Art & Design

Local, on-demand maintenance skills for SvelteKit + TypeScript repos — security, performance, refactoring, accessibility, and test coverage

A seven-question post-ship retrospective skill for Claude Code, built around confidence, blind spots, and decay

Drafts and reviews prose for Claude Code — writes new content in the right voice per channel, or scans existing text for AI patterns and rewrites it in an authentic human voice

Installable agent skill for safely configuring FoloToy character personas, opening lines, and voices

中文内容创作 SKILL

y1n-flow · 多模型编排开发流 | A multi-model orchestrated dev workflow for DeepSeek Harness:主代理编排、子代理执行,plan document 为唯一事实源,内置编码验证闭环 / lead agent orchestrates, sub-agents execute, one plan doc as source of truth, built-in review loop

Claude skill: stylize photo into lo-fi doodle style

Evidence-led, Vanguard-policy-safe engineering guidance Skill for League of Legends data integrations. Build compliant tools better.

GLEIF vLEI 信任鏈的可執行沙盒 — A runnable model of the GLEIF verifiable LEI trust chain: real Ed25519, CESR, SAIDs and ACDC edge operators in pure Python, plus a path to a real KERIA stack.

Claude Code skill: build an interactive map of how a topic works in an unfamiliar codebase

可爱的云｜Lovely Cloud — 把云朵照片用极克制的手绘轻轻点出灵气的 AI skill，保留原图天空与留白，不重绘不加水印

Durable, source-grounded project memory skill for AI agents using LWC Wiki, document graphs, and CodeGraph.

HXMPPT — AI Agent PPT skill: local PPTD→PPTX renderer, 44 design systems, draft-first workflow with human review gate (MIT)

A safety-gated Agent Skill for analyzing WizTree CSV exports and cleaning Windows disks in staged, auditable steps.

面向 DeepSeek Harness (DSH) 的浏览器网页搜索技能：通过 Playwright MCP 驱动本机 Edge 打开必应搜索，按可信/可疑/拦截三级安全规则过滤后输出。A browser web-search skill for DeepSeek Harness (DSH) via Playwright MCP + Edge + Bing with three-tier safety filtering.

Self-hosted long-term temporal graph memory for AI agents — MCP, REST and a dashboard in one container, with FalkorDB or Memgraph.

Small, human-approved workflows for AI coding agents.

Free image reading & generation for DeepSeek Harness — paste an image into any chat, even text-only sessions. 免费读图·生图 · 9 种语言 · 无 Key 入库

A judgment layer for AI-made slides — not another PPT generator.

High-fidelity CSS icon to SVG conversion Skill for AI Agents and a deterministic CLI.

Evidence-backed Codex Skill for finding production-scale risks in data-heavy features before they become outages.

面向地质资源与地质工程研究生的 Codex skills 套件。它检索地震勘探与智能地球物理论文，将每日 10 篇开放 PDF 保存到 Obsidian，并生成可直接点击本地原文的中文推荐笔记。

Everything you need to build DeepSeek Harness plugins: official docs archive (EN/ZH), Cordis primer, 15-repo community deep-dive, 20+ battle-tested pitfalls - plus the dsh-plugin-guide agent skill.

Agent Skills - 29 skills for AI agents (Sisyphus, opencode): frontend-perfection (Lighthouse audit), secret-scanner, security-review, version-bumper, commit-lint, coverage-analyzer, api-contract-testing, seo-toolkit, sql-helper, docs-system, code-review, github-repo-hygiene. skill.json manifests, CI, Conventional Commits.