不要用本技能。
Cumcm Code Reviewer
数学建模参赛代码评价（CUMCM/研赛/美赛/校赛/自定义均可）：用户提供“赛题＋参赛论文＋代码”三项材料后，技能拆题并抽取论文声明的模型/参数/结果口径，逐问核验代码是否兑现，能跑就真跑，输出参考分、逐问分析、可复现结论与具体到文件和公式的问题清单。用于代码自查、参赛材料整体把关、获奖代码审评；只评代码，不单独评论文质量，不给奖项位次。报告按“资格红线＋8 点检测链＋六域二十六项”组织，覆盖正确性、数值稳定性、数据链路、可复现性、工程质量、验证测试与交付合规。
Cumcm Model Review
评价全国大学生数学建模竞赛本科组的模型选择与算法方案。根据赛题、全部题目附件及按小问组织的方案，逐模型和算法联网查证，输出有依据的百分制诊断、具体问题、修改方案和优化脉络。逐问强制重读赛题原文并做四遍分析（抄读/自解/对照/反查），四遍记录是报告的必备部分。适用于建模方案审查、方法适配性评价和方案迭代；不要求完整论文或已完成实验。
Cumcm Code Writer
数学建模竞赛代码编写（CUMCM/研赛/美赛/校赛/自定义均可）：用户给出“数学模型＋采用算法＋模型框架（可选赛题原文与论文提纲）”后，技能先做硬门禁——确认数据是否齐全、本机 Python/MATLAB 与依赖是否可用，缺料缺工具就出《待补清单》并停下；门禁通过才按赛题小问编写竞赛可读风格的代码，固定随机种子，跑三轮自测（跑通／数值与算法正确性／多种子稳定性与论文口径一致），最后生成两份交付物：①符合国赛附录要求的《附录》（支撑材料文件列表＋全部完整源码，逐文件哈希校对）②《结果文档》（逐问结果表＋严谨而具创意的可视化＋运行说明与环境快照）。用于“帮我写这道题的代码／按这个模型和算法实现／生成附录和结果文档”等场景。不写论文正文，不给奖项位次。
Htmx
Build interactive web UIs with htmx by adding hypermedia attributes to HTML and returning HTML fragments from the server. Use when writing or reviewing htmx code, working with hx-* attributes (hx-get, hx-post, hx-trigger, hx-target, hx-swap, hx-boost), wiring AJAX/SSE/WebSocket-driven HTML, or designing server endpoints that respond with HTML partials.
Css Menu
CSS 증상 사전 — 화면이 깨졌을 때 CSS 용어를 몰라도 증상으로 원인을 찾고 고치게 하는 사전. 사용자가 '가운데 정렬이 안 돼요', '스크롤이 두 개예요', '삐져나가요', '버튼이 안 눌려요', '폰에서만 깨져요', '글자가 이상하게 끊겨요', '안 보여요' 같은 화면 증상을 호소할 때, 레이아웃·정렬·간격·글자·겹침·스크롤이 깨졌다고 할 때, 또는 깨진 스크린샷을 보여줄 때 이 스킬을 사용한다. 기획자·디자이너 등 비개발자의 표현('답답해요', '들쭉날쭉해요', '덜컹거려요')도 증상으로 취급해 매핑한다.
Session Mention
Diagnose and fix Claude Code cross-session messaging: sending a message from one live session to another with @<session-name> on the same machine. Use when the user says the @mention isn't working, doesn't autocomplete, or the message went to the wrong session, or asks how to name sessions so they can be addressed, hand work between sessions, or list/attach/stop sessions. Covers naming (--name, /…
Design Brief
Produce a project DESIGN.md so an AI coding agent builds consistent, non-generic UI instead of the default AI look. Use when the user wants a design system, a reusable style brief, to match a reference site's feel, to keep pages consistent, or says the AI's output looks generic. Ships a DESIGN.md template (palette+roles, type, spacing, components, and the reasoning), an anti-slop checklist of the…
Slide Pick
Decide WHAT to draw on each slide before designing a deck. Given a topic and the judgment the audience must make, this picks the right layout, chart, and diagram type, names it, and blocks the choices that mislead. Use when the user asks to make a PPT/deck/발표자료/장표, or asks which chart/layout/diagram to use, or says 'make it clean/fast'. Ships a selection method (판단 문장 → 후보 좁히기 → 금지 규칙), a fill-in…
Edit Doc
Make a document the reader can edit and save right in the browser, with no server, extension, or login. Two kinds: (1) a standalone HTML document that carries its own editor (reports, letters, guides, notices) — copy skeleton.html and write the content; (2) a Markdown document edited in a standalone source+preview editor that saves .md — ship md-editor.html. Use when the user asks for an editable…
App Menu
모바일 앱 UI를 만들 때, 사용자가 컴포넌트를 말로 풀어 설명하거나('아래에서 올라오는 판 만들어줘', '앱 켜면 뜨는 로고 화면', '옆에서 나오는 메뉴', '노치에 안 가리게', '누르면 진동') 정식 이름을 모를 때, 그 말을 정확한 모바일 UI 명칭(바텀시트·스플래시·드로어·세이프에어리어·햅틱 등)으로 옮기고 SwiftUI·Flutter·React Native의 실제 컴포넌트명으로 연결해 준다. iOS·안드로이드 앱 화면/컴포넌트를 만들거나 고칠 때, Expo·Flutter·SwiftUI 작업 중 UI 이름·플랫폼 관례(탭 타깃 44pt·세이프에어리어·모달=풀스크린)를 확인할 때 사용한다. 웹 UI는 ui-menu 를 쓴다.