Menu
SkillsMP has collected 31 skills from suphiozdedee/projenicdesign.com. Open a skill to review its source and details.
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/suphiozdedee/projenicdesign.com.Showing 31 of 31 collected skills.
Run protected AAS maintainer sweeps, PR merge batches, canonical sync, Core preview checks, and scripted releases. Use for repository maintenance, main alignment, CLI/MCP/Workbench changes, or release work; not ordinary contribution tasks.
把用户上传的 Logo、人物头像、个人形象、IP 角色、插画、产品照片或标志性物件，扩展成一套统一的视觉身份提示词。用户提到一张图做品牌全案、个人品牌视觉、头像延展、IP 设定、品牌主视觉、包装周边、社交媒体视觉，或要求保持参考图一致性生成多场景图片时使用。默认输出视觉 DNA 卡和一组可直接生图的完整提示词；有生图工具且用户明确要求时可继续生成图片。
Source text: Chinese
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK. ACTIVATE this skill when the user wants to create, configure, or orchestrate Google Antigravity agents.
Plan and generate a conversion-oriented image-ad set in two phases: approve a hero concept and copy direction, then fan it out into platform formats.
Generate on-brand social or advertising image candidates from a confirmed brand system and asset library, with explicit compliance checks.
Combine multiple authorized portraits into a coherent group scene while preserving each person's likeness, placement, and consent boundaries.
Edit or transform a supplied image while preserving the specific people, products, composition, or brand details the user marks as fixed.
Apply a bounded image-enhancement operation such as upscaling, background removal, extension, or cleanup while preserving the intended subject.
Turn a creative brief into a bounded set of text-to-image or reference-guided image candidates, selecting the MuAPI model and parameters for the actual job.
Establish reusable brand, asset, platform, rights, and delivery context for repeatable image-production work.
Turn a story premise into an ordered set of visual keyframes with continuity notes, without generating video or audio.
Route a broad creative brief into the smallest useful general or specialist image workflow, coordinate MuAPI calls, and return one evidence-backed production plan.
Visualize decluttered, redesigned, or staged interiors while preserving room geometry and separating concepts from property claims.
Explore logos, wordmarks, symbols, and compact brand identity directions from approved brand inputs, with legibility and trademark-review gates.
Re-render an authorized subject, product, or scene from selected camera angles while preserving the approved parent asset.
Restore damaged, faded, noisy, or low-resolution photographs while distinguishing recovered detail from model reconstruction.
Generate a themed pack of portraits from an authorized identity reference while locking likeness and varying only the requested scene or styling.
Plan and produce truthful ecommerce, marketplace, reseller, or commercial product-image sets from approved SKU references, with channel-specific QA and provenance.
Produce consent-based professional portrait and headshot sets from authorized identity references, with controlled styling and identity QA.
Reframe one approved hero image into platform-specific social formats while preserving the subject, palette, and visual identity.
Produce a small set of truthful, high-contrast video or article thumbnail directions with platform-aware composition and text-safe space.
Create high-fidelity mobile or web interface mockups and lightweight design-system boards from a product brief, with accessibility and implementation handoff notes.
Create clearly labeled garment-on-person visualization drafts while preserving authorized person and garment details.
Operate 20+ penetration-testing tools (Nmap, Nuclei, SQLMap, FFUF, Hashcat, and more) through structured workflows with consistent output handling.
Source text: Mixed languages
Bug-bounty/SRC vulnerability-hunting workflow: five-phase methodology (intake, recon, enumeration, hunt, report) with attack playbooks for SQLi, XSS, RCE, SSRF, IDOR, CSRF, path traversal, and file upload.
Source text: Mixed languages
网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。
Source text: Chinese
长篇网文规划与写作。支持只讨论结构、只写大纲或指定细纲，明确要求正文后再写章节。触发方式：/story-long-write、/写长篇、「帮我开书」「规划剧情」「写大纲」「补细纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。
Source text: Chinese
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。
Source text: Chinese
网文写作工具集基础设施部署与检查。为 Claude Code / OpenCode / Codex / Google Antigravity / ZCode / OpenClaw / Reasonix 提供内置适配；Web AI / 通用 Agent 可走 skills + AGENTS.md 文件模式。触发方式：/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」「检查写作环境」。
Source text: Chinese
短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。
Source text: Chinese
网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可管理作者习惯、启动本地 Dashboard。触发方式：/story、$story、/story dashboard、/网文、「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」。
Source text: Chinese