Skip to main content
LongLeo287
GitHub 创作者资料

LongLeo287

按仓库查看 3 个 GitHub 仓库中的 1,022 个已收集 skills。

已收集 skills
1,022
仓库
3
更新
2026年8月4日
仓库浏览

仓库与代表性 skills

domain-skills-library
综合办公文员

Multi-domain skill reference collection covering ai-integration, databases, finance, frontend, google-workspace, and POS systems. Each domain contains reference docs, best practices, and agent skill blueprints.

2026年4月11日
deep-research
信函文员

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

2026年4月11日
notebooklm-mcp
软件开发工程师

Localized RAG and Notebook injection via MCP

2026年4月11日
azure-appconfiguration-ts
软件开发工程师

Build applications using Azure App Configuration SDK for JavaScript (@azure/app-configuration). Use when working with configuration settings, feature flags, Key Vault references, dynamic refresh, or centralized configuration management.

2026年4月11日
azure-cloud-migrate
软件开发工程师

Assess and migrate cross-cloud workloads to Azure with migration reports and code conversion guidance. Supports AWS, GCP, and other providers. WHEN: migrate Lambda to Azure Functions, migrate AWS to Azure, Lambda migration assessment, convert AWS serverless…

2026年4月11日
go-concurrency-patterns
软件开发工程师

Master Go concurrency with goroutines, channels, sync primitives, and context. Use when building concurrent Go applications, implementing worker pools, or debugging race conditions.

2026年4月11日
godot-gdscript-patterns
软件开发工程师

Master Godot 4 GDScript patterns including signals, scenes, state machines, and optimization. Use when building Godot games, implementing game systems, or learning GDScript best practices.

2026年4月11日
hivefiver-ralph-tasking
项目管理专家

Convert HiveFiver plans and TODO state into Ralph PRD JSON and beads graphs with enriched related entities and anti-pattern validation.

2026年4月11日
已展示 8 / 542 个已收集 Skill。
html-ppt
网页开发工程师

HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片", "演讲稿", "做一份 PPT", "做一份 slides", a…

2026年8月4日
yao-meta-skill
其他计算机职业

Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.

2026年8月4日
book-to-skill
其他计算机职业

Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document…

2026年8月4日
seedance-20
影片与视频编辑

This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface - Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink,…

2026年8月4日
seedance-copyright
影片与视频编辑

This skill should be used when a Seedance 2.0 prompt mentions named characters, franchises, studios, celebrities, public figures, private people, brand logos, copyrighted scenes, songs, voices, or real-person likeness workflows and needs an IP-safe rewrite.

2026年8月4日
seedance-filter
影片与视频编辑

This skill should be used when a Seedance 2.0 prompt is blocked, rejected, silently degraded, or likely to trigger a content filter; or when the user asks for a safer rewrite without losing the creative intent.

2026年8月4日
seedance-interview-short
影片与视频编辑

This skill should be used when the user wants a fast Seedance 2.0 creative brief, a short interview, a compressed intake flow, or a quick director-style clarification before prompt writing.

2026年8月4日
seedance-vocab-en
技术写作员

This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.

2026年8月4日
已展示 8 / 465 个已收集 Skill。
anti-slop-visual
未分类

Diệt "AI slop" trong PROMPT ẢNH/VIDEO của SEOSONA Flow — chuyển phương pháp no-ai-slop (liệt kê cụm tố-cáo cần cấm) từ văn xuôi sang THỊ GIÁC. Dùng khi viết/tinh prompt gen, review prompt trong kho, hoặc làm node prompt tự động: cấm token sáo rỗng…

2026年8月3日
build-capability
未分类

Tham chiếu "tự dựng năng lực từ đầu" cho SEOSONA — chưng cất pattern từ build-your-own-x cho các thứ SEOSONA hay cần: CLI/sidecar, parser/interpreter (DSL workflow), local search (prompt/memory), storage/query layer. Dùng khi cần tự viết 1 công cụ nền (không…

2026年8月3日
character-consistency
未分类

Giữ NHÂN VẬT / PHONG CÁCH nhất quán qua nhiều ảnh khi gen loạt trong SEOSONA Flow — định nghĩa 1 khối CHARACTER/STYLE tái dùng verbatim, dựng bộ góc chuẩn, và chèn khối đó vào MỌI prompt cảnh sau. Dùng khi user muốn 1 nhân vật/KOC/mascot giữ y hệt diện mạo…

2026年8月3日
flow-mcp
未分类

Cách lái SEOSONA Flow (gen ẢNH/VIDEO/b-roll) qua Local MCP server (mcp-local/) — cho agent HOẶC SEOSONA Video AI V2 gọi. Dùng khi cần sinh visual asset từ ngoài extension (Claude Code/Cursor/V2), chọn tool đúng (discovery→gen/run_workflow), đọc envelope…

2026年8月3日
image-qa
未分类

QA ảnh AI-generated TRƯỚC khi dùng cho SEOSONA Flow — kiểm tay/mặt/chữ-rác/watermark/style + đối chiếu CHÍNH TẢ chữ trong ảnh (OCR-diff vs chuỗi đích) + check ở cỡ thumbnail, rồi ra verdict ACCEPT / REGENERATE / OVERLAY kèm 1 fix cụ thể. Dùng khi user muốn…

2026年8月3日
img-to-3d
未分类

Dựng lại vật thể trong 1 ảnh tham chiếu thành model Three.js CODE-ONLY, procedural, animation-ready (không depth-map/point-cloud/photogrammetry). Dùng khi user muốn biến 1 ảnh sản phẩm/vật thể thành scene 3D web nhẹ, hoặc cần asset Three.js sinh bằng code.…

2026年8月3日
interview-to-spec
未分类

Chống brief mơ hồ khi gen ẢNH/VIDEO ở SEOSONA Flow — model PHỎNG VẤN người dùng tới khi đủ thông tin rồi mới viết spec/prompt (mượn pattern "interview-to-spec" của Claude prompt-library). Dùng khi yêu cầu gen còn thiếu (chủ thể/bối cảnh/tỉ lệ/phong cách/mục…

2026年8月3日
mllm-judge
未分类

Quality-gate ảnh/clip AI cho SEOSONA Flow bằng MLLM-as-judge — chấm theo rubric (bám prompt / chất lượng motion & temporal / thẩm mỹ / artifact-vật-lý) với pre-filter rẻ bằng JS trước khi tốn model. Dùng khi cần cổng chất lượng tự động trong pipeline gen…

2026年8月3日
已展示 8 / 15 个已收集 Skill。
已展示 3 / 3 个仓库
已展示全部仓库