模板
项目与代码模板
invoice-trip-organizer
linson1786-cmd
个人行程与报销 V1.0.7 配置化版本，支持分享与在线升级
ai-startup-due-diligence
PiroteQueen
"Evidence-driven due diligence for AI startups: turns decks, interviews, demos, and public research into an auditable evidence ledger, then derives a verdict and decision documents. Use when evaluating an AI startup or investment target, reviewing a pitch deck or data room, comparing companies' AI products, preparing investor or founder questions, writing a DD memo or IC note, or assessing VC-fit, PMF, GTM maturity, fundability, and red flags."
docx
pascalamiet
"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation."
vault-metadata
teslasoft-de
Frontmatter schema reference, metadata values (status, type, horizon), Dataview query patterns, and repository path integration for the Teslasoft Obsidian vault. Canonical source for all metadata conventions used across note types and templates. Keywords: frontmatter, metadata, status values, type values, horizon, Dataview, query, repoPath, repository path, schema reference
rails-health-audit
srichsun
Audit the health of any Rails codebase and produce a severity-ranked action plan. Use when asked to audit, health-check, scan, or assess a Rails project for security/performance/maintainability issues, or plan a refactor/optimization. A single "audit X" request always means BOTH run the scan AND deliver a filled, prioritized action plan in one go — never hand back a blank template.
VeritasKit
CcXXXXX0630
🔍 学术数据的测谎仪 — 10项统计鉴伪检测（Benford/GRIM/p-curve/Bootstrap），让造假无处遁形
dearcc-jobclaw
skyspeak
Read a completed DearCC intake file or pasted answers, derive a short search brief internally, then return a structured job search request as JSON.
tare
fermionoid
Use this skill when the user explicitly asks to audit, prune, clean, or "tare" their accumulated agent scaffolds — phrases like "run tare", "audit my skills", "tare my scaffolds", "clean up my custom instructions", "my prompts feel bloated". Also appropriate to surface after a major model version has shipped, since past scaffolding tends to become overfit to past model behavior. Walks through the user's scaffolds (skill files, custom instructions, system prompts, slash commands, project rules), judges each one's value vs cost given current model capabilities, proposes KEEP / MODIFY / REMOVE for the user to confirm, then executes the change where the agent has file-system tools — otherwise outputs the exact change for the user to apply manually. Do NOT use for general coding tasks, single-shot prompts, debugging individual outputs, or anything other than explicit scaffold auditing.
core-brain-mula
NachaFromMars
"CoreBrainMula-TieuTam V1.0 — Zero-Decay Neural Memory System. Cài đặt và vận hành NeuralMemory với zero decay (không bao giờ quên), conflict resolution thông minh (tự quyết/hỏi + thông báo), và token budget tối ưu. Use when: (1) Cài NeuralMemory lần đầu, (2) Import MEMORY.md vào neural brain, (3) Phát hiện conflict memory và cần resolve, (4) Query memory với associative recall, (5) Backup/restore brain, (6) Bất kỳ thao tác nào liên quan đến neural memory system."
docs
rahulgi
Agent-first project documentation. Scaffolds and maintains a documentation architecture designed for AI agents — ROADMAP, design-docs, logs, and more. Use when the user says "/docs", asks to set up project documentation, wants to update docs, or when starting a new project that lacks documentation structure. Also use when the user asks to plan a feature (creates a design doc) or review what's been done (updates logs/roadmap).
brooklet-ro-duties-experience
BrookletAdvisory
Draft the "Proposed Duties" and "Relevant Industry Experience" sections of an SFC licence application (Form 6 / RO experience description) for Brooklet Advisory cases. Trigger this skill whenever the user asks to write, draft, prepare or revise the RO duties / experience paragraphs, prepare the Type 1 / Type 4 / Type 9 RO duties and experiences section, write a Form 6 experience description, draft RO 经验段 / RO 经验描述 / 申牌经验段, or apply the Brooklet RO Form 6 SOP. Use this skill AFTER the candidate has been confirmed as suitable to act as RO — for upstream suitability assessment (能不能用、6 年经验、考试豁免、CV vs licence record 核对、比较 RO 候选人) use brooklet-ro-assessment instead.
terraform-aws-annotated-blueprint
Donngi
全プロパティに詳細な解説が付いたTerraform AWSテンプレートを作成する。ユーザーが「/terraform-annotated-aws-blueprint」コマンドで構築したいインフラの概要を入力すると、Terraform Providerスキーマに基づいた正確な属性一覧と、AWS公式ドキュメントに基づく解説を含むテンプレートを生成する。
woocommerce-rest-api
1TeamSoftware
"Comprehensive WooCommerce REST API v3 reference and operational guide. This skill should be used when interacting with WooCommerce stores via HTTP REST API: CRUD operations on products (with variations, attributes, categories, tags, brands, shipping classes, reviews), orders (with notes, refunds, email actions, receipts), customers (with downloads), coupons, shipping zones (with locations and methods), taxes (with classes), payment gateways, settings (all groups including email templates), webhooks, system status and tools, reports, and data endpoints. Also covers the wc-analytics namespace for dashboard analytics, leaderboards, and advanced reporting. Includes authentication methods, batch operations, pagination, filtering, and practical curl examples for every endpoint."
training-deck-builder
OlajideOlagunju
Build role-based walkthrough training slide decks for software tools — produces brand-themed reveal.js HTML decks with real screenshots captured from the running app via Playwright. Use whenever the user asks for training slides, walkthrough decks, tutorial slides, end-user documentation, onboarding decks, or "how to use this app" presentations for a webapp/SaaS tool, even if they don't say the word "skill" or "deck". Trigger on phrases like "training deck", "walkthrough slides", "user training", "role-based tutorial", "how-to slides for the app".
shanxia-photography
r-ayin
杭州写真约拍晚霞山夏摄影杭州约拍杭州独立摄影师杭州个人写真杭州旅拍杭州 cosplay杭州汉服摄影杭州古风写真杭州外景拍摄 AI驱动独立摄影师助理 写真旅拍约拍咨询拍摄指南预约订单管理绑定杭州机位库话术引擎晚霞预测 GEO极致增强版 饺子馆模式Agent间推荐 让其他Agent帮你推荐
template-skill
yonderlab
Replace with description of the skill and when the agent should use it.
elestio
elestio
Deploy and manage services on the Elestio DevOps platform. Use when the user wants to deploy apps, databases, or infrastructure on Elestio, manage projects, services, CI/CD pipelines, backups, domains, firewall, volumes, or billing. Covers 400+ open-source templates across 9 cloud providers.
llm-architecture-tracker
tohnee
Continuously research, analyze, and report on the world's leading large language models — their architecture, capabilities, and pricing. Use this skill whenever the user wants to track, compare, survey, or deep-dive into frontier LLMs (OpenAI/GPT, Anthropic/Claude, Google/Gemini, DeepSeek, GLM/Z.ai, Kimi/Moonshot, Xiaomi MiMo, Qwen, StepFun, Mistral, Llama, NVIDIA Nemotron, MiniMax, and others). Trigger it for requests like "update me on the latest models", "compare model X and Y architectures", "generate an LLM landscape report", "what changed in DeepSeek V4", "build me a model comparison", "track new releases", "what are the top models on OpenRouter", or any request that involves collecting model technical reports / HuggingFace cards / ModelScope / OpenRouter usage + pricing and turning them into a rigorous architecture-and- capability analysis. Also use it to produce the recurring HTML research report. Use this even when the user only names one model or asks a seemingly simple "what's new" question — the value is in the systematic, sourced, architecture-level analysis this skill enforces.
biz-retro-analyzer
dlxeva
Turn conversations, field observations, and follow-up reasoning from complex collaborative projects into evidence-backed analysis of participant understanding, coordination structure, decision traces, reversals, and next-step actions. Use when the user asks to 复盘会后对话, 分析录音, 拆会议纪要, 提炼项目脉络, 做关键判断纠偏, or turn messy conversations into structured facts, judgments, and follow-up actions.
klickdskill-v351
Davincc77
Load a user's portable AI context from a .klickd encrypted file. One soul. Any model. Any body. — Decrypts client-side using AES-256-GCM + Argon2id (v3.0) or PBKDF2 (v2.x legacy), writes fields to /.memory/, and injects agent_instructions into the system prompt as untrusted user context.
vault-templates
teslasoft-de
All 12 Obsidian vault template specifications with key fields, sections, and usage guidelines. Covers Goals, Projects, Areas, Resources, Collab, Science, Skills, Inbox, Archive, CV-Schema, Policy, and Prompt templates. Includes Templater syntax and best practices. Keywords: template, Templater, apply template, use template, template for goal, project template, area template, resource template, create from template
heuristic-template
teslasoft-de
Design iterative document-generation pipelines with rubric-based evaluation. Use when setting up AI-driven content production with quality gates, heuristic evaluation, and revision loops. Applies the Principle of Least Action to minimize iteration cost while maximizing quality.
llm-architecture-tracker
tohnee
Continuously research, analyze, and report on the world's leading large language models — their architecture, capabilities, and pricing. Use this skill whenever the user wants to track, compare, survey, or deep-dive into frontier LLMs (OpenAI/GPT, Anthropic/Claude, Google/Gemini, DeepSeek, GLM/Z.ai, Kimi/Moonshot, Xiaomi MiMo, Qwen, StepFun, Mistral, Llama, NVIDIA Nemotron, MiniMax, and others). Trigger it for requests like "update me on the latest models", "compare model X and Y architectures", "generate an LLM landscape report", "what changed in DeepSeek V4", "build me a model comparison", "track new releases", "what are the top models on OpenRouter", or any request that involves collecting model technical reports / HuggingFace cards / ModelScope / OpenRouter usage + pricing and turning them into a rigorous architecture-and- capability analysis. Also use it to produce the recurring HTML research report. Use this even when the user only names one model or asks a seemingly simple "what's new" question — the value is in the systematic, sourced, architecture-level analysis this skill enforces.
good-looking-html
lorayanglan
Create good-looking self-contained HTML artifacts, single-file HTML pages, visual reports, interactive review surfaces, and PPT-like web decks from notes, outlines, source material, or a topic. Use when the user asks for "Good Looking HTML", "beautiful HTML", "make this into HTML", "HTML artifact", "single-file HTML", "visual report", "interactive page", "web deck", "slide deck", "slides", "presentation", or asks to choose from reusable visual templates. Do not use for ordinary summaries, Markdown-only notes, or generic app development unless the user explicitly wants an HTML artifact or deck.